From e1c753d29405ce751577294e5cca297c6e46a3da Mon Sep 17 00:00:00 2001 From: Dmitry Ryumin Date: Fri, 26 Jan 2024 00:39:17 +0300 Subject: [PATCH] Summary --- json_data/3d-from-multi-view-and-sensors.json | 2002 ------- json_data/3d-from-single-images.json | 102 - json_data/adversarial-attack-and-defense.json | 1527 ------ json_data/autonomous-driving.json | 1727 ------ json_data/biometrics.json | 277 - json_data/computational-imaging.json | 1327 ----- .../computer-vision-for-social-good.json | 127 - json_data/computer-vision-theory.json | 127 - json_data/datasets-and-evaluation.json | 1352 ----- ...learning-architectures-and-techniques.json | 2302 -------- .../document-analysis-and-understanding.json | 302 -- json_data/efficient-and-scalable-vision.json | 1202 ----- ...odied-vision-active-agents-simulation.json | 352 -- json_data/explainable-ai-for-cv.json | 602 --- json_data/explainable-computer-vision.json | 602 --- ...ge-and-video-synthesis-and-generation.json | 4627 ----------------- ...ine-learning-other-than-deep-learning.json | 352 -- ...and-biological-vision-cell-microscopy.json | 1302 ----- json_data/multi-modal-learning.json | 2227 -------- json_data/multimodal-learning.json | 2227 -------- .../navigation-and-autonomous-driving.json | 1727 ------ ...tion-methods-other-than-deep-learning.json | 302 -- json_data/others.json | 302 -- .../photogrammetry-and-remote-sensing.json | 202 - ...physics-based-vision-and-shape-from-x.json | 302 -- json_data/robotics.json | 577 -- .../scene-analysis-and-understanding.json | 1352 ----- ...mentation-grouping-and-shape-analysis.json | 2777 ---------- ...-unsupervised-representation-learning.json | 1777 ------- ...countability-privacy-ethics-in-vision.json | 752 --- .../video-action-and-event-understanding.json | 2052 -------- ...ow-level-analysis-motion-and-tracking.json | 1152 ---- json_data/vision-and-graphics.json | 802 --- .../vision-applications-and-systems.json | 877 ---- json_data/vision-language-and-reasoning.json | 402 -- 35 files changed, 40020 deletions(-) delete mode 100644 json_data/3d-from-multi-view-and-sensors.json delete mode 100644 json_data/3d-from-single-images.json delete mode 100644 json_data/adversarial-attack-and-defense.json delete mode 100644 json_data/autonomous-driving.json delete mode 100644 json_data/biometrics.json delete mode 100644 json_data/computational-imaging.json delete mode 100644 json_data/computer-vision-for-social-good.json delete mode 100644 json_data/computer-vision-theory.json delete mode 100644 json_data/datasets-and-evaluation.json delete mode 100644 json_data/deep-learning-architectures-and-techniques.json delete mode 100644 json_data/document-analysis-and-understanding.json delete mode 100644 json_data/efficient-and-scalable-vision.json delete mode 100644 json_data/embodied-vision-active-agents-simulation.json delete mode 100644 json_data/explainable-ai-for-cv.json delete mode 100644 json_data/explainable-computer-vision.json delete mode 100644 json_data/image-and-video-synthesis-and-generation.json delete mode 100644 json_data/machine-learning-other-than-deep-learning.json delete mode 100644 json_data/medical-and-biological-vision-cell-microscopy.json delete mode 100644 json_data/multi-modal-learning.json delete mode 100644 json_data/multimodal-learning.json delete mode 100644 json_data/navigation-and-autonomous-driving.json delete mode 100644 json_data/optimization-methods-other-than-deep-learning.json delete mode 100644 json_data/others.json delete mode 100644 json_data/photogrammetry-and-remote-sensing.json delete mode 100644 json_data/physics-based-vision-and-shape-from-x.json delete mode 100644 json_data/robotics.json delete mode 100644 json_data/scene-analysis-and-understanding.json delete mode 100644 json_data/segmentation-grouping-and-shape-analysis.json delete mode 100644 json_data/self-supervised-or-unsupervised-representation-learning.json delete mode 100644 json_data/transparency-fairness-accountability-privacy-ethics-in-vision.json delete mode 100644 json_data/video-action-and-event-understanding.json delete mode 100644 json_data/video-low-level-analysis-motion-and-tracking.json delete mode 100644 json_data/vision-and-graphics.json delete mode 100644 json_data/vision-applications-and-systems.json delete mode 100644 json_data/vision-language-and-reasoning.json diff --git a/json_data/3d-from-multi-view-and-sensors.json b/json_data/3d-from-multi-view-and-sensors.json deleted file mode 100644 index bc35396..0000000 --- a/json_data/3d-from-multi-view-and-sensors.json +++ /dev/null @@ -1,2002 +0,0 @@ -[ - { - "title": "NeuMap: Neural Coordinate Mapping by Auto-Transdecoder for Camera Localization", - "base_url": null, - "title_page": null, - "repo": "Tangshitao/NeuMap", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_NeuMap_Neural_Coordinate_Mapping_by_Auto-Transdecoder_for_Camera_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11177", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "u4DGwkXuJXA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Object Pose Estimation with Statistical Guarantees: Conformal Keypoint Detection and Geometric Uncertainty Propagation", - "base_url": null, - "title_page": null, - "repo": "NVlabs/ConformalKeypoint", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Object_Pose_Estimation_With_Statistical_Guarantees_Conformal_Keypoint_Detection_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12246", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NWUf4hd571E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "NeuralUDF: Learning Unsigned Distance Fields for Multi-View Reconstruction of Surfaces with Arbitrary Topologies", - "base_url": null, - "title_page": null, - "repo": "xxlong0/NeuralUDF", - "web_page": "https://www.xxlong.site/NeuralUDF/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Long_NeuralUDF_Learning_Unsigned_Distance_Fields_for_Multi-View_Reconstruction_of_Surfaces_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14173", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JnaXx7qyYQY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "NEF: Neural Edge Fields for 3D Parametric Curve Reconstruction from Multi-View Images", - "base_url": null, - "title_page": null, - "repo": "yunfan1202/NEF_code", - "web_page": null, - "github_page": "https://yunfan1202.github.io/NEF/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ye_NEF_Neural_Edge_Fields_for_3D_Parametric_Curve_Reconstruction_From_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07653", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_F4EnZ1I_2g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Looking Through the Glass: Neural Surface Reconstruction Against High Specular Reflections", - "base_url": null, - "title_page": null, - "repo": "JiaxiongQ/NeuS-HSR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qiu_Looking_Through_the_Glass_Neural_Surface_Reconstruction_Against_High_Specular_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08706", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lwHd-GJAmMA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Multi-View Azimuth Stereo via Tangent Space Consistency", - "base_url": null, - "title_page": null, - "repo": "xucao-42/mvas", - "web_page": null, - "github_page": "https://xucao-42.github.io/mvas_homepage/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cao_Multi-View_Azimuth_Stereo_via_Tangent_Space_Consistency_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16447", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Instant Multi-View Head Capture through Learnable Registration", - "base_url": null, - "title_page": null, - "repo": "TimoBolkart/TEMPEH", - "web_page": "https://tempeh.is.tue.mpg.de/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bolkart_Instant_Multi-View_Head_Capture_Through_Learnable_Registration_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.07437", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AolpvKpmjEw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "EditableNeRF: Editing Topologically Varying Neural Radiance Fields by Key Points", - "base_url": null, - "title_page": null, - "repo": "chengwei-zheng/EditableNeRF_cvpr23", - "web_page": null, - "github_page": "https://chengwei-zheng.github.io/EditableNeRF/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zheng_EditableNeRF_Editing_Topologically_Varying_Neural_Radiance_Fields_by_Key_Points_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04247", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Eu2twgbg4kI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Iterative Geometry Encoding Volume for Stereo Matching", - "base_url": null, - "title_page": null, - "repo": "gangweiX/IGEV", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Iterative_Geometry_Encoding_Volume_for_Stereo_Matching_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06615", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Hi-LASSIE: High-Fidelity Articulated Shape and Skeleton Discovery from Sparse Image Ensemble", - "base_url": null, - "title_page": null, - "repo": "google/hi-lassie", - "web_page": null, - "github_page": "https://chhankyao.github.io/hi-lassie/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yao_Hi-LASSIE_High-Fidelity_Articulated_Shape_and_Skeleton_Discovery_From_Sparse_Image_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.11042", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "s9FWABEm0WU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "VDN-NeRF: Resolving Shape-Radiance Ambiguity via View-Dependence Normalization", - "base_url": null, - "title_page": null, - "repo": "BoifZ/VDN-NeRF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_VDN-NeRF_Resolving_Shape-Radiance_Ambiguity_via_View-Dependence_Normalization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17968", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yXPlqxEScK4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Neuralangelo: High-Fidelity Neural Surface Reconstruction", - "base_url": null, - "title_page": null, - "repo": "nvlabs/neuralangelo", - "web_page": "https://research.nvidia.com/labs/dir/neuralangelo/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Neuralangelo_High-Fidelity_Neural_Surface_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.03092", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Qpdw3SW54kI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "In-Hand 3D Object Scanning from an RGB Sequence", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://rgbinhandscanning.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hampali_In-Hand_3D_Object_Scanning_From_an_RGB_Sequence_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16193", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OaBKtUBbn3M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "SHS-Net: Learning Signed Hyper Surfaces for Oriented Normal Estimation of Point Clouds", - "base_url": null, - "title_page": null, - "repo": "LeoQLi/SHS-Net", - "web_page": null, - "github_page": "https://leoqli.github.io/SHS-Net/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_SHS-Net_Learning_Signed_Hyper_Surfaces_for_Oriented_Normal_Estimation_of_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.05873", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9DHAkjsnVYo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "FAC: 3D Representation Learning via Foreground Aware Feature Contrast", - "base_url": null, - "title_page": null, - "repo": "KangchengLiu/FAC_Foreground_Aware_Contrast", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_FAC_3D_Representation_Learning_via_Foreground_Aware_Feature_Contrast_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06388", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Neural Kernel Surface Reconstruction", - "base_url": null, - "title_page": null, - "repo": "nv-tlabs/nksr", - "web_page": "https://research.nvidia.com/labs/toronto-ai/NKSR/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Neural_Kernel_Surface_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.19590", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "J1V5F2z-dWY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "NeRFVS: Neural Radiance Fields for Free View Synthesis via Geometry Scaffolds", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_NeRFVS_Neural_Radiance_Fields_for_Free_View_Synthesis_via_Geometry_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.06287", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "HelixSurf: A Robust and Efficient Neural Implicit Surface Learning of Indoor Scenes with Iterative Intertwined Regularization", - "base_url": null, - "title_page": null, - "repo": "Gorilla-Lab-SCUT/HelixSurf", - "web_page": null, - "github_page": "https://lzhnb.github.io/project-pages/helixsurf.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liang_HelixSurf_A_Robust_and_Efficient_Neural_Implicit_Surface_Learning_of_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14340", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "eS5HjmX-l-w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Multi-Space Neural Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "ZX-Yin/ms-nerf", - "web_page": null, - "github_page": "https://zx-yin.github.io/msnerf/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yin_Multi-Space_Neural_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.04268", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mknOiuT7rVo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "MSF: Motion-guided Sequential Fusion for Efficient 3D Object Detection from Point Cloud Sequences", - "base_url": null, - "title_page": null, - "repo": "skyhehe123/MSF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_MSF_Motion-Guided_Sequential_Fusion_for_Efficient_3D_Object_Detection_From_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08316", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "PVO: Panoptic Visual Odometry", - "base_url": null, - "title_page": null, - "repo": "zju3dv/pvo", - "web_page": null, - "github_page": "https://zju3dv.github.io/pvo/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ye_PVO_Panoptic_Visual_Odometry_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.01610", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "j8iJdh_lPH4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Diffusion-SDF: Text-to-Shape via Voxelized Diffusion", - "base_url": null, - "title_page": null, - "repo": "ttlmh/Diffusion-SDF", - "web_page": null, - "github_page": "https://ttlmh.github.io/DiffusionSDF/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Diffusion-SDF_Text-To-Shape_via_Voxelized_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03293", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "FF2ZYKEFmIY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Rotation-Invariant Transformer for Point Cloud Matching", - "base_url": null, - "title_page": null, - "repo": "haoyu94/RoITr", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_Rotation-Invariant_Transformer_for_Point_Cloud_Matching_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08231", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GH8tz4Ng3dI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "HexPlane: A Fast Representation for Dynamic Scenes", - "base_url": null, - "title_page": null, - "repo": "Caoang327/HexPlane", - "web_page": null, - "github_page": "https://caoang327.github.io/HexPlane/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cao_HexPlane_A_Fast_Representation_for_Dynamic_Scenes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.09632", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "y-i_jMjnBII", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Learning 3D Representations from 2D Pre-trained Models via Image-to-Point Masked Autoencoders", - "base_url": null, - "title_page": null, - "repo": "ZrrSkywalker/I2P-MAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Learning_3D_Representations_From_2D_Pre-Trained_Models_via_Image-to-Point_Masked_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06785", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Progressive Neighbor Consistency Mining for Correspondence Pruning", - "base_url": null, - "title_page": null, - "repo": "xinliu29/NCMNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Progressive_Neighbor_Consistency_Mining_for_Correspondence_Pruning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Z-j7o-2AoBg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "SCoDA: Domain Adaptive Shape Completion for Real Scans", - "base_url": null, - "title_page": null, - "repo": "yushuang-wu/SCoDA", - "web_page": null, - "github_page": "https://yushuang-wu.github.io/SCoDA/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_SCoDA_Domain_Adaptive_Shape_Completion_for_Real_Scans_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10179", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Adaptive Patch Deformation for Textureless-Resilient Multi-View Stereo", - "base_url": null, - "title_page": null, - "repo": "whoiszzj/APD-MVS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Adaptive_Patch_Deformation_for_Textureless-Resilient_Multi-View_Stereo_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "s3Y8Ty-8X_I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Level-S2fM: Structure from Motion on Neural Level Set of Implicit Surfaces", - "base_url": null, - "title_page": null, - "repo": "henry123-boy/Level-S2FM_official", - "web_page": null, - "github_page": "https://henry123-boy.github.io/level-s2fm/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiao_Level-S2fM_Structure_From_Motion_on_Neural_Level_Set_of_Implicit_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12018", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yK8nt--Nl64", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "PLA: Language-Driven Open-Vocabulary 3D Scene Understanding", - "base_url": null, - "title_page": null, - "repo": "CVMI-Lab/PLA", - "web_page": null, - "github_page": "https://dingry.github.io/projects/PLA", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ding_PLA_Language-Driven_Open-Vocabulary_3D_Scene_Understanding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16312", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2VWANzUJ4DM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "SUDS: Scalable Urban Dynamic Scenes", - "base_url": null, - "title_page": null, - "repo": "hturki/suds", - "web_page": null, - "github_page": "https://haithemturki.com/suds/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Turki_SUDS_Scalable_Urban_Dynamic_Scenes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14536", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fcdEGt_ymeE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "3D Semantic Segmentation in the Wild: Learning Generalized Models for Adverse-Condition Point Clouds", - "base_url": null, - "title_page": null, - "repo": "xiaoaoran/SemanticSTF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiao_3D_Semantic_Segmentation_in_the_Wild_Learning_Generalized_Models_for_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00690", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "HhbdhKoRz6c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "BAEFormer: Bi-Directional and Early Interaction Transformers for Bird's Eye View Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pan_BAEFormer_Bi-Directional_and_Early_Interaction_Transformers_for_Birds_Eye_View_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Dionysus: Recovering Scene Structures by Dividing into Semantic Pieces", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Dionysus_Recovering_Scene_Structures_by_Dividing_Into_Semantic_Pieces_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "LP-DIF: Learning Local Pattern-Specific Deep Implicit Function for 3D Objects and Scenes", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_LP-DIF_Learning_Local_Pattern-Specific_Deep_Implicit_Function_for_3D_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Neural Kaleidoscopic Space Sculpting", - "base_url": null, - "title_page": null, - "repo": "ByeongjooAhn/neural_kaleidoscopic_space_sculpting", - "web_page": "https://imaging.cs.cmu.edu/neural_kaleidoscopic_space_sculpting/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ahn_Neural_Kaleidoscopic_Space_Sculpting_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_u19SOAEwzU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Starting from Non-Parametric Networks for 3D Point Cloud Analysis", - "base_url": null, - "title_page": null, - "repo": "ZrrSkywalker/Point-NN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Starting_From_Non-Parametric_Networks_for_3D_Point_Cloud_Analysis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08134", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ddfZVawhPEY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Panoptic Compositional Feature Field for Editable Scene Rendering with Network-Inferred Labels via Metric Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cheng_Panoptic_Compositional_Feature_Field_for_Editable_Scene_Rendering_With_Network-Inferred_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Robust Dynamic Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/robust-dynrf", - "web_page": null, - "github_page": "https://robust-dynrf.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Robust_Dynamic_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02239", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "38S56ottFQ4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "BAD-NeRF: Bundle Adjusted Deblur Neural Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "WU-CVGL/BAD-NeRF", - "web_page": null, - "github_page": "https://wangpeng000.github.io/BAD-NeRF/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_BAD-NeRF_Bundle_Adjusted_Deblur_Neural_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12853", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xoES4eONYoA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Consistent Direct Time-of-Flight Video Depth Super-Resolution", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/DVSR", - "web_page": null, - "github_page": "https://zhsun0357.github.io/consistent_dtof_video/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Consistent_Direct_Time-of-Flight_Video_Depth_Super-Resolution_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.08658", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "77LTIDqhBjA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Patch-based 3D Natural Scene Generation from a Single Example", - "base_url": null, - "title_page": null, - "repo": "wyysf-98/Sin3DGen", - "web_page": "http://weiyuli.xyz/Sin3DGen/", - "github_page": null, - "colab": "https://colab.research.google.com/github/wyysf-98/Sin3DGen/blob/main/colab_demo.ipynb", - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Patch-Based_3D_Natural_Scene_Generation_From_a_Single_Example_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.12670", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-buKPdBmLWo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "3D Video Loops from Asynchronous Input", - "base_url": null, - "title_page": null, - "repo": "limacv/VideoLoop3D", - "web_page": null, - "github_page": "https://limacv.github.io/VideoLoop3D_web/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ma_3D_Video_Loops_From_Asynchronous_Input_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05312", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Z_Zs1NLPACk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "UniDistill: A Universal Cross-Modality Knowledge Distillation Framework for 3D Object Detection in Bird's-Eye View", - "base_url": null, - "title_page": null, - "repo": "megvii-research/CVPR2023-UniDistill", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_UniDistill_A_Universal_Cross-Modality_Knowledge_Distillation_Framework_for_3D_Object_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15083", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_DW32YG7SSE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Neural Scene Chronology", - "base_url": null, - "title_page": null, - "repo": "zju3dv/NeuSC", - "web_page": null, - "github_page": "https://zju3dv.github.io/neusc/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Neural_Scene_Chronology_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.07970", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ak47wEZH1kY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "RUST: Latent Neural Scene Representations from Unposed Imagery", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://rust-paper.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sajjadi_RUST_Latent_Neural_Scene_Representations_From_Unposed_Imagery_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14306", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Painting 3D Nature in 2D: View Synthesis of Natural Scenes from a Single Semantic Mask", - "base_url": null, - "title_page": null, - "repo": "zhanghe3z/PaintingNature", - "web_page": null, - "github_page": "https://zju3dv.github.io/paintingnature/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Painting_3D_Nature_in_2D_View_Synthesis_of_Natural_Scenes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.07224", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-ipSXuzSs2A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "F2-NeRF: Fast Neural Radiance Field Training with Free Camera Trajectories", - "base_url": null, - "title_page": null, - "repo": "totoro97/f2-nerf", - "web_page": null, - "github_page": "https://totoro97.github.io/projects/f2-nerf/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_F2-NeRF_Fast_Neural_Radiance_Field_Training_With_Free_Camera_Trajectories_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15951", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JWQYAucCNl0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "VL-SAT: Visual-Linguistic Semantics Assisted Training for 3D Semantic Scene Graph Prediction in Point Cloud", - "base_url": null, - "title_page": null, - "repo": "wz7in/CVPR2023-VLSAT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_VL-SAT_Visual-Linguistic_Semantics_Assisted_Training_for_3D_Semantic_Scene_Graph_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14408", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YKicx1B5f7c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "REC-MV: REconstructing 3D Dynamic Cloth from Monocular Videos", - "base_url": null, - "title_page": null, - "repo": "GAP-LAB-CUHK-SZ/REC-MV", - "web_page": null, - "github_page": "https://lingtengqiu.github.io/2023/REC-MV/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qiu_REC-MV_REconstructing_3D_Dynamic_Cloth_From_Monocular_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.14236", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "agZ1qOEM1pA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "MVImgNet: A Large-Scale Dataset of Multi-View Images", - "base_url": null, - "title_page": null, - "repo": "GAP-LAB-CUHK-SZ/MVImgNet", - "web_page": "https://gaplab.cuhk.edu.cn/projects/MVImgNet/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_MVImgNet_A_Large-Scale_Dataset_of_Multi-View_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06042", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Shakes on a Plane: Unsupervised Depth Estimation from Unstabilized Photography", - "base_url": null, - "title_page": null, - "repo": "princeton-computational-imaging/SoaP", - "web_page": "https://light.princeton.edu/publication/soap/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chugunov_Shakes_on_a_Plane_Unsupervised_Depth_Estimation_From_Unstabilized_Photography_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.12324", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6Chkn8nW6bk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "GINA-3D: Learning to Generate Implicit Neural Assets in the Wild", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shen_GINA-3D_Learning_To_Generate_Implicit_Neural_Assets_in_the_Wild_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02163", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "aCAik8icuLI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "MobileNeRF: Exploiting the Polygon Rasterization Pipeline for Efficient Neural Field Rendering on Mobile Architectures", - "base_url": null, - "title_page": null, - "repo": "google-research/jax3d", - "web_page": null, - "github_page": "https://mobile-nerf.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_MobileNeRF_Exploiting_the_Polygon_Rasterization_Pipeline_for_Efficient_Neural_Field_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.00277", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "C1rULzOcjuw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "DynIBaR: Neural Dynamic Image-based Rendering", - "base_url": null, - "title_page": null, - "repo": "google/dynibar", - "web_page": null, - "github_page": "https://dynibar.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_DynIBaR_Neural_Dynamic_Image-Based_Rendering_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11082", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SCFfqYBGXt0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "IMP: Iterative Matching and Pose Estimation with Adaptive Pooling", - "base_url": null, - "title_page": null, - "repo": "feixue94/imp-release", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xue_IMP_Iterative_Matching_and_Pose_Estimation_With_Adaptive_Pooling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.14837", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yH3d-AzyTGo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Learning the Distribution of Errors in Stereo Matching for Joint Disparity and Uncertainty Estimation", - "base_url": null, - "title_page": null, - "repo": "lly00412/SEDNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Learning_the_Distribution_of_Errors_in_Stereo_Matching_for_Joint_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00152", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5Y6Vo69SiLQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "NeAT: Learning Neural Implicit Surfaces with Arbitrary Topologies from Multi-View Images", - "base_url": null, - "title_page": null, - "repo": "xmeng525/NeAT", - "web_page": null, - "github_page": "https://xmeng525.github.io/xiaoxumeng.github.io/projects/cvpr23_neat", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Meng_NeAT_Learning_Neural_Implicit_Surfaces_With_Arbitrary_Topologies_From_Multi-View_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12012", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GQNaW8GZOsM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "ShadowNeuS: Neural SDF Reconstruction by Shadow Ray Supervision", - "base_url": null, - "title_page": null, - "repo": "gerwang/ShadowNeuS", - "web_page": null, - "github_page": "https://gerwang.github.io/shadowneus/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ling_ShadowNeuS_Neural_SDF_Reconstruction_by_Shadow_Ray_Supervision_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14086", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jvxJ7bVuTBk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Bi-LRFusion: Bi-Directional LiDAR-Radar Fusion for 3D Dynamic Object Detection", - "base_url": null, - "title_page": null, - "repo": "JessieW0806/Bi-LRFusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Bi-LRFusion_Bi-Directional_LiDAR-Radar_Fusion_for_3D_Dynamic_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.01438", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mVm8x09SqHs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "NeRF-DS: Neural Radiance Fields for Dynamic Specular Objects", - "base_url": null, - "title_page": null, - "repo": "JokerYan/NeRF-DS", - "web_page": null, - "github_page": "https://jokeryan.github.io/projects/nerf-ds/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yan_NeRF-DS_Neural_Radiance_Fields_for_Dynamic_Specular_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14435", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VQShDzJ4NvI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "LoGoNet: Towards Accurate 3D Object Detection with Local-to-Global Cross-Modal Fusion", - "base_url": null, - "title_page": null, - "repo": "PJLab-ADG/LoGoNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_LoGoNet_Towards_Accurate_3D_Object_Detection_With_Local-to-Global_Cross-Modal_Fusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.03595", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "3D Registration with Maximal Cliques", - "base_url": null, - "title_page": null, - "repo": "zhangxy0517/3D-Registration-with-Maximal-Cliques", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_3D_Registration_With_Maximal_Cliques_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.10854", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LhALRCQo400", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "OmniObject3D: Large-Vocabulary 3D Object Dataset for Realistic Perception, Reconstruction and Generation", - "base_url": null, - "title_page": null, - "repo": "omniobject3d/OmniObject3D", - "web_page": null, - "github_page": "https://omniobject3d.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_OmniObject3D_Large-Vocabulary_3D_Object_Dataset_for_Realistic_Perception_Reconstruction_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.07525", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3rK9gVWxwS0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Progressive Spatio-Temporal Alignment for Efficient Event-based Motion Estimation", - "base_url": null, - "title_page": null, - "repo": "huangxueyan/PEME", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Progressive_Spatio-Temporal_Alignment_for_Efficient_Event-Based_Motion_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hEMm-Fkim7M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "RefSR-NeRF: Towards High Fidelity and Super Resolution View Synthesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_RefSR-NeRF_Towards_High_Fidelity_and_Super_Resolution_View_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "NoPe-NeRF: Optimising Neural Radiance Field with No Pose Prior", - "base_url": null, - "title_page": null, - "repo": "ActiveVisionLab/nope-nerf", - "web_page": "https://nope-nerf.active.vision/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bian_NoPe-NeRF_Optimising_Neural_Radiance_Field_With_No_Pose_Prior_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07388", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DVFbxol_mdA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Spherical Transformer for LiDAR-based 3D Recognition", - "base_url": null, - "title_page": null, - "repo": "dvlab-research/SphereFormer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lai_Spherical_Transformer_for_LiDAR-Based_3D_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12766", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "b3p_7yin5Qk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Progressively Optimized Local Radiance Fields for Robust View Synthesis", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/localrf", - "web_page": null, - "github_page": "https://localrf.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Meuleman_Progressively_Optimized_Local_Radiance_Fields_for_Robust_View_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13791", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GfXAHDxUY4M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "PersonNeRF: Personalized Reconstruction from Photo Collections", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://grail.cs.washington.edu/projects/personnerf/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Weng_PersonNeRF_Personalized_Reconstruction_From_Photo_Collections_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.08504", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XbkSYQw_dUE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "NeuWigs: A Neural Dynamic Model for Volumetric Hair Capture and Animation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://ziyanw1.github.io/neuwigs/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_NeuWigs_A_Neural_Dynamic_Model_for_Volumetric_Hair_Capture_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.00613", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "I6Lz4fgTt0c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Representing Volumetric Videos As Dynamic MLP Maps", - "base_url": null, - "title_page": null, - "repo": "zju3dv/mlp_maps", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Peng_Representing_Volumetric_Videos_As_Dynamic_MLP_Maps_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.06717", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "s-ZSokF61iY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Rethinking the Approximation Error in 3D Surface Fitting for Point Cloud Normal Estimation", - "base_url": null, - "title_page": null, - "repo": "hikvision-research/3DVision", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Du_Rethinking_the_Approximation_Error_in_3D_Surface_Fitting_for_Point_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17167", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0Hjzf0UCtq4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "A Practical Stereo Depth System for Smart Glasses", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_A_Practical_Stereo_Depth_System_for_Smart_Glasses_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10551", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jRh2qlclJ8w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Compressing Volumetric Radiance Fields to 1 MB", - "base_url": null, - "title_page": null, - "repo": "AlgoHunt/VQRF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Compressing_Volumetric_Radiance_Fields_to_1_MB_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16386", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "HyperReel: High-Fidelity 6-DoF Video With Ray-Conditioned Sampling", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/hyperreel", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Attal_HyperReel_High-Fidelity_6-DoF_Video_With_Ray-Conditioned_Sampling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02238", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hBjJQ1lpR0k", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Point2Pix: Photo-Realistic Point Cloud Rendering via Neural Radiance Fields", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Point2Pix_Photo-Realistic_Point_Cloud_Rendering_via_Neural_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16482", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XmGJ8VfCxPQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Command-Driven Articulated Object Understanding and Manipulation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chu_Command-Driven_Articulated_Object_Understanding_and_Manipulation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-UJBvLH93uM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "SCADE: NeRFs from Space Carving With Ambiguity-Aware Depth Estimates", - "base_url": null, - "title_page": null, - "repo": "mikacuy/scade", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Uy_SCADE_NeRFs_from_Space_Carving_With_Ambiguity-Aware_Depth_Estimates_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13582", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5XwWZn-kjBU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - }, - { - "title": "Panoptic Lifting for 3D Scene Understanding with Neural Fields", - "base_url": null, - "title_page": null, - "repo": "nihalsid/panoptic-lifting", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Siddiqui_Panoptic_Lifting_for_3D_Scene_Understanding_With_Neural_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09802", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "QtsiL-6rSuM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Multi-View and Sensors" - } -] \ No newline at end of file diff --git a/json_data/3d-from-single-images.json b/json_data/3d-from-single-images.json deleted file mode 100644 index 000e553..0000000 --- a/json_data/3d-from-single-images.json +++ /dev/null @@ -1,102 +0,0 @@ -[ - { - "title": "3D-Aware Multi-Class Image-to-Image Translation With NeRFs", - "base_url": null, - "title_page": null, - "repo": "sen-mao/3di2i-translation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_3D-Aware_Multi-Class_Image-to-Image_Translation_With_NeRFs_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15012", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CjBPP2l9Bjg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Single Images" - }, - { - "title": "DisCoScene: Spatially Disentangled Generative Radiance Fields for Controllable 3D-Aware Scene Synthesis", - "base_url": null, - "title_page": null, - "repo": "snap-research/discoscene", - "web_page": null, - "github_page": "https://snap-research.github.io/discoscene/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_DisCoScene_Spatially_Disentangled_Generative_Radiance_Fields_for_Controllable_3D-Aware_Scene_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.11984", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Single Images" - }, - { - "title": "MagicPony: Learning Articulated 3D Animals in the Wild", - "base_url": null, - "title_page": null, - "repo": "elliottwu/MagicPony", - "web_page": null, - "github_page": "https://3dmagicpony.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_MagicPony_Learning_Articulated_3D_Animals_in_the_Wild_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12497", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KoLzpESstLk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Single Images" - }, - { - "title": "Seeing a Rose in Five Thousand Ways", - "base_url": null, - "title_page": null, - "repo": "zzyunzhi/object-intrinsics", - "web_page": "https://ai.stanford.edu/~yzzhang/projects/rose/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Seeing_a_Rose_in_Five_Thousand_Ways_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04965", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "oe5N3sNDp2w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "3D from Single Images" - } -] \ No newline at end of file diff --git a/json_data/adversarial-attack-and-defense.json b/json_data/adversarial-attack-and-defense.json deleted file mode 100644 index 845621b..0000000 --- a/json_data/adversarial-attack-and-defense.json +++ /dev/null @@ -1,1527 +0,0 @@ -[ - { - "title": "TWINS: A Fine-Tuning Framework for Improved Transferability of Adversarial Robustness and Generalization", - "base_url": null, - "title_page": null, - "repo": "ziquanliu/CVPR2023-TWINS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_TWINS_A_Fine-Tuning_Framework_for_Improved_Transferability_of_Adversarial_Robustness_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11135", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wI0KfALYIeI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Sibling-Attack: Rethinking Transferable Adversarial Attacks Against Face Recognition", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Sibling-Attack_Rethinking_Transferable_Adversarial_Attacks_Against_Face_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12512", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "a3f2_7S2uWA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "T-SEA: Transfer-based Self-Ensemble Attack on Object Detection", - "base_url": null, - "title_page": null, - "repo": "VDIGPKU/T-SEA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_T-SEA_Transfer-Based_Self-Ensemble_Attack_on_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.09773", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1rkwIvv1KJ0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "The Enemy of My Enemy is My Friend: Exploring Inverse Adversaries for Improving Adversarial Training", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dong_The_Enemy_of_My_Enemy_Is_My_Friend_Exploring_Inverse_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.00525", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rNoto-p2k0o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Trade-Off between Robustness and Accuracy of Vision Transformers", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Trade-Off_Between_Robustness_and_Accuracy_of_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Physically Realizable Natural-Looking Clothing Textures Evade Person Detectors via 3D Modeling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Physically_Realizable_Natural-Looking_Clothing_Textures_Evade_Person_Detectors_via_3D_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.01778", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jUif0yYeSb0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Proximal Splitting Adversarial Attack for Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "jeromerony/alma_prox_segmentation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rony_Proximal_Splitting_Adversarial_Attack_for_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.07179", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Feature Separation and Recalibration for Adversarial Robustness", - "base_url": null, - "title_page": null, - "repo": "wkim97/FSR", - "web_page": "https://sgvr.kaist.ac.kr/~wjkim/FSR/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Feature_Separation_and_Recalibration_for_Adversarial_Robustness_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13846", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PcnGZ0JYyNQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Enhancing the Self-Universality for Transferable Targeted Attacks", - "base_url": null, - "title_page": null, - "repo": "zhipeng-wei/Self-Universality", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_Enhancing_the_Self-Universality_for_Transferable_Targeted_Attacks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.03716", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-JFDxqcTM3A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Backdoor Defense via Adaptively Splitting Poisoned Dataset", - "base_url": null, - "title_page": null, - "repo": "KuofengGao/ASD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_Backdoor_Defense_via_Adaptively_Splitting_Poisoned_Dataset_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12993", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "s_r7SLduKVY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Dynamic Generative Targeted Attacks with Pattern Injection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_Dynamic_Generative_Targeted_Attacks_With_Pattern_Injection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "L37AqVQCpVc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Exploring the Relationship between Architectural Design and Adversarially Robust Generalization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Exploring_the_Relationship_Between_Architectural_Design_and_Adversarially_Robust_Generalization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.14105", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YmeNgIbADdM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Discrete Point-Wise Attack Is Not Enough: Generalized Manifold Adversarial Attack for Face Recognition", - "base_url": null, - "title_page": null, - "repo": "tokaka22/GMAA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Discrete_Point-Wise_Attack_Is_Not_Enough_Generalized_Manifold_Adversarial_Attack_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.06083", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Cs489KVQBFI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Towards Benchmarking and Assessing Visual Naturalness of Physical World Adversarial Attacks", - "base_url": null, - "title_page": null, - "repo": "zhangsn-19/PAN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Towards_Benchmarking_and_Assessing_Visual_Naturalness_of_Physical_World_Adversarial_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.12863", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "MaLP: Manipulation Localization using a Proactive Scheme", - "base_url": null, - "title_page": null, - "repo": "vishal3477/pro_loc", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Asnani_MaLP_Manipulation_Localization_Using_a_Proactive_Scheme_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16976", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1NFxT-8mIYk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "TrojDiff: Trojan Attacks on Diffusion Models with Diverse Targets", - "base_url": null, - "title_page": null, - "repo": "chenweixin107/TrojDiff", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_TrojDiff_Trojan_Attacks_on_Diffusion_Models_With_Diverse_Targets_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05762", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Minimizing Maximum Model Discrepancy for Transferable Black-Box Targeted Attacks", - "base_url": null, - "title_page": null, - "repo": "Asteriajojo/M3D", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Minimizing_Maximum_Model_Discrepancy_for_Transferable_Black-Box_Targeted_Attacks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09035", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Improving Robust Generalization by Direct PAC-Bayesian Bound Minimization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Improving_Robust_Generalization_by_Direct_PAC-Bayesian_Bound_Minimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12624", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Fz_MbbFsk9s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "AGAIN: Adversarial Training with Attribution Span Enlargement and Hybrid Feature Fusion", - "base_url": null, - "title_page": null, - "repo": "InsLin/AGAIN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yin_AGAIN_Adversarial_Training_With_Attribution_Span_Enlargement_and_Hybrid_Feature_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GVQtWpZjzQk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Backdoor Defense via Deconfounded Representation Learning", - "base_url": null, - "title_page": null, - "repo": "zaixizhang/CBD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Backdoor_Defense_via_Deconfounded_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06818", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YmRnyTmV0Ec", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Adversarially Robust Neural Architecture Search for Graph Neural Networks", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_Adversarially_Robust_Neural_Architecture_Search_for_Graph_Neural_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04168", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_NH-00oUWVg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "PointCert: Point Cloud Classification with Deterministic Certified Robustness Guarantees", - "base_url": null, - "title_page": null, - "repo": "jzhang538/PointCert", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_PointCert_Point_Cloud_Classification_With_Deterministic_Certified_Robustness_Guarantees_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01959", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hSnbPNU_Is8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Towards Compositional Adversarial Robustness: Generalizing Adversarial Training to Composite Semantic Perturbations", - "base_url": null, - "title_page": null, - "repo": "IBM/composite-adv", - "web_page": "https://hsiung.cc/CARBEN", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hsiung_Towards_Compositional_Adversarial_Robustness_Generalizing_Adversarial_Training_to_Composite_Semantic_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2202.04235", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "N3sqkI1dfyM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Physically Adversarial Infrared Patches with Learnable Shapes and Locations", - "base_url": null, - "title_page": null, - "repo": "shighghyujie/infrared_patch_attack", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_Physically_Adversarial_Infrared_Patches_With_Learnable_Shapes_and_Locations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13868", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MAwLZiYO08s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Color Backdoor: A Robust Poisoning Attack in Color Space", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_Color_Backdoor_A_Robust_Poisoning_Attack_in_Color_Space_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Towards Effective Adversarial Textured 3D Meshes on Physical Face Recognition", - "base_url": null, - "title_page": null, - "repo": "thu-ml/AT3D", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Towards_Effective_Adversarial_Textured_3D_Meshes_on_Physical_Face_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15818", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Turning Strengths into Weaknesses: A Certified Robustness Inspired Attack Framework Against Graph Neural Networks", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Turning_Strengths_Into_Weaknesses_A_Certified_Robustness_Inspired_Attack_Framework_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06199", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Randomized Adversarial Training via Taylor Expansion", - "base_url": null, - "title_page": null, - "repo": "Alexkael/Randomized-Adversarial-Training", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jin_Randomized_Adversarial_Training_via_Taylor_Expansion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10653", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OuKM6zf_BYA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Backdoor Cleansing with Unlabeled Data", - "base_url": null, - "title_page": null, - "repo": "luluppang/BCU", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pang_Backdoor_Cleansing_With_Unlabeled_Data_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12044", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "The Best Defense is a Good Offense: Adversarial Augmentation Against Adversarial Attacks", - "base_url": null, - "title_page": null, - "repo": "NVlabs/A5", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Frosio_The_Best_Defense_Is_a_Good_Offense_Adversarial_Augmentation_Against_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.14188", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "pUasda84YPE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Ensemble-based Blackbox Attacks on Dense Prediction", - "base_url": null, - "title_page": null, - "repo": "CSIPlab/EBAD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cai_Ensemble-Based_Blackbox_Attacks_on_Dense_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14304", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4z7dHpq3u5s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Defending Against Patch-based Backdoor Attacks on Self-Supervised Learning", - "base_url": null, - "title_page": null, - "repo": "UCDvision/PatchSearch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tejankar_Defending_Against_Patch-Based_Backdoor_Attacks_on_Self-Supervised_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.01482", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "V92Ji3rAApM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Adversarial Robustness via Random Projection Filters", - "base_url": null, - "title_page": null, - "repo": "UniSerj/Random-Projection-Filters", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dong_Adversarial_Robustness_via_Random_Projection_Filters_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CSklqMWbn-M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Boundary Unlearning: Rapid Forgetting of Deep Networks via Shifting the Decision Boundary", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Boundary_Unlearning_Rapid_Forgetting_of_Deep_Networks_via_Shifting_the_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Physical-World Optical Adversarial Attacks on 3D Face Recognition", - "base_url": null, - "title_page": null, - "repo": "PolyLiYJ/SLAttack", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Physical-World_Optical_Adversarial_Attacks_on_3D_Face_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.13412", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gv2J3rDZ_p4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Black-Box Sparse Adversarial Attack via Multi-Objective Optimisation", - "base_url": null, - "title_page": null, - "repo": "phoenixwilliams/Black-Box-Sparse-Adversarial-Attack-via-Multi-Objective-Optimisation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Williams_Black-Box_Sparse_Adversarial_Attack_via_Multi-Objective_Optimisation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "How to Backdoor Diffusion Models?", - "base_url": null, - "title_page": null, - "repo": "IBM/BadDiffusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chou_How_to_Backdoor_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.05400", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "The Resource Problem of using Linear Layer Leakage Attack in Federated Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_The_Resource_Problem_of_Using_Linear_Layer_Leakage_Attack_in_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14868", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "uxAWL6i7LNw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Efficient Loss Function by Minimizing the Detrimental Effect of Floating-Point Errors on Gradient-based Attacks", - "base_url": null, - "title_page": null, - "repo": "MIFPE/Efficient-Loss-Function", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_Efficient_Loss_Function_by_Minimizing_the_Detrimental_Effect_of_Floating-Point_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Hq2pvz4lJBA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Detecting Backdoors in Pre-trained Encoders", - "base_url": null, - "title_page": null, - "repo": "GiantSeaweed/DECREE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_Detecting_Backdoors_in_Pre-Trained_Encoders_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15180", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lTlxReKZZbc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Can't Steal? Cont-Steal! Contrastive Stealing Attacks Against Image Encoders", - "base_url": null, - "title_page": null, - "repo": "zeyangsha/Cont-Steal", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sha_Cant_Steal_Cont-Steal_Contrastive_Stealing_Attacks_Against_Image_Encoders_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RFw8X-eGprE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "CFA: Class-Wise Calibrated Fair Adversarial Training", - "base_url": null, - "title_page": null, - "repo": "PKU-ML/CFA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_CFA_Class-Wise_Calibrated_Fair_Adversarial_Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14460", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Towards Transferable Targeted Adversarial Examples", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Towards_Transferable_Targeted_Adversarial_Examples_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1Avki-hH3lo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Hierarchical Fine-grained Image Forgery Detection and Localization", - "base_url": null, - "title_page": null, - "repo": "CHELSEA234/HiFi_IFDL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Guo_Hierarchical_Fine-Grained_Image_Forgery_Detection_and_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17111", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "RIATIG: Reliable and Imperceptible Adversarial Text-to-Image Generation with Natural Prompts", - "base_url": null, - "title_page": null, - "repo": "WUSTL-CSPL/RIATIG", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_RIATIG_Reliable_and_Imperceptible_Adversarial_Text-to-Image_Generation_With_Natural_Prompts_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "SlowLiDAR: Increasing the Latency of LiDAR-based Detection using Adversarial Examples", - "base_url": null, - "title_page": null, - "repo": "WUSTL-CSPL/SlowLiDAR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_SlowLiDAR_Increasing_the_Latency_of_LiDAR-Based_Detection_Using_Adversarial_Examples_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Progressive Backdoor Erasing via Connecting Backdoor and Adversarial Attacks", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mu_Progressive_Backdoor_Erasing_via_Connecting_Backdoor_and_Adversarial_Attacks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2202.06312", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Improving the Transferability of Adversarial Samples by Path-Augmented Method", - "base_url": null, - "title_page": null, - "repo": "jpzhang1810/PAM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Improving_the_Transferability_of_Adversarial_Samples_by_Path-Augmented_Method_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15735", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mzaSwLaHA3Y", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Boosting Accuracy and Robustness of Student Models via Adaptive Adversarial Distillation", - "base_url": null, - "title_page": null, - "repo": "boyellow/AdaAD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Boosting_Accuracy_and_Robustness_of_Student_Models_via_Adaptive_Adversarial_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ncs7svnpRCY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "StyLess: Boosting the Transferability of Adversarial Examples", - "base_url": null, - "title_page": null, - "repo": "uhiu/StyLess", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liang_StyLess_Boosting_the_Transferability_of_Adversarial_Examples_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11579", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VYu7pyOIt7E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Introducing Competition to Boost the Transferability of Targeted Adversarial Examples through Clean Feature Mixup", - "base_url": null, - "title_page": null, - "repo": "dreamflake/CFM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Byun_Introducing_Competition_To_Boost_the_Transferability_of_Targeted_Adversarial_Examples_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.14846", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "R1OvhDH_jVk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Transferable Adversarial Attacks on Vision Transformers with Token Gradient Regularization", - "base_url": null, - "title_page": null, - "repo": "jpzhang1810/TGR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Transferable_Adversarial_Attacks_on_Vision_Transformers_With_Token_Gradient_Regularization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15754", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lVWCIhcO_oo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Jedi: Entropy-based Localization and Removal of Adversarial Patches", - "base_url": null, - "title_page": null, - "repo": "ihsenLab/jedi-CVPR2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tarchoun_Jedi_Entropy-Based_Localization_and_Removal_of_Adversarial_Patches_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10029", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8B5Mn9t7zc8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Seasoning Model Soups for Robustness to Adversarial and Natural Distribution Shifts", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Croce_Seasoning_Model_Soups_for_Robustness_to_Adversarial_and_Natural_Distribution_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.10164", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "CUDA: Convolution-based Unlearnable Datasets", - "base_url": null, - "title_page": null, - "repo": "vinusankars/Convolution-based-Unlearnability", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sadasivan_CUDA_Convolution-Based_Unlearnable_Datasets_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.04278", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "b4uiWxB0g4c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Demystifying Causal Features on Adversarial Examples and Causal Inoculation for Robust Network by Adversarial Instrumental Variable Regression", - "base_url": null, - "title_page": null, - "repo": "ByungKwanLee/Causal-Adversarial-Instruments", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Demystifying_Causal_Features_on_Adversarial_Examples_and_Causal_Inoculation_for_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01052", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Generalist: Decoupling Natural and Robust Generalization", - "base_url": null, - "title_page": null, - "repo": "PKU-ML/Generalist", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Generalist_Decoupling_Natural_and_Robust_Generalization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13813", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IQlHOPZwAIE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "The Dark Side of Dynamic Routing Neural Networks: Towards Efficiency Backdoor Injection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_The_Dark_Side_of_Dynamic_Routing_Neural_Networks_Towards_Efficiency_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GtSm6WKsRGg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Revisiting Residual Networks for Adversarial Robustness", - "base_url": null, - "title_page": null, - "repo": "zhichao-lu/robust-residual-network", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Revisiting_Residual_Networks_for_Adversarial_Robustness_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.11005", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xfgGKnaZv7Y", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Detecting Backdoors During the Inference Stage based on Corruption Robustness Consistency", - "base_url": null, - "title_page": null, - "repo": "CGCL-codes/TeCo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Detecting_Backdoors_During_the_Inference_Stage_Based_on_Corruption_Robustness_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.18191", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - }, - { - "title": "Cooperation or Competition: Avoiding Player Domination for Multi-Target Robustness via Adaptive Budgets", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Cooperation_or_Competition_Avoiding_Player_Domination_for_Multi-Target_Robustness_via_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.15482", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Adversarial Attack and Defense" - } -] \ No newline at end of file diff --git a/json_data/autonomous-driving.json b/json_data/autonomous-driving.json deleted file mode 100644 index eb50428..0000000 --- a/json_data/autonomous-driving.json +++ /dev/null @@ -1,1727 +0,0 @@ -[ - { - "title": "GraVoS: Voxel Selection for 3D Point-Cloud Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shrout_GraVoS_Voxel_Selection_for_3D_Point-Cloud_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.08780", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8rVLxIT-2wQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "BEV@DC: Bird's-Eye View Assisted Training for Depth Completion", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_BEVDC_Birds-Eye_View_Assisted_Training_for_Depth_Completion_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IvhaqXL1NNY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Are we Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark", - "base_url": null, - "title_page": null, - "repo": "JeffWang987/ASAP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Are_We_Ready_for_Vision-Centric_Driving_Streaming_Perception_The_ASAP_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08914", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YjNkmvm83ww", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer", - "base_url": null, - "title_page": null, - "repo": "Nightmare-n/PVT-SSD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_PVT-SSD_Single-Stage_3D_Object_Detector_With_Point-Voxel_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.06621", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "J1FVUpmW9JA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "End-to-End Vectorized HD-Map Construction with Piecewise Bezier Curve", - "base_url": null, - "title_page": null, - "repo": "er-muyue/BeMapNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qiao_End-to-End_Vectorized_HD-Map_Construction_With_Piecewise_Bezier_Curve_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.09700", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_MoDAR_Using_Motion_Forecasting_for_3D_Object_Detection_in_Point_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.03206", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xIPWjmGzaqU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "LaserMix for Semi-Supervised LiDAR Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "ldkong1205/LaserMix", - "web_page": "https://ldkong.com/LaserMix", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kong_LaserMix_for_Semi-Supervised_LiDAR_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.00026", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7-zvIHKqkl0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "SxJyJay/MSMDFusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiao_MSMDFusion_Fusing_LiDAR_and_Camera_at_Multiple_Scales_With_Multi-Depth_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.03102", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5mkacK_wsqY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "LiDAR2Map: In Defense of LiDAR-based Semantic Map Construction using Online Camera Distillation", - "base_url": null, - "title_page": null, - "repo": "songw-zju/LiDAR2Map", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_LiDAR2Map_In_Defense_of_LiDAR-Based_Semantic_Map_Construction_Using_Online_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11379", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nr25xFZbx8U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Think Twice Before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "OpenDriveLab/ThinkTwice", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jia_Think_Twice_Before_Driving_Towards_Scalable_Decoders_for_End-to-End_Autonomous_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.06242", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Planning-Oriented Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "OpenDriveLab/UniAD", - "web_page": null, - "github_page": "https://opendrivelab.github.io/UniAD/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Planning-Oriented_Autonomous_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.10156", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "R4iuq3zDBL4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Distilling Focal Knowledge from Imperfect Expert for 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "OpenDriveLab/Birds-eye-view-Perception", - "web_page": null, - "github_page": "https://github.com/OpenDriveLab/Birds-eye-view-Perception/blob/master/nuScenes_playground/FocalDistiller/README.md", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zeng_Distilling_Focal_Knowledge_From_Imperfect_Expert_for_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Np9_pEzleG4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection", - "base_url": null, - "title_page": null, - "repo": "tusen-ai/Anchor3DLane", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Anchor3DLane_Learning_To_Regress_3D_Anchors_for_Monocular_3D_Lane_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02371", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5ceKZ6q5TVc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation", - "base_url": null, - "title_page": null, - "repo": "tudelft-iv/SliceMatch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lentsch_SliceMatch_Geometry-Guided_Aggregation_for_Cross-View_Pose_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14651", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gql1dkQQNrA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Azimuth Super-Resolution for FMCW Radar in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "yujheli/Pitt-Radar", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Azimuth_Super-Resolution_for_FMCW_Radar_in_Autonomous_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception", - "base_url": null, - "title_page": null, - "repo": "ucla-mobility/V2V4Real", - "web_page": "https://mobility-lab.seas.ucla.edu/v2v4real/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_V2V4Real_A_Real-World_Large-Scale_Dataset_for_Vehicle-to-Vehicle_Cooperative_Perception_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07601", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "67N0epSAvRA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/implicito/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Agro_Implicit_Occupancy_Flow_Fields_for_Perception_and_Prediction_in_Self-Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2308.01471", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Coaching a Teachable Student", - "base_url": null, - "title_page": null, - "repo": "h2xlab/CaT", - "web_page": null, - "github_page": "https://catdrive.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Coaching_a_Teachable_Student_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.10014", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5tmkDHfgqvU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chi_BEV-SAN_Accurate_BEV_3D_Object_Detection_via_Slice_Attention_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.01231", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UYGZoi490GI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Center Focusing Network for Real-Time LiDAR Panoptic Segmentation", - "base_url": null, - "title_page": null, - "repo": "gangzhang842/cfnet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Center_Focusing_Network_for_Real-Time_LiDAR_Panoptic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2311.09499", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LHaQhrVysDo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_IPCC-TP_Utilizing_Incremental_Pearson_Correlation_Coefficient_for_Joint_Multi-Agent_Trajectory_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00575", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0eQUiil3AXs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency", - "base_url": null, - "title_page": null, - "repo": "weakmono3d/weakmono3d", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tao_Weakly_Supervised_Monocular_3D_Object_Detection_Using_Multi-View_Projection_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08686", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AXBa5Rn58j4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "CXTrack: Improving 3D Point Cloud Tracking with Contextual Information", - "base_url": null, - "title_page": null, - "repo": "slothfulxtx/cxtrack3d", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_CXTrack_Improving_3D_Point_Cloud_Tracking_With_Contextual_Information_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.08542", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9CbtQt4umws", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "ReasonNet: End-to-End Driving with Temporal and Global Reasoning", - "base_url": null, - "title_page": null, - "repo": "opendilab/DOS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shao_ReasonNet_End-to-End_Driving_With_Temporal_and_Global_Reasoning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.10507", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "59wCGdrHGE4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Seeing with Sound: Long-Range Acoustic Beamforming for Multimodal Scene Understanding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://light.princeton.edu/publication/seeingwithsound/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chakravarthula_Seeing_With_Sound_Long-range_Acoustic_Beamforming_for_Multimodal_Scene_Understanding_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "N5QinjRhKYQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "LinK: Linear Kernel for LiDAR-based 3D Perception", - "base_url": null, - "title_page": null, - "repo": "MCG-NJU/LinK", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_LinK_Linear_Kernel_for_LiDAR-Based_3D_Perception_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16094", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UM2W7rHE6V4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "zzj403/BEV_Robust", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_Understanding_the_Robustness_of_3D_Object_Detection_With_Birds-Eye-View_Representations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17297", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TqoR7gwzTXQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Tri-Perspective View for Vision-based 3D Semantic Occupancy Prediction", - "base_url": null, - "title_page": null, - "repo": "wzzheng/TPVFormer", - "web_page": "https://wzzheng.net/TPVFormer/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Tri-Perspective_View_for_Vision-Based_3D_Semantic_Occupancy_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.07817", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XWVNn0_6iJg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping using Monocular Frontal View Images", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "http://skyeye.cs.uni-freiburg.de/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gosala_SkyEye_Self-Supervised_Birds-Eye-View_Semantic_Mapping_Using_Monocular_Frontal_View_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.04233", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PGne5XG4f_8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "BEV-LaneDet: An Efficient 3D Lane Detection based on Virtual Camera via Key-Points", - "base_url": null, - "title_page": null, - "repo": "gigo-team/bev_lane_det", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_BEV-LaneDet_An_Efficient_3D_Lane_Detection_Based_on_Virtual_Camera_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.06006", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "OcTr: Octree-based Transformer for 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_OcTr_Octree-Based_Transformer_for_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12621", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NgCI8s7Kh8M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Instant Domain Augmentation for LiDAR Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "kwonyoung9120/LiDomAug", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ryu_Instant_Domain_Augmentation_for_LiDAR_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14378", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tnheIfyQkqc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries", - "base_url": null, - "title_page": null, - "repo": "Tsinghua-MARS-Lab/ViP3D", - "web_page": null, - "github_page": "https://tsinghua-mars-lab.github.io/ViP3D/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gu_ViP3D_End-to-End_Visual_Trajectory_Prediction_via_3D_Agent_Queries_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.01582", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1apYGKgeWdc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "UniSim: A Neural Closed-Loop Sensor Simulator", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/unisim/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_UniSim_A_Neural_Closed-Loop_Sensor_Simulator_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2308.01898", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3OwjE1Mv_3I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Learning Compact Representations for LiDAR Completion and Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/ultralidar/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_Learning_Compact_Representations_for_LiDAR_Completion_and_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2311.01448", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CWOfT3Wrxh4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Towards Unsupervised Object Detection from LiDAR Point Clouds", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/research/oyster", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Towards_Unsupervised_Object_Detection_From_LiDAR_Point_Clouds_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2311.02007", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gUQZmIhCxVM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking", - "base_url": null, - "title_page": null, - "repo": "TRI-ML/PF-Track", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pang_Standing_Between_Past_and_Future_Spatio-Temporal_Modeling_for_Multi-Camera_3D_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.03802", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AP46BbkJ7vY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "thu-ml/3D_Corruptions_AD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dong_Benchmarking_Robustness_of_3D_Object_Detection_to_Common_Corruptions_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11040", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xIRQhg3I1-A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Klingner_X3KD_Knowledge_Distillation_Across_Modalities_Tasks_and_Stages_for_Multi-Camera_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.02203", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1do9DPFmr38", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "PeakConv: Learning Peak Receptive Field for Radar Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "zlw9161/PKC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_PeakConv_Learning_Peak_Receptive_Field_for_Radar_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds", - "base_url": null, - "title_page": null, - "repo": "Nightmare-n/GD-MAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_GD-MAE_Generative_Decoder_for_MAE_Pre-Training_on_LiDAR_Point_Clouds_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03010", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "k8JE6CDjyng", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Neural Map Prior for Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "Tsinghua-MARS-Lab/neural_map_prior", - "web_page": null, - "github_page": "https://tsinghua-mars-lab.github.io/neural_map_prior/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_Neural_Map_Prior_for_Autonomous_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08481", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "FpzxaBVw3L0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field", - "base_url": null, - "title_page": null, - "repo": "Len-Li/Lift3D", - "web_page": null, - "github_page": "https://len-li.github.io/lift3d-web/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Lift3D_Synthesize_3D_Training_Data_by_Lifting_2D_GAN_to_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03526", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation with Implicit Neural Representations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gong_Continuous_Pseudo-Label_Rectified_Domain_Adaptive_Semantic_Segmentation_With_Implicit_Neural_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Single Domain Generalization for LiDAR Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "gzgzys9887/DGLSS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Single_Domain_Generalization_for_LiDAR_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XUe-N3p5btc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Uncertainty-Aware Vision-based Metric Cross-View Geolocalization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://fferflo.github.io/projects/vismetcvgl23/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fervers_Uncertainty-Aware_Vision-Based_Metric_Cross-View_Geolocalization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12145", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1vHFiA0prL0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "MixSim: A Hierarchical Framework for Mixed Reality Traffic Simulation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/mixsim/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Suo_MixSim_A_Hierarchical_Framework_for_Mixed_Reality_Traffic_Simulation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds", - "base_url": null, - "title_page": null, - "repo": "qcraftai/pillarnext", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_PillarNeXt_Rethinking_Network_Designs_for_3D_Object_Detection_in_LiDAR_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.04925", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zdMSqNvi-KM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "PJLab-ADG/3DTrans", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Uni3D_A_Unified_Baseline_for_Multi-Dataset_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06880", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "CAPE: Camera View Position Embedding for Multi-View 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "kaixinbear/CAPE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_CAPE_Camera_View_Position_Embedding_for_Multi-View_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10209", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "LiDAR-in-the-Loop Hyperparameter Optimization", - "base_url": null, - "title_page": null, - "repo": "princeton-computational-imaging/LITL-Optimization", - "web_page": "https://light.princeton.edu/publication/lidar-in-the-loop-hyperparameter-optimization/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Goudreault_LiDAR-in-the-Loop_Hyperparameter_Optimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8IjqoctJgOs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "PJLab-ADG/3DTrans", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yuan_Bi3D_Bi-Domain_Active_Learning_for_Cross-Domain_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05886", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction", - "base_url": null, - "title_page": null, - "repo": "ynw2021/FEND", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_FEND_A_Future_Enhanced_Distribution-Aware_Contrastive_Learning_Framework_for_Long-Tail_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16574", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "31Put0T54qI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "PRBonn/TARL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nunes_Temporal_Consistent_3D_LiDAR_Representation_Learning_for_Semantic_Perception_in_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0CtDbwRYLeo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "WoodwindHu/DTS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Density-Insensitive_Unsupervised_Domain_Adaption_on_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.09446", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Zb020nG6sD0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization", - "base_url": null, - "title_page": null, - "repo": "liw95/SGLoc", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_SGLoc_Scene_Geometry_Encoding_for_Outdoor_LiDAR_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Tek6yA20N7M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "MediaBrain-SJTU/TBP-Former", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fang_TBP-Former_Learning_Temporal_Birds-Eye-View_Pyramid_for_Joint_Perception_and_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09998", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RlS2rDlaM9w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Khan_Localized_Semantic_Feature_Mixers_for_Efficient_Pedestrian_Detection_in_Autonomous_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4jSlqKnTemw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Deep Dive Into Gradients: Better Optimization for 3D Object Detection with Gradient-Corrected IoU Supervision", - "base_url": null, - "title_page": null, - "repo": "ming71/GCIoU-loss", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ming_Deep_Dive_Into_Gradients_Better_Optimization_for_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_ProphNet_Efficient_Agent-Centric_Motion_Forecasting_With_Anchor-Informed_Proposals_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12071", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "ADLab-AutoDrive/BEVHeight", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_BEVHeight_A_Robust_Framework_for_Vision-Based_Roadside_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08498", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "W-y-MIrdXQc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion", - "base_url": null, - "title_page": null, - "repo": "NVlabs/VoxFormer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_VoxFormer_Sparse_Voxel_Transformer_for_Camera-Based_3D_Semantic_Scene_Completion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.12251", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "L0M9ayR316g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Hidden Gems: 4D Radar Scene Flow Learning using Cross-Modal Supervision", - "base_url": null, - "title_page": null, - "repo": "Toytiny/CMFlow", - "web_page": null, - "github_page": "https://toytiny.github.io/publication/23-cmflow-cvpr/index.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ding_Hidden_Gems_4D_Radar_Scene_Flow_Learning_Using_Cross-Modal_Supervision_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00462", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hHgzBhy6NVQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mahmoud_Self-Supervised_Image-to-Point_Distillation_via_Semantically_Tolerant_Contrastive_Loss_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.05709", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Query-Centric Trajectory Prediction", - "base_url": null, - "title_page": null, - "repo": "ZikangZhou/QCNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Query-Centric_Trajectory_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "i46Sj0PUwyI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Efficient Hierarchical Entropy Model for Learned Point Cloud Compression", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Song_Efficient_Hierarchical_Entropy_Model_for_Learned_Point_Cloud_Compression_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MSnZRJ94CM8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "Novel Class Discovery for 3D Point Cloud Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "LuigiRiz/NOPS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Riz_Novel_Class_Discovery_for_3D_Point_Cloud_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11610", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kRp1F-_emj8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_MotionDiffuser_Controllable_Multi-Agent_Motion_Prediction_Using_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.03083", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IfGTZwm1abg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - }, - { - "title": "FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs", - "base_url": null, - "title_page": null, - "repo": "RLuke22/FJMP", - "web_page": null, - "github_page": "https://rluke22.github.io/FJMP/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rowe_FJMP_Factorized_Joint_Multi-Agent_Motion_Prediction_Over_Learned_Directed_Acyclic_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16197", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "asmCOhPQuNw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Autonomous Driving" - } -] \ No newline at end of file diff --git a/json_data/biometrics.json b/json_data/biometrics.json deleted file mode 100644 index 6d94bfa..0000000 --- a/json_data/biometrics.json +++ /dev/null @@ -1,277 +0,0 @@ -[ - { - "title": "Instance-Aware Domain Generalization for Face Anti-Spoofing", - "base_url": null, - "title_page": null, - "repo": "qianyuzqy/IADG", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Instance-Aware_Domain_Generalization_for_Face_Anti-Spoofing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05640", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "p8IrAiEgfiE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "OpenGait: Revisiting Gait Recognition Toward Better Practicality", - "base_url": null, - "title_page": null, - "repo": "ShiqiYu/OpenGait", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fan_OpenGait_Revisiting_Gait_Recognition_Towards_Better_Practicality_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.06597", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "Recognizability Embedding Enhancement for Very Low-Resolution Face Recognition and Quality Estimation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chai_Recognizability_Embedding_Enhancement_for_Very_Low-Resolution_Face_Recognition_and_Quality_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10066", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "e8MtMhkxE7M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "GaitGCI: Generative Counterfactual Intervention for Gait Recognition", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dou_GaitGCI_Generative_Counterfactual_Intervention_for_Gait_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.03428", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "95QcfX0Pbi0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "Rethinking Domain Generalization for Face Anti-Spoofing: Separability and Alignment", - "base_url": null, - "title_page": null, - "repo": "sunyiyou/SAFAS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Rethinking_Domain_Generalization_for_Face_Anti-Spoofing_Separability_and_Alignment_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13662", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "u9APqG02AeQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "AstroNet: When Astrocyte Meets Artificial Neural Network", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Han_AstroNet_When_Astrocyte_Meets_Artificial_Neural_Network_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "DCFace: Synthetic Face Generation with Dual Condition Diffusion Model", - "base_url": null, - "title_page": null, - "repo": "mk-minchul/dcface", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_DCFace_Synthetic_Face_Generation_With_Dual_Condition_Diffusion_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.07060", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jm1bDutCM80", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "LidarGait: Benchmarking 3D Gait Recognition with Point Clouds", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://lidargait.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shen_LidarGait_Benchmarking_3D_Gait_Recognition_With_Point_Clouds_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10598", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Z_jKaETR9Rk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "CR-FIQA: Face Image Quality Assessment by Learning Sample Relative Classifiability", - "base_url": null, - "title_page": null, - "repo": "fdbtrs/CR-FIQA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Boutros_CR-FIQA_Face_Image_Quality_Assessment_by_Learning_Sample_Relative_Classifiability_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2112.06592", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Qf_F1YLql6I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "Dual-Bridging with Adversarial Noise Generation for Domain Adaptive rPPG Estimation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Du_Dual-Bridging_With_Adversarial_Noise_Generation_for_Domain_Adaptive_rPPG_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "n6jns55AyGw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - }, - { - "title": "Evading Forensic Classifiers with Attribute-Conditioned Adversarial Faces", - "base_url": null, - "title_page": null, - "repo": "koushiksrivats/face_attribute_attack", - "web_page": null, - "github_page": "https://koushiksrivats.github.io/face_attribute_attack/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shamshad_Evading_Forensic_Classifiers_With_Attribute-Conditioned_Adversarial_Faces_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.13091", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZkPuU3lIK9U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Biometrics" - } -] \ No newline at end of file diff --git a/json_data/computational-imaging.json b/json_data/computational-imaging.json deleted file mode 100644 index 13a4331..0000000 --- a/json_data/computational-imaging.json +++ /dev/null @@ -1,1327 +0,0 @@ -[ - { - "title": "Polarimetric iToF: Measuring High-Fidelity Depth through Scattering Media", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jeon_Polarimetric_iToF_Measuring_High-Fidelity_Depth_Through_Scattering_Media_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.17618", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_1VulpRBBWs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "All-in-Focus Imaging from Event Focal Stack", - "base_url": null, - "title_page": null, - "repo": "HYLZ-2019/EFS", - "web_page": null, - "github_page": "https://hylz-2019.github.io/blog/2023/aif-efs/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lou_All-in-Focus_Imaging_From_Event_Focal_Stack_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9HQLqj4cY7o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Learning Event Guided High Dynamic Range Video Reconstruction", - "base_url": null, - "title_page": null, - "repo": "YixinYang-00/HDRev", - "web_page": null, - "github_page": "https://yixinyang-00.github.io/project/hdrev/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Learning_Event_Guided_High_Dynamic_Range_Video_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3v_3zW_KGlw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Propagate and Calibrate: Real-Time Passive Non-Line-of-Sight Tracking", - "base_url": null, - "title_page": null, - "repo": "AgainstEntropy/NLOS-Track", - "web_page": null, - "github_page": "https://againstentropy.github.io/NLOS-Track/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Propagate_and_Calibrate_Real-Time_Passive_Non-Line-of-Sight_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11791", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jRr6WGRTekI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Efficient View Synthesis and 3D-based Multi-Frame Denoising with Multiplane Feature Representations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://thomas-tanay.github.io/posts/2023-mpfer", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tanay_Efficient_View_Synthesis_and_3D-Based_Multi-Frame_Denoising_With_Multiplane_Feature_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.18139", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TmLlz7yVq9w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Occlusion-Free Scene Recovery via Neural Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "FreeButUselessSoul/occ-nerf", - "web_page": null, - "github_page": "https://freebutuselesssoul.github.io/occnerf/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_Occlusion-Free_Scene_Recovery_via_Neural_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6uaaHN2OrcE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Image Super-Resolution using T-Tetromino Pixels", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Grosche_Image_Super-Resolution_Using_T-Tetromino_Pixels_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2111.09013", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Event-based Blurry Frame Interpolation Under Blind Exposure", - "base_url": null, - "title_page": null, - "repo": "WarranWeng/EBFI-BE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Weng_Event-Based_Blurry_Frame_Interpolation_Under_Blind_Exposure_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "n3LrH5DS2yA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Decoupling-and-Aggregating for Image Exposure Correction", - "base_url": null, - "title_page": null, - "repo": "peylnog/Decoupling-and-Aggregating-for-Image-Exposure-Correction", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Decoupling-and-Aggregating_for_Image_Exposure_Correction_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Pko1GRPp9Ck", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "VILA: Learning Image Aesthetics from User Comments with Vision-Language Pretraining", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://github.com/google-research/google-research/tree/master/vila", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ke_VILA_Learning_Image_Aesthetics_From_User_Comments_With_Vision-Language_Pretraining_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14302", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "The Differentiable Lens: Compound Lens Search Over Glass Surfaces and Materials for Object Detection", - "base_url": null, - "title_page": null, - "repo": "princeton-computational-imaging/joint-lens-design", - "web_page": "https://light.princeton.edu/publication/joint-lens-design/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cote_The_Differentiable_Lens_Compound_Lens_Search_Over_Glass_Surfaces_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04441", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "f6NuKnPwVDc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Megahertz Light Steering without Moving Parts", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://imaging.cs.cmu.edu/ultrafast_steering/#code", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pediredla_Megahertz_Light_Steering_Without_Moving_Parts_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hD8btaKr5Bc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Text2Scene: Text-Driven Indoor Scene Stylization with Part-Aware Details", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hwang_Text2Scene_Text-Driven_Indoor_Scene_Stylization_With_Part-Aware_Details_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2308.16880", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CGIXY2kwIYM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "RankMix: Data Augmentation for Weakly Supervised Learning of Classifying Whole Slide Images with Diverse Sizes and Imbalanced Categories", - "base_url": null, - "title_page": null, - "repo": "willpower057/RankMix", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_RankMix_Data_Augmentation_for_Weakly_Supervised_Learning_of_Classifying_Whole_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Guided Depth Super-Resolution by Deep Anisotropic Diffusion", - "base_url": null, - "title_page": null, - "repo": "prs-eth/Diffusion-Super-Resolution", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Metzger_Guided_Depth_Super-Resolution_by_Deep_Anisotropic_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11592", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7RgXJz_3kcg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "K3DN: Disparity-Aware Kernel Estimation for Dual-Pixel Defocus Deblurring", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_K3DN_Disparity-Aware_Kernel_Estimation_for_Dual-Pixel_Defocus_Deblurring_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Rawgment: Noise-Accounted RAW Augmentation Enables Recognition in a Wide Variety of Environments", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yoshimura_Rawgment_Noise-Accounted_RAW_Augmentation_Enables_Recognition_in_a_Wide_Variety_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.16046", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Low-Light Image Enhancement via Structure Modeling and Guidance", - "base_url": null, - "title_page": null, - "repo": "xiaogang00/SMG-LLIE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Low-Light_Image_Enhancement_via_Structure_Modeling_and_Guidance_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.05839", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Yd3OEyGPC_A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Analyzing Physical Impacts using Transient Surface Wave Imaging", - "base_url": null, - "title_page": null, - "repo": "a1600012888/Analyzing-Physical-Impacts-using-Transient-Surface-Wave-Imaging", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Analyzing_Physical_Impacts_Using_Transient_Surface_Wave_Imaging_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qm-3XCkP-XM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "DC2: Dual-Camera Defocus Control by Learning to Refocus", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://defocus-control.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Alzayer_DC2_Dual-Camera_Defocus_Control_by_Learning_To_Refocus_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03285", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "T0xiA_PvwA4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "pCON: Polarimetric Coordinate Networks for Neural Scene Representations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://visual.ee.ucla.edu/pcon.htm/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Peters_pCON_Polarimetric_Coordinate_Networks_for_Neural_Scene_Representations_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Joint HDR Denoising and Fusion: A Real-World Mobile HDR Image Dataset", - "base_url": null, - "title_page": null, - "repo": "shuaizhengliu/Joint-HDRDN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Joint_HDR_Denoising_and_Fusion_A_Real-World_Mobile_HDR_Image_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TPGmNDIjYdo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "1000 FPS HDR Video with a Spike-RGB Hybrid Camera", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://changyakun.github.io/1000FPS-HDR/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chang_1000_FPS_HDR_Video_With_a_Spike-RGB_Hybrid_Camera_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "b5Ooso-48aI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "NLOST: Non-Line-of-Sight Imaging with Transformer", - "base_url": null, - "title_page": null, - "repo": "Depth2World/NLOST", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_NLOST_Non-Line-of-Sight_Imaging_With_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VrxrRO-KERI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Thermal Spread Functions (TSF): Physics-Guided Material Classification", - "base_url": null, - "title_page": null, - "repo": "aniketdashpute/TSF", - "web_page": null, - "github_page": "https://aniketdashpute.github.io/TSF/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dashpute_Thermal_Spread_Functions_TSF_Physics-Guided_Material_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00696", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Structured Kernel Estimation for Photon-Limited Deconvolution", - "base_url": null, - "title_page": null, - "repo": "sanghviyashiitb/structured-kernel-cvpr23", - "web_page": null, - "github_page": "https://sanghviyashiitb.github.io/structured-kernel-webpage/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sanghvi_Structured_Kernel_Estimation_for_Photon-Limited_Deconvolution_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.03472", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jqCUJb3BUUo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "EfficientSCI: Densely Connected Network with Space-Time Factorization for Large-Scale Video Snapshot Compressive Imaging", - "base_url": null, - "title_page": null, - "repo": "ucaswangls/EfficientSCI", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_EfficientSCI_Densely_Connected_Network_With_Space-Time_Factorization_for_Large-Scale_Video_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.10006", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "eaLP6rCjhOo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "EvShutter: Transforming Events for Unconstrained Rolling Shutter Correction", - "base_url": null, - "title_page": null, - "repo": "juliuserbach/EvShutter", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Erbach_EvShutter_Transforming_Events_for_Unconstrained_Rolling_Shutter_Correction_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0S3yT8HWcHw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Tunable Convolutions with Parametric Multi-Loss Optimization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Maggioni_Tunable_Convolutions_With_Parametric_Multi-Loss_Optimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00898", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Iqqsp_81csY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Non-Line-of-Sight Imaging with Signal Superresolution Network", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Non-Line-of-Sight_Imaging_With_Signal_Superresolution_Network_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lTvc838KPxQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Few-Shot Non-Line-of-Sight Imaging with Signal-Surface Collaborative Regularization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Few-Shot_Non-Line-of-Sight_Imaging_With_Signal-Surface_Collaborative_Regularization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15367", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "aLRuK0Lrlk4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Seeing Electric Network Frequency from Events", - "base_url": null, - "title_page": null, - "repo": "xlx-creater/E-ENF", - "web_page": null, - "github_page": "https://xlx-creater.github.io/E-ENF", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Seeing_Electric_Network_Frequency_From_Events_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.02597", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "u6jaYrfAooc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Realistic Saliency Guided Image Enhancement", - "base_url": null, - "title_page": null, - "repo": "compphoto/RealisticImageEnhancement", - "web_page": null, - "github_page": "https://yaksoy.github.io/realisticEditing/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Miangoleh_Realistic_Saliency_Guided_Image_Enhancement_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.06092", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5dKUDMnnjuo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Learned Image Compression with Mixed Transformer-CNN Architectures", - "base_url": null, - "title_page": null, - "repo": "jmliu206/LIC_TCM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Learned_Image_Compression_With_Mixed_Transformer-CNN_Architectures_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14978", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Self-Supervised Blind Motion Deblurring with Deep Expectation Maximization", - "base_url": null, - "title_page": null, - "repo": "Chilie/Deblur_MCEM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Self-Supervised_Blind_Motion_Deblurring_With_Deep_Expectation_Maximization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Brsu6HNrrTI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Solving 3D Inverse Problems using Pre-Trained 2D Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "HJ-harry/DiffusionMBIR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chung_Solving_3D_Inverse_Problems_Using_Pre-Trained_2D_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10655", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "M-SQLJr5hDQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Parallel Diffusion Models of Operator and Image for Blind Inverse Problems", - "base_url": null, - "title_page": null, - "repo": "BlindDPS/blind-dps", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chung_Parallel_Diffusion_Models_of_Operator_and_Image_for_Blind_Inverse_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10656", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "uQx63WUOIj0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Range-Nullspace Video Frame Interpolation with Focalized Motion Estimation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_Range-Nullspace_Video_Frame_Interpolation_With_Focalized_Motion_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "BWHgHTftmxo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Combining Implicit-Explicit View Correlation for Light Field Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "Congrx/LF-IENet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cong_Combining_Implicit-Explicit_View_Correlation_for_Light_Field_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9FY8La3NRRY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Document Image Shadow Removal Guided by Color-Aware Background", - "base_url": null, - "title_page": null, - "repo": "hyyh1314/BGShadowNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Document_Image_Shadow_Removal_Guided_by_Color-Aware_Background_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Op9nsx3VfHI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Kernel Aware Resampler", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bernasconi_Kernel_Aware_Resampler_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "S_NLPL0D3Is", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Polarized Color Image Denoising", - "base_url": null, - "title_page": null, - "repo": "bandasyou/pcdenoise", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Polarized_Color_Image_Denoising_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6Dt9qf_11w8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Constructing Deep Spiking Neural Networks from Artificial Neural Networks with Knowledge Distillation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Constructing_Deep_Spiking_Neural_Networks_From_Artificial_Neural_Networks_With_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05627", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Role of Transients in Two-Bounce Non-Line-of-Sight Imaging", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Somasundaram_Role_of_Transients_in_Two-Bounce_Non-Line-of-Sight_Imaging_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.01308", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9K_oV_QY-z0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Inverting the Imaging Process by Learning an Implicit Camera Model", - "base_url": null, - "title_page": null, - "repo": "xhuangcv/neucam", - "web_page": null, - "github_page": "https://xhuangcv.github.io/neucam/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Inverting_the_Imaging_Process_by_Learning_an_Implicit_Camera_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.12748", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZkYst_A7Zhs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Deep Polarization Reconstruction with PDAVIS Events", - "base_url": null, - "title_page": null, - "repo": "SensorsINI/e2p", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mei_Deep_Polarization_Reconstruction_With_PDAVIS_Events_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "pdwpfDMUXSE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "A Unified Spatial-Angular Structured Light for Single-View Acquisition of Shape and Reflectance", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_A_Unified_Spatial-Angular_Structured_Light_for_Single-View_Acquisition_of_Shape_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "O4IR6BKqzto", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Energy-Efficient Adaptive 3D Sensing", - "base_url": null, - "title_page": null, - "repo": "btilmon/holoCu", - "web_page": null, - "github_page": "https://btilmon.github.io/e3d.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tilmon_Energy-Efficient_Adaptive_3D_Sensing_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ind5EmM2ZDI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "HDR Imaging with Spatially Varying Signal-to-Noise Ratios", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chi_HDR_Imaging_With_Spatially_Varying_Signal-to-Noise_Ratios_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17253", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Swept-Angle Synthetic Wavelength Interferometry", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://imaging.cs.cmu.edu/swept_angle_swi", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kotwal_Swept-Angle_Synthetic_Wavelength_Interferometry_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.10655", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "E-oFIrXDSWY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Passive Micron-Scale Time-of-Flight with Sunlight Interferometry", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://imaging.cs.cmu.edu/sunlight_interferometry/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kotwal_Passive_Micron-Scale_Time-of-Flight_With_Sunlight_Interferometry_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10732", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "s4IZE5uoNm4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Implicit View-Time Interpolation of Stereo Videos using Multi-Plane Disparities and Non-Uniform Coordinates", - "base_url": null, - "title_page": null, - "repo": "avinashpaliwal/StereoMPD", - "web_page": "https://people.engr.tamu.edu/nimak/Papers/CVPR23StereoVideo/index.html", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Paliwal_Implicit_View-Time_Interpolation_of_Stereo_Videos_Using_Multi-Plane_Disparities_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17181", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XJa_bf8OCrc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - }, - { - "title": "Learning a Deep Color Difference Metric for Photographic Images", - "base_url": null, - "title_page": null, - "repo": "haoychen3/CD-Flow", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Learning_a_Deep_Color_Difference_Metric_for_Photographic_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14964", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XwRfCcPDnnE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computational Imaging" - } -] \ No newline at end of file diff --git a/json_data/computer-vision-for-social-good.json b/json_data/computer-vision-for-social-good.json deleted file mode 100644 index be6cf1f..0000000 --- a/json_data/computer-vision-for-social-good.json +++ /dev/null @@ -1,127 +0,0 @@ -[ - { - "title": "Unlearnable Clusters: Towards Label-Agnostic Unlearnable Examples", - "base_url": null, - "title_page": null, - "repo": "jiamingzhang94/Unlearnable-Clusters", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Unlearnable_Clusters_Towards_Label-Agnostic_Unlearnable_Examples_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.01217", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision for Social Good" - }, - { - "title": "On the Difficulty of Unpaired Infrared-to-Visible Video Translation: Fine-Grained Content-Rich Patches Transfer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_On_the_Difficulty_of_Unpaired_Infrared-to-Visible_Video_Translation_Fine-Grained_Content-Rich_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ENiyidPXqb8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision for Social Good" - }, - { - "title": "SCConv: Spatial and Channel Reconstruction Convolution for Feature Redundancy", - "base_url": null, - "title_page": null, - "repo": "cheng-haha/ScConv", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_SCConv_Spatial_and_Channel_Reconstruction_Convolution_for_Feature_Redundancy_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YDV_qAw9c1k", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision for Social Good" - }, - { - "title": "TruFor: Leveraging All-Round Clues for Trustworthy Image Forgery Detection and Localization", - "base_url": null, - "title_page": null, - "repo": "grip-unina/TruFor", - "web_page": null, - "github_page": "https://grip-unina.github.io/TruFor/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Guillaro_TruFor_Leveraging_All-Round_Clues_for_Trustworthy_Image_Forgery_Detection_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.10957", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision for Social Good" - }, - { - "title": "Angelic Patches for Improving Third-Party Object Detector Performance", - "base_url": null, - "title_page": null, - "repo": "averysi224/angelic_patches", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Si_Angelic_Patches_for_Improving_Third-Party_Object_Detector_Performance_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision for Social Good" - } -] \ No newline at end of file diff --git a/json_data/computer-vision-theory.json b/json_data/computer-vision-theory.json deleted file mode 100644 index 3a798e5..0000000 --- a/json_data/computer-vision-theory.json +++ /dev/null @@ -1,127 +0,0 @@ -[ - { - "title": "Neural Dependencies Emerging from Learning Massive Categories", - "base_url": null, - "title_page": null, - "repo": "RuiLiFeng/Neural-Dependencies", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_Neural_Dependencies_Emerging_From_Learning_Massive_Categories_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12339", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dQup_xxcuCo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision Theory" - }, - { - "title": "Gaussian Label Distribution Learning for Spherical Image Object Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Gaussian_Label_Distribution_Learning_for_Spherical_Image_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "BgHCXmFep9w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision Theory" - }, - { - "title": "Unbalanced Optimal Transport: A Unified Framework for Object Detection", - "base_url": null, - "title_page": null, - "repo": "hdeplaen/uotod", - "web_page": null, - "github_page": "https://hdeplaen.github.io/uotod/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/De_Plaen_Unbalanced_Optimal_Transport_A_Unified_Framework_for_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.02402", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ma3Y-TbpJNs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision Theory" - }, - { - "title": "DropKey for Vision Transformer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_DropKey_for_Vision_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.02646", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7ACKCzPg5hE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision Theory" - }, - { - "title": "SplineCam: Exact Visualization and Characterization of Deep Network Geometry and Decision Boundaries", - "base_url": null, - "title_page": null, - "repo": "AhmedImtiazPrio/SplineCAM", - "web_page": null, - "github_page": "https://imtiazhumayun.github.io/splinecam/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Humayun_SplineCam_Exact_Visualization_and_Characterization_of_Deep_Network_Geometry_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.12828", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NTXEqGCUDR0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Computer Vision Theory" - } -] \ No newline at end of file diff --git a/json_data/datasets-and-evaluation.json b/json_data/datasets-and-evaluation.json deleted file mode 100644 index e44b238..0000000 --- a/json_data/datasets-and-evaluation.json +++ /dev/null @@ -1,1352 +0,0 @@ -[ - { - "title": "Large-Scale Training Data Search for Object Re-Identification", - "base_url": null, - "title_page": null, - "repo": "yorkeyao/SnP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yao_Large-Scale_Training_Data_Search_for_Object_Re-Identification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16186", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OAZ0Pka2mKE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Class Prototypes based Contrastive Learning for Classifying Multi-Label and Fine-grained Educational Videos", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gupta_Class_Prototypes_Based_Contrastive_Learning_for_Classifying_Multi-Label_and_Fine-Grained_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EhIeZtBB8bk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "V2X-Seq: A Large-Scale Sequential Dataset for Vehicle-Infrastructure Cooperative Perception and Forecasting", - "base_url": null, - "title_page": null, - "repo": "AIR-THU/DAIR-V2X-Seq", - "web_page": "https://thudair.baai.ac.cn/index", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_V2X-Seq_A_Large-Scale_Sequential_Dataset_for_Vehicle-Infrastructure_Cooperative_Perception_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.05938", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "NewsNet: A Novel Dataset for Hierarchical Temporal Segmentation", - "base_url": null, - "title_page": null, - "repo": "NewsNet-Benchmark/NewsNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_NewsNet_A_Novel_Dataset_for_Hierarchical_Temporal_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dEGco30TBCk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "CLOTH4D: A Dataset for Clothed Human Reconstruction", - "base_url": null, - "title_page": null, - "repo": "AemikaChow/AiDLab-fAshIon-Data", - "web_page": null, - "github_page": "https://github.com/AemikaChow/CLOTH4D", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zou_CLOTH4D_A_Dataset_for_Clothed_Human_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8Cc_kl55bFo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Accelerating Dataset Distillation via Model Augmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Accelerating_Dataset_Distillation_via_Model_Augmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06152", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "ImageNet-E: Benchmarking Neural Network Robustness via Attribute Editing", - "base_url": null, - "title_page": null, - "repo": "alibaba/easyrobust", - "web_page": null, - "github_page": "https://github.com/alibaba/easyrobust/tree/main/benchmarks/imagenet-e", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_ImageNet-E_Benchmarking_Neural_Network_Robustness_via_Attribute_Editing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17096", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "66Be-LDVHbc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Visual Atoms: Pre-Training Vision Transformers with Sinusoidal Waves", - "base_url": null, - "title_page": null, - "repo": "masora1030/CVPR2023-FDSL-on-VisualAtom", - "web_page": null, - "github_page": "https://masora1030.github.io/Visual-Atoms-Pre-training-Vision-Transformers-with-Sinusoidal-Waves/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Takashima_Visual_Atoms_Pre-Training_Vision_Transformers_With_Sinusoidal_Waves_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01112", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2reoDrFf0OA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Infinite Photorealistic Worlds using Procedural Generation", - "base_url": null, - "title_page": null, - "repo": "princeton-vl/infinigen", - "web_page": "https://infinigen.org/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Raistrick_Infinite_Photorealistic_Worlds_Using_Procedural_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.09310", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6tgspeI-GHY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "CelebV-Text: A Large-Scale Facial Text-Video Dataset", - "base_url": null, - "title_page": null, - "repo": "celebv-text/CelebV-Text", - "web_page": null, - "github_page": "https://celebv-text.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_CelebV-Text_A_Large-Scale_Facial_Text-Video_Dataset_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14717", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0TS1hQwjNWw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Spring: A High-Resolution High-Detail Dataset and Benchmark for Scene Flow, Optical Flow and Stereo", - "base_url": null, - "title_page": null, - "repo": "cv-stuttgart/sceneflow_from_blender", - "web_page": "https://spring-benchmark.org/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mehl_Spring_A_High-Resolution_High-Detail_Dataset_and_Benchmark_for_Scene_Flow_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01943", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "omcntkTrFTg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Connecting Vision and Language with Video Localized Narratives", - "base_url": null, - "title_page": null, - "repo": "google/video-localized-narratives", - "web_page": null, - "github_page": "https://google.github.io/video-localized-narratives/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Voigtlaender_Connecting_Vision_and_Language_With_Video_Localized_Narratives_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.11217", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "j1LUa-Cd4L8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Towards Artistic Image Aesthetics Assessment: A Large-Scale Dataset and a New Method", - "base_url": null, - "title_page": null, - "repo": "Dreemurr-T/BAID", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yi_Towards_Artistic_Image_Aesthetics_Assessment_A_Large-Scale_Dataset_and_a_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15166", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "U1h4S7J2xnw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "MD-VQA: Multi-Dimensional Quality Assessment for UGC Live Videos", - "base_url": null, - "title_page": null, - "repo": "zzc-1998/MD-VQA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_MD-VQA_Multi-Dimensional_Quality_Assessment_for_UGC_Live_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14933", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Toward RAW Object Detection: A New Benchmark and a New Model", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Toward_RAW_Object_Detection_A_New_Benchmark_and_a_New_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dyudIByvYKc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Objaverse: A Universe of Annotated 3D Objects", - "base_url": null, - "title_page": null, - "repo": "allenai/objaverse-xl", - "web_page": "https://objaverse.allenai.org/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Deitke_Objaverse_A_Universe_of_Annotated_3D_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08051", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Habitat-Matterport 3D Semantics Dataset", - "base_url": null, - "title_page": null, - "repo": "matterport/habitat-matterport-3dresearch", - "web_page": "https://aihabitat.org/datasets/hm3d-semantics/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yadav_Habitat-Matterport_3D_Semantics_Dataset_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.05633", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Similarity Metric Learning for RGB-Infrared Group Re-Identification", - "base_url": null, - "title_page": null, - "repo": "WhollyOat/CM-Group", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_Similarity_Metric_Learning_for_RGB-Infrared_Group_Re-Identification_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VUWEkJYvDO0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "MISC210K: A Large-Scale Dataset for Multi-Instance Semantic Correspondence", - "base_url": null, - "title_page": null, - "repo": "YXSUNMADMAX/MISC210K", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_MISC210K_A_Large-Scale_Dataset_for_Multi-Instance_Semantic_Correspondence_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "WeatherStream: Light Transport Automation of Single Image Deweathering", - "base_url": null, - "title_page": null, - "repo": "UCLA-VMG/WeatherStream", - "web_page": "https://visual.ee.ucla.edu/wstream.htm/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_WeatherStream_Light_Transport_Automation_of_Single_Image_Deweathering_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "y2cQdAmegaY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "MobileBrick: Building LEGO for 3D Reconstruction on Mobile Devices", - "base_url": null, - "title_page": null, - "repo": "ActiveVisionLab/MobileBrick", - "web_page": "https://code.active.vision/MobileBrick/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_MobileBrick_Building_LEGO_for_3D_Reconstruction_on_Mobile_Devices_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01932", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0NzsB3rdXlY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "GeoNet: Benchmarking Unsupervised Adaptation Across Geographies", - "base_url": null, - "title_page": null, - "repo": "ViLab-UCSD/GeoNet", - "web_page": null, - "github_page": "https://tarun005.github.io/GeoNet/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kalluri_GeoNet_Benchmarking_Unsupervised_Adaptation_Across_Geographies_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15443", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Logical Consistency and Greater Descriptive Power for Facial Hair Attribute Learning", - "base_url": null, - "title_page": null, - "repo": "HaiyuWu/LogicalConsistency", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Logical_Consistency_and_Greater_Descriptive_Power_for_Facial_Hair_Attribute_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.11102", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Pmpe3jJu8zQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "PACO: Parts and Attributes of Common Objects", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/paco", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ramanathan_PACO_Parts_and_Attributes_of_Common_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.01795", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "sIDX_2W9Wc8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Understanding Deep Generative Models with Generalized Empirical Likelihoods", - "base_url": null, - "title_page": null, - "repo": "google-deepmind/understanding_deep_generative_models_with_generalized_empirical_likelihood", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ravuri_Understanding_Deep_Generative_Models_With_Generalized_Empirical_Likelihoods_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.09780", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "BEDLAM: A Synthetic Dataset of Bodies Exhibiting Detailed Lifelike Animated Motion", - "base_url": null, - "title_page": null, - "repo": "pixelite1201/BEDLAM", - "web_page": "https://bedlam.is.tue.mpg.de/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Black_BEDLAM_A_Synthetic_Dataset_of_Bodies_Exhibiting_Detailed_Lifelike_Animated_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.16940", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OBttHFwdtfI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Unicode Analogies: An Anti-Objectivist Visual Reasoning Challenge", - "base_url": null, - "title_page": null, - "repo": "SvenShade/UnicodeAnalogies", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Spratley_Unicode_Analogies_An_Anti-Objectivist_Visual_Reasoning_Challenge_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "A New Comprehensive Benchmark for Semi-Supervised Video Anomaly Detection and Anticipation", - "base_url": null, - "title_page": null, - "repo": "zugexiaodui/campus_vad_code", - "web_page": null, - "github_page": "https://campusvad.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cao_A_New_Comprehensive_Benchmark_for_Semi-Supervised_Video_Anomaly_Detection_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.13611", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kdLapd4rBCc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "An In-Depth Exploration of Person Re-Identification and Gait Recognition in Cloth-Changing Conditions", - "base_url": null, - "title_page": null, - "repo": "BNU-IVC/CCPG", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_An_In-Depth_Exploration_of_Person_Re-Identification_and_Gait_Recognition_in_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Toward Verifiable and Reproducible Human Evaluation for Text-to-Image Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Otani_Toward_Verifiable_and_Reproducible_Human_Evaluation_for_Text-to-Image_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.01816", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "65QMukifH60", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "BiasBed - Rigorous Texture Bias Evaluation", - "base_url": null, - "title_page": null, - "repo": "D1noFuzi/BiasBed", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kalischek_BiasBed_-_Rigorous_Texture_Bias_Evaluation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13190", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "A Large-Scale Homography Benchmark", - "base_url": null, - "title_page": null, - "repo": "danini/homography-benchmark", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Barath_A_Large-Scale_Homography_Benchmark_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.09997", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8RmTlekfKGY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Exploring and Utilizing Pattern Imbalance", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mei_Exploring_and_Utilizing_Pattern_Imbalance_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "w6AUguS5eQQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Full or Weak Annotations? An Adaptive Strategy for Budget-constrained Annotation Campaigns", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tejero_Full_or_Weak_Annotations_An_Adaptive_Strategy_for_Budget-Constrained_Annotation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11678", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PixUJ9Xl5_8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "ReLight My NeRF: A Dataset for Novel View Synthesis and Relighting of Real World Objects", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://eyecan-ai.github.io/rene/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Toschi_ReLight_My_NeRF_A_Dataset_for_Novel_View_Synthesis_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10448", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "23vZMbbZAHY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Open-Vocabulary Attribute Detection", - "base_url": null, - "title_page": null, - "repo": "OVAD-Benchmark/ovad-benchmark-code", - "web_page": null, - "github_page": "https://ovad-benchmark.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bravo_Open-Vocabulary_Attribute_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12914", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "cWOspjb9sPs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Visual DNA: Representing and Comparing Images using Distributions of Neuron Activations", - "base_url": null, - "title_page": null, - "repo": "bramtoula/vdna", - "web_page": null, - "github_page": "https://bramtoula.github.io/vdna/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ramtoula_Visual_DNA_Representing_and_Comparing_Images_Using_Distributions_of_Neuron_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10036", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dCbAiKrq1Jw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Blind Image Quality Assessment via Vision-Language Correspondence: A Multitask Learning Perspective", - "base_url": null, - "title_page": null, - "repo": "zwx8981/LIQE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Blind_Image_Quality_Assessment_via_Vision-Language_Correspondence_A_Multitask_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14968", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "An Image Quality Assessment Dataset for Portraits", - "base_url": null, - "title_page": null, - "repo": "DXOMARK-Research/PIQ2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chahine_An_Image_Quality_Assessment_Dataset_for_Portraits_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05772", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "cvWjOWq5wnk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Multi-Sensor Large-Scale Dataset for Multi-View 3D Reconstruction", - "base_url": null, - "title_page": null, - "repo": "Skoltech-3D/sk3d_data", - "web_page": "https://skoltech3d.appliedai.tech/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Voynov_Multi-Sensor_Large-Scale_Dataset_for_Multi-View_3D_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2203.06111", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KPwghPyZWDE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "3D-POP - An Automated Annotation Approach to Facilitate Markerless 2D-3D Tracking of Freely Moving Birds with Marker-based Motion Capture", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Naik_3D-POP_-_An_Automated_Annotation_Approach_to_Facilitate_Markerless_2D-3D_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13174", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "uGMsJ0qQZrA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Positive-Augmented Contrastive Learning for Image and Video Captioning Evaluation", - "base_url": null, - "title_page": null, - "repo": "aimagelab/pacscore", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sarto_Positive-Augmented_Contrastive_Learning_for_Image_and_Video_Captioning_Evaluation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12112", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4PP9fCdBw88", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Visual Localization using Imperfect 3D Models from the Internet", - "base_url": null, - "title_page": null, - "repo": "v-pnk/cadloc", - "web_page": null, - "github_page": "https://v-pnk.github.io/cadloc/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Panek_Visual_Localization_Using_Imperfect_3D_Models_From_the_Internet_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05947", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4Na026FMaP0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Fantastic Breaks: A Dataset of Paired 3D Scans of Real-World Broken Objects and Their Complete Counterparts", - "base_url": null, - "title_page": null, - "repo": "Terascale-All-sensing-Research-Studio/FantasticBreaks", - "web_page": null, - "github_page": "https://terascale-all-sensing-research-studio.github.io/FantasticBreaks/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lamb_Fantastic_Breaks_A_Dataset_of_Paired_3D_Scans_of_Real-World_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14152", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "StarCraftImage: A Dataset for Prototyping Spatial Reasoning Methods for Multi-Agent Environments", - "base_url": null, - "title_page": null, - "repo": "inouye-lab/starcraftimage", - "web_page": "https://starcraftdata.davidinouye.com/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kulinski_StarCraftImage_A_Dataset_for_Prototyping_Spatial_Reasoning_Methods_for_Multi-Agent_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "MammalNet: A Large-Scale Video Benchmark for Mammal Recognition and Behavior Understanding", - "base_url": null, - "title_page": null, - "repo": "Vision-CAIR/MammalNet", - "web_page": null, - "github_page": "https://mammal-net.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_MammalNet_A_Large-Scale_Video_Benchmark_for_Mammal_Recognition_and_Behavior_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.00576", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "sY71Oag2JMw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "A Large-Scale Robustness Analysis of Video Action Recognition Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Schiappa_A_Large-Scale_Robustness_Analysis_of_Video_Action_Recognition_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.01398", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Affection: Learning Affective Explanations for Real-World Visual Data", - "base_url": null, - "title_page": null, - "repo": "affectivetools/eeai", - "web_page": "https://affective-explanations.org/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Achlioptas_Affection_Learning_Affective_Explanations_for_Real-World_Visual_Data_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.01946", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "b7dvTySVxXU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "ShapeTalk: A Language Dataset and Framework for 3D Shape Edits and Deformations", - "base_url": null, - "title_page": null, - "repo": "optas/changeit3d", - "web_page": null, - "github_page": "https://changeit3d.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Achlioptas_ShapeTalk_A_Language_Dataset_and_Framework_for_3D_Shape_Edits_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "Deep Depth Estimation from Thermal Image", - "base_url": null, - "title_page": null, - "repo": "UkcheolShin/MS2-MultiSpectralStereoDataset", - "web_page": "https://sites.google.com/view/multi-spectral-stereo-dataset", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shin_Deep_Depth_Estimation_From_Thermal_Image_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "DF-Platter: Multi-Face Heterogeneous Deepfake Dataset", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://iab-rubric.org/df-platter-database", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Narayan_DF-Platter_Multi-Face_Heterogeneous_Deepfake_Dataset_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OeCc6mrP5uE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "A New Dataset based on Images Taken by Blind People for Testing the Robustness of Image Classification Models Trained for ImageNet Categories", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://vizwiz.org/tasks-and-datasets/image-classification/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bafghi_A_New_Dataset_Based_on_Images_Taken_by_Blind_People_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bw7l09n7tZ8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "RealImpact: A Dataset of Impact Sound Fields for Real Objects", - "base_url": null, - "title_page": null, - "repo": "samuel-clarke/RealImpact", - "web_page": "https://samuelpclarke.com/realimpact/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Clarke_RealImpact_A_Dataset_of_Impact_Sound_Fields_for_Real_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.09944", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OeZMeze-oIs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - }, - { - "title": "NICO++: Towards Better Benchmarking for Domain Generalization", - "base_url": null, - "title_page": null, - "repo": "xxgege/NICO-plus", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_NICO_Towards_Better_Benchmarking_for_Domain_Generalization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2204.08040", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Datasets and Evaluation" - } -] \ No newline at end of file diff --git a/json_data/deep-learning-architectures-and-techniques.json b/json_data/deep-learning-architectures-and-techniques.json deleted file mode 100644 index 622ad5a..0000000 --- a/json_data/deep-learning-architectures-and-techniques.json +++ /dev/null @@ -1,2302 +0,0 @@ -[ - { - "title": "PA&DA: Jointly Sampling PAth and DAta for Consistent NAS", - "base_url": null, - "title_page": null, - "repo": "ShunLu91/PA-DA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_PADA_Jointly_Sampling_Path_and_Data_for_Consistent_NAS_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14772", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Aphq-rzvato", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Top-Down Visual Attention from Analysis by Synthesis", - "base_url": null, - "title_page": null, - "repo": "bfshi/AbSViT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shi_Top-Down_Visual_Attention_From_Analysis_by_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13043", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9MG--mbXfYE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "CUF: Continuous Upsampling Filters", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://cuf-paper.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Vasconcelos_CUF_Continuous_Upsampling_Filters_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.06965", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "pusooSMrbHs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Curvature-Balanced Feature Manifold Learning for Long-tailed Classification", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ma_Curvature-Balanced_Feature_Manifold_Learning_for_Long-Tailed_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12307", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Neighborhood Attention Transformer", - "base_url": null, - "title_page": null, - "repo": "SHI-Labs/Neighborhood-Attention-Transformer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hassani_Neighborhood_Attention_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2204.07143", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ya4BfioxIHA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Progressive Random Convolutions for Single Domain Generalization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Choi_Progressive_Random_Convolutions_for_Single_Domain_Generalization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00424", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Domain Expansion of Image Generators", - "base_url": null, - "title_page": null, - "repo": "adobe-research/domain-expansion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nitzan_Domain_Expansion_of_Image_Generators_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.05225", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Gradient Norm Aware Minimization Seeks First-Order Flatness and Improves Generalization", - "base_url": null, - "title_page": null, - "repo": "xxgege/GAM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Gradient_Norm_Aware_Minimization_Seeks_First-Order_Flatness_and_Improves_Generalization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.03108", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Boosting Verified Training for Robust Image Classifications via Abstraction", - "base_url": null, - "title_page": null, - "repo": "zhangzhaodi233/ABSCERT", - "web_page": null, - "github_page": "https://cuf-paper.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Boosting_Verified_Training_for_Robust_Image_Classifications_via_Abstraction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11552", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "abLiWBDfxCU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Joint Token Pruning and Squeezing Towards more Aggressive Compression of Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "megvii-research/TPS-CVPR2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_Joint_Token_Pruning_and_Squeezing_Towards_More_Aggressive_Compression_of_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10716", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "BxM3R_9KKRs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Vision Transformer with Super Token Sampling", - "base_url": null, - "title_page": null, - "repo": "adaptivetokensampling/ATS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Vision_Transformer_With_Super_Token_Sampling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11167", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-n-DuHRgmpY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "PointListNet: Deep Learning on 3D Point Lists", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fan_PointListNet_Deep_Learning_on_3D_Point_Lists_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Rate Gradient Approximation Attack Threats Deep Spiking Neural Networks", - "base_url": null, - "title_page": null, - "repo": "putshua/SNN_attack_RGA", - "web_page": "https://cvpr2023.thecvf.com/virtual/2023/poster/22925", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bu_Rate_Gradient_Approximation_Attack_Threats_Deep_Spiking_Neural_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dt2c0vP1cGk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Masked Jigsaw Puzzle: A Versatile Position Embedding for Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "yhlleo/MJP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ren_Masked_Jigsaw_Puzzle_A_Versatile_Position_Embedding_for_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.12551", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2ebjSE9pHRc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Deep Graph Reprogramming", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jing_Deep_Graph_Reprogramming_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.14593", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "ConvNeXt V2: Co-Designing and Scaling ConvNets With Masked Autoencoders", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/ConvNeXt-V2", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Woo_ConvNeXt_V2_Co-Designing_and_Scaling_ConvNets_With_Masked_Autoencoders_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.00808", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wXuC7iDZI2M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Frustratingly Easy Regularization on Representation Can Boost Deep Reinforcement Learning", - "base_url": null, - "title_page": null, - "repo": "sweetice/PEER-CVPR23", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Frustratingly_Easy_Regularization_on_Representation_Can_Boost_Deep_Reinforcement_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.14557", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9YQoxTVn0nI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Unified Pose Sequence Modeling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Foo_Unified_Pose_Sequence_Modeling_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "M6hthIqiLQM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "RIFormer: Keep Your Vision Backbone Effective but Removing Token Mixer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_RIFormer_Keep_Your_Vision_Backbone_Effective_but_Removing_Token_Mixer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05659", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Real-Time Neural Light Field on Mobile Devices", - "base_url": null, - "title_page": null, - "repo": "snap-research/MobileR2L", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cao_Real-Time_Neural_Light_Field_on_Mobile_Devices_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08057", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Towards Scalable Neural Representation for Diverse Videos", - "base_url": null, - "title_page": null, - "repo": "boheumd/D-NeRV", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Towards_Scalable_Neural_Representation_for_Diverse_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14124", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ByqNGvCCHPA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "AutoFocusFormer: Image Segmentation off the Grid", - "base_url": null, - "title_page": null, - "repo": "apple/ml-autofocusformer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ziwen_AutoFocusFormer_Image_Segmentation_off_the_Grid_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.12406", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "i1mZtk70yGY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Minimizing the Accumulated Trajectory Error to Improve Dataset Distillation", - "base_url": null, - "title_page": null, - "repo": "AngusDujw/FTD-distillation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Du_Minimizing_the_Accumulated_Trajectory_Error_To_Improve_Dataset_Distillation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11004", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Deep Learning of Partial Graph Matching via Differentiable Top-K", - "base_url": null, - "title_page": null, - "repo": "Thinklab-SJTU/ThinkMatch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Deep_Learning_of_Partial_Graph_Matching_via_Differentiable_Top-K_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zFZ2WQHlVGo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "WIRE: Wavelet Implicit Neural Representations", - "base_url": null, - "title_page": null, - "repo": "vishwa91/wire", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Saragadam_WIRE_Wavelet_Implicit_Neural_Representations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.05187", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4jI8DZPEfEY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Decompose, Adjust, Compose: Effective Normalization by Playing With Frequency for Domain Generalization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lee_Decompose_Adjust_Compose_Effective_Normalization_by_Playing_With_Frequency_for_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.02328", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Towards a Smaller Student: Capacity Dynamic Distillation for Efficient Image Retrieval", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_Towards_a_Smaller_Student_Capacity_Dynamic_Distillation_for_Efficient_Image_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09230", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "UniHCP: A Unified Model for Human-Centric Perceptions", - "base_url": null, - "title_page": null, - "repo": "OpenGVLab/UniHCP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ci_UniHCP_A_Unified_Model_for_Human-Centric_Perceptions_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.02936", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Trainable Projected Gradient Method for Robust Fine-Tuning", - "base_url": null, - "title_page": null, - "repo": "PotatoTian/TPGM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tian_Trainable_Projected_Gradient_Method_for_Robust_Fine-Tuning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10720", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Boosting Semi-Supervised Learning by Exploiting All Unlabeled Data", - "base_url": null, - "title_page": null, - "repo": "megvii-research/FullMatch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Boosting_Semi-Supervised_Learning_by_Exploiting_All_Unlabeled_Data_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11066", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AhizJGbenCY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "B-Spline Texture Coefficients Estimator for Screen Content Image Super-Resolution", - "base_url": null, - "title_page": null, - "repo": "ByeongHyunPak/btc", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pak_B-Spline_Texture_Coefficients_Estimator_for_Screen_Content_Image_Super-Resolution_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SmVsO3POFZk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Run, Don't Walk: Chasing Higher FLOPS for Faster Neural Networks", - "base_url": null, - "title_page": null, - "repo": "JierunChen/FasterNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Run_Dont_Walk_Chasing_Higher_FLOPS_for_Faster_Neural_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.03667", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Z-SX5r2gVeU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "HyperMatch: Noise-Tolerant Semi-Supervised Learning via Relaxed Contrastive Constraint", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_HyperMatch_Noise-Tolerant_Semi-Supervised_Learning_via_Relaxed_Contrastive_Constraint_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RHF3ADsRwUI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "From Node Interaction To Hop Interaction: New Effective and Scalable Graph Learning Paradigm", - "base_url": null, - "title_page": null, - "repo": "JC-202/HopGNN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_From_Node_Interaction_To_Hop_Interaction_New_Effective_and_Scalable_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11761", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "z14shuNm6Fk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Slide-Transformer: Hierarchical Vision Transformer With Local Self-Attention", - "base_url": null, - "title_page": null, - "repo": "LeapLabTHU/Slide-Transformer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pan_Slide-Transformer_Hierarchical_Vision_Transformer_With_Local_Self-Attention_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04237", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-lceSYJ4adE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "On the Pitfall of Mixup for Uncertainty Calibration", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_On_the_Pitfall_of_Mixup_for_Uncertainty_Calibration_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xyJBTPsL-dQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Edges to Shapes to Concepts: Adversarial Augmentation for Robust Vision", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tripathi_Edges_to_Shapes_to_Concepts_Adversarial_Augmentation_for_Robust_Vision_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "grwNf3mEzlo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Mod-Squad: Designing Mixtures of Experts As Modular Multi-Task Learners", - "base_url": null, - "title_page": null, - "repo": "UMass-Foundation-Model/Mod-Squad", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Mod-Squad_Designing_Mixtures_of_Experts_As_Modular_Multi-Task_Learners_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08066", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PK44nE1M8ug", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "DeepMAD: Mathematical Architecture Design for Deep Convolutional Neural Network", - "base_url": null, - "title_page": null, - "repo": "alibaba/lightweight-neural-architecture-search", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shen_DeepMAD_Mathematical_Architecture_Design_for_Deep_Convolutional_Neural_Network_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.02165", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IfmdIs3QGaA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "PaCa-ViT: Learning Patch-to-Cluster Attention in Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "iVMCL/PaCaViT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Grainger_PaCa-ViT_Learning_Patch-to-Cluster_Attention_in_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KajsMJAhisI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "BiFormer: Vision Transformer With Bi-Level Routing Attention", - "base_url": null, - "title_page": null, - "repo": "rayleizhu/BiFormer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_BiFormer_Vision_Transformer_With_Bi-Level_Routing_Attention_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08810", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VHaJl2FNxP8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "DeSTSeg: Segmentation Guided Denoising Student-Teacher for Anomaly Detection", - "base_url": null, - "title_page": null, - "repo": "apple/ml-destseg", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_DeSTSeg_Segmentation_Guided_Denoising_Student-Teacher_for_Anomaly_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11317", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Hierarchical Neural Memory Network for Low Latency Event Processing", - "base_url": null, - "title_page": null, - "repo": "hamarh/HMNet_pth", - "web_page": null, - "github_page": "https://hamarh.github.io/hmnet/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hamaguchi_Hierarchical_Neural_Memory_Network_for_Low_Latency_Event_Processing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.17852", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Er-sKbcov8I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Block Selection Method for Using Feature Norm in Out-of-Distribution Detection", - "base_url": null, - "title_page": null, - "repo": "gist-ailab/block-selection-for-OOD-detection", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_Block_Selection_Method_for_Using_Feature_Norm_in_Out-of-Distribution_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.02295", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "prgocfj5hnc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "NAR-Former: Neural Architecture Representation Learning Towards Holistic Attributes Prediction", - "base_url": null, - "title_page": null, - "repo": "yuny220/NAR-Former", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yi_NAR-Former_Neural_Architecture_Representation_Learning_Towards_Holistic_Attributes_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.08024", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VuCVQy7Ea9I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "MDL-NAS: A Joint Multi-Domain Learning Framework for Vision Transformer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_MDL-NAS_A_Joint_Multi-Domain_Learning_Framework_for_Vision_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SjL4JXxiUw8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "VNE: An Effective Method for Improving Deep Representation by Manipulating Eigenvalue Distribution", - "base_url": null, - "title_page": null, - "repo": "jaeill/CVPR23-VNE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_VNE_An_Effective_Method_for_Improving_Deep_Representation_by_Manipulating_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.01434", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YW4DRxU0LrI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Multi-Agent Automated Machine Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Multi-Agent_Automated_Machine_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.09084", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lVkpmbUbvM4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Making Vision Transformers Efficient From a Token Sparsification View", - "base_url": null, - "title_page": null, - "repo": "changsn/STViT-R", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chang_Making_Vision_Transformers_Efficient_From_a_Token_Sparsification_View_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08685", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "obLwEmelttw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Integral Neural Networks", - "base_url": null, - "title_page": null, - "repo": "TheStageAI/TorchIntegral", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Solodskikh_Integral_Neural_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MdSVyi00r3E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "RangeViT: Towards Vision Transformers for 3D Semantic Segmentation in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "valeoai/rangevit", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ando_RangeViT_Towards_Vision_Transformers_for_3D_Semantic_Segmentation_in_Autonomous_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.10222", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "MIANet: Aggregating Unbiased Instance and General Information for Few-Shot Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "Aldrich2y/MIANet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_MIANet_Aggregating_Unbiased_Instance_and_General_Information_for_Few-Shot_Semantic_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.13864", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "One-Shot Model for Mixed-Precision Quantization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Koryakovskiy_One-Shot_Model_for_Mixed-Precision_Quantization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vHSGGL9XR6M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Learning Dynamic Style Kernels for Artistic Style Transfer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Learning_Dynamic_Style_Kernels_for_Artistic_Style_Transfer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00414", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "r5xUjntANCA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "SVGformer: Representation Learning for Continuous Vector Graphics Using Transformers", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cao_SVGformer_Representation_Learning_for_Continuous_Vector_Graphics_Using_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "s6OqutGKGa4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "How To Prevent the Continuous Damage of Noises To Model Training?", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_How_To_Prevent_the_Continuous_Damage_of_Noises_To_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "B3g-PE5R3Ac", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "GKEAL: Gaussian Kernel Embedded Analytic Learning for Few-Shot Class Incremental Task", - "base_url": null, - "title_page": null, - "repo": "ZHUANGHP/Analytic-continual-learning", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhuang_GKEAL_Gaussian_Kernel_Embedded_Analytic_Learning_for_Few-Shot_Class_Incremental_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5hSrTcvkQ00", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Differentiable Architecture Search With Random Features", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Differentiable_Architecture_Search_With_Random_Features_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.08835", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "ERM-KTP: Knowledge-Level Machine Unlearning via Knowledge Transfer", - "base_url": null, - "title_page": null, - "repo": "RUIYUN-ML/ERM-KTP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_ERM-KTP_Knowledge-Level_Machine_Unlearning_via_Knowledge_Transfer_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VUG0eFlyYn4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "FIANCEE: Faster Inference of Adversarial Networks via Conditional Early Exits", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Karpikova_FIANCEE_Faster_Inference_of_Adversarial_Networks_via_Conditional_Early_Exits_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10306", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Beyond Attentive Tokens: Incorporating Token Importance and Diversity for Efficient Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "BWLONG/BeyondAttentiveTokens", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Long_Beyond_Attentive_Tokens_Incorporating_Token_Importance_and_Diversity_for_Efficient_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11315", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Token Turing Machines", - "base_url": null, - "title_page": null, - "repo": "projects/token_turing", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ryoo_Token_Turing_Machines_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.09119", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "A21OGHJ4FmE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Co-Training 2L Submodels for Visual Recognition", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Touvron_Co-Training_2L_Submodels_for_Visual_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04884", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "HOTNAS: Hierarchical Optimal Transport for Neural Architecture Search", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_HOTNAS_Hierarchical_Optimal_Transport_for_Neural_Architecture_Search_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NV-HVjmtr_8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "SLACK: Stable Learning of Augmentations With Cold-Start and KL Regularization", - "base_url": null, - "title_page": null, - "repo": "naver/slack", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Marrie_SLACK_Stable_Learning_of_Augmentations_With_Cold-Start_and_KL_Regularization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.09998v1", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nTH5SME2_fk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "MarginMatch: Improving Semi-Supervised Learning with Pseudo-Margins", - "base_url": null, - "title_page": null, - "repo": "tsosea2/marginmatch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sosea_MarginMatch_Improving_Semi-Supervised_Learning_with_Pseudo-Margins_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2308.09037", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Alias-Free Convnets: Fractional Shift Invariance via Polynomial Activations", - "base_url": null, - "title_page": null, - "repo": "hmichaeli/alias_free_convnets", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Michaeli_Alias-Free_Convnets_Fractional_Shift_Invariance_via_Polynomial_Activations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08085", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-8SeI0KDuAI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Detection of Out-of-Distribution Samples Using Binary Neuron Activation Patterns", - "base_url": null, - "title_page": null, - "repo": "safednn-group/nap-ood", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Olber_Detection_of_Out-of-Distribution_Samples_Using_Binary_Neuron_Activation_Patterns_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.14268", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UoptSWWXV9U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Mitigating Task Interference in Multi-Task Learning via Explicit Task Routing With Non-Learnable Primitives", - "base_url": null, - "title_page": null, - "repo": "zhichao-lu/etr-nlp-mtl", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ding_Mitigating_Task_Interference_in_Multi-Task_Learning_via_Explicit_Task_Routing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2308.02066", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Oue6vtprTPk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Superclass Learning With Representation Enhancement", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kang_Superclass_Learning_With_Representation_Enhancement_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "FH1WWEvKJI0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Perception and Semantic Aware Regularization for Sequential Confidence Calibration", - "base_url": null, - "title_page": null, - "repo": "husterpzh/PSSR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Peng_Perception_and_Semantic_Aware_Regularization_for_Sequential_Confidence_Calibration_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.19498", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "cic1NxV9G5Y", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "DART: Diversify-Aggregate-Repeat Training Improves Generalization of Neural Networks", - "base_url": null, - "title_page": null, - "repo": "val-iisc/DART", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jain_DART_Diversify-Aggregate-Repeat_Training_Improves_Generalization_of_Neural_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14685", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4QAZrLp7AWM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Improving Robustness of Vision Transformers by Reducing Sensitivity To Patch Corruptions", - "base_url": null, - "title_page": null, - "repo": "guoyongcs/RSPC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Guo_Improving_Robustness_of_Vision_Transformers_by_Reducing_Sensitivity_To_Patch_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "E2PN: Efficient SE(3)-Equivariant Point Network", - "base_url": null, - "title_page": null, - "repo": "minghanz/E2PN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_E2PN_Efficient_SE3-Equivariant_Point_Network_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "B4XDxd0h08I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Generalization Matters: Loss Minima Flattening via Parameter Hybridization for Efficient Online Knowledge Distillation", - "base_url": null, - "title_page": null, - "repo": "tianlizhang/OKDPH", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Generalization_Matters_Loss_Minima_Flattening_via_Parameter_Hybridization_for_Efficient_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14666", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LpUXn1ytYnA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Regularization of Polynomial Networks for Image Recognition", - "base_url": null, - "title_page": null, - "repo": "grigorisg9gr/regularized_polynomials", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chrysos_Regularization_of_Polynomial_Networks_for_Image_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13896", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "h7iBpEHGVNc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Hyperspherical Embedding for Point Cloud Completion", - "base_url": null, - "title_page": null, - "repo": "haomengz/HyperPC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Hyperspherical_Embedding_for_Point_Cloud_Completion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.05634", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lyoOYk_gPlQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "On the Effectiveness of Partial Variance Reduction in Federated Learning With Heterogeneous Data", - "base_url": null, - "title_page": null, - "repo": "lyn1874/fedpvr", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_On_the_Effectiveness_of_Partial_Variance_Reduction_in_Federated_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.02191", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "J6ZtL46Gr0w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Independent Component Alignment for Multi-Task Learning", - "base_url": null, - "title_page": null, - "repo": "SamsungLabs/MTL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Senushkin_Independent_Component_Alignment_for_Multi-Task_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.19000", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mDSPJsrLu1g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "MP-Former: Mask-Piloted Transformer for Image Segmentation", - "base_url": null, - "title_page": null, - "repo": "IDEA-Research/MP-Former", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_MP-Former_Mask-Piloted_Transformer_for_Image_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07336", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WXaGsgv0ngk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "SMPConv: Self-Moving Point Representations for Continuous Convolution", - "base_url": null, - "title_page": null, - "repo": "sangnekim/SMPConv", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_SMPConv_Self-Moving_Point_Representations_for_Continuous_Convolution_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02330", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tMiwzeD13uk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "MaskCon: Masked Contrastive Learning for Coarse-Labelled Dataset", - "base_url": null, - "title_page": null, - "repo": "MrChenFeng/MaskCon_CVPR2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_MaskCon_Masked_Contrastive_Learning_for_Coarse-Labelled_Dataset_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12756", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "V4is0vAYNOw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "FlexiViT: One Model for All Patch Sizes", - "base_url": null, - "title_page": null, - "repo": "bwconrad/flexivit", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Beyer_FlexiViT_One_Model_for_All_Patch_Sizes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08013", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jijeGJWh4u4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "GEN: Pushing the Limits of Softmax-Based Out-of-Distribution Detection", - "base_url": null, - "title_page": null, - "repo": "XixiLiu95/GEN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_GEN_Pushing_the_Limits_of_Softmax-Based_Out-of-Distribution_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2zEhSGNd_I4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Zero-Shot Noise2Noise: Efficient Image Denoising Without Any Data", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": "https://colab.research.google.com/drive/1i82nyizTdszyHkaHBuKPbWnTzao8HF9b", - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mansour_Zero-Shot_Noise2Noise_Efficient_Image_Denoising_Without_Any_Data_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11253", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "l6s68JAfknE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Castling-ViT: Compressing Self-Attention via Switching Towards Linear-Angular Attention at Vision Transformer Inference", - "base_url": null, - "title_page": null, - "repo": "GATECH-EIC/Castling-ViT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/You_Castling-ViT_Compressing_Self-Attention_via_Switching_Towards_Linear-Angular_Attention_at_Vision_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10526", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2x31-_xbi5U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "HNeRV: A Hybrid Neural Representation for Videos", - "base_url": null, - "title_page": null, - "repo": "haochen-rye/HNeRV", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_HNeRV_A_Hybrid_Neural_Representation_for_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02633", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "k2WNoWFCbHA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Re-Basin via Implicit Sinkhorn Differentiation", - "base_url": null, - "title_page": null, - "repo": "fagp/sinkhorn-rebasin", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pena_Re-Basin_via_Implicit_Sinkhorn_Differentiation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.12042", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RPSqoLx-ggk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Bayesian Posterior Approximation With Stochastic Ensembles", - "base_url": null, - "title_page": null, - "repo": "oleksandr-balabanov/stochastic-ensembles", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Balabanov_Bayesian_Posterior_Approximation_With_Stochastic_Ensembles_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08123", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "FedDM: Iterative Distribution Matching for Communication-Efficient Federated Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_FedDM_Iterative_Distribution_Matching_for_Communication-Efficient_Federated_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.09653", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WDNOxM6UILs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Enhancing Multiple Reliability Measures via Nuisance-Extended Information Bottleneck", - "base_url": null, - "title_page": null, - "repo": "jh-jeong/nuisance_ib", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jeong_Enhancing_Multiple_Reliability_Measures_via_Nuisance-Extended_Information_Bottleneck_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14096", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - }, - { - "title": "Federated Learning With Data-Agnostic Distribution Fusion", - "base_url": null, - "title_page": null, - "repo": "LiruichenSpace/FedFusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Duan_Federated_Learning_With_Data-Agnostic_Distribution_Fusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IW2BhW8POyg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Deep Learning Architectures and Techniques" - } -] \ No newline at end of file diff --git a/json_data/document-analysis-and-understanding.json b/json_data/document-analysis-and-understanding.json deleted file mode 100644 index e6cfe6c..0000000 --- a/json_data/document-analysis-and-understanding.json +++ /dev/null @@ -1,302 +0,0 @@ -[ - { - "title": "Towards Flexible Multi-Modal Document Models", - "base_url": null, - "title_page": null, - "repo": "CyberAgentAILab/flex-dm", - "web_page": null, - "github_page": "https://cyberagentailab.github.io/flex-dm/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Inoue_Towards_Flexible_Multi-Modal_Document_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.18248", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "byUtRi_Yrc8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "Improving Table Structure Recognition with Visual-Alignment Sequential Coordinate Modeling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Improving_Table_Structure_Recognition_With_Visual-Alignment_Sequential_Coordinate_Modeling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06949", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Onf5En9AI30", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "Unifying Layout Generation with a Decoupled Diffusion Model", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hui_Unifying_Layout_Generation_With_a_Decoupled_Diffusion_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05049", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zXGBvHt8v80", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "Conditional Text Image Generation with Diffusion Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_Conditional_Text_Image_Generation_With_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "G09Hf7on4oc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "Turning a CLIP Model into a Scene Text Detector", - "base_url": null, - "title_page": null, - "repo": "wenwenyu/TCM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_Turning_a_CLIP_Model_Into_a_Scene_Text_Detector_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14338", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-xy5MkHtADc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "Unifying Vision, Text, and Layout for Universal Document Processing", - "base_url": null, - "title_page": null, - "repo": "microsoft/i-Code", - "web_page": null, - "github_page": "https://github.com/microsoft/i-Code/tree/main/i-Code-Doc", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Unifying_Vision_Text_and_Layout_for_Universal_Document_Processing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.02623", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "d3J5opFgiDE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "Modeling Entities as Semantic Points for Visual Information Extraction in the Wild", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": "https://www.modelscope.cn/datasets/damo/SIBR/summary", - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Modeling_Entities_As_Semantic_Points_for_Visual_Information_Extraction_in_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13095", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vRlErNSMsQ0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "GeoLayoutLM: Geometric Pre-Training for Visual Information Extraction", - "base_url": null, - "title_page": null, - "repo": "AlibabaResearch/AdvancedLiterateMachinery", - "web_page": null, - "github_page": "https://github.com/AlibabaResearch/AdvancedLiterateMachinery/tree/main/DocumentUnderstanding/GeoLayoutLM", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_GeoLayoutLM_Geometric_Pre-Training_for_Visual_Information_Extraction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10759", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qsGkp29mdgo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "Handwritten Text Generation from Visual Archetypes", - "base_url": null, - "title_page": null, - "repo": "aimagelab/VATr", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pippi_Handwritten_Text_Generation_From_Visual_Archetypes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15269", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WjgJX3lG4qQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "Towards Robust Tampered Text Detection in Document Image: New Dataset and New Solution", - "base_url": null, - "title_page": null, - "repo": "qcf-568/DocTamper", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qu_Towards_Robust_Tampered_Text_Detection_in_Document_Image_New_Dataset_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Slf1OF4vGdo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "M6Doc: A Large-Scale Multi-Format, Multi-Type, Multi-Layout, Multi-Language, Multi-Annotation Category Dataset for Modern Document Layout Analysis", - "base_url": null, - "title_page": null, - "repo": "HCIILAB/M6Doc", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cheng_M6Doc_A_Large-Scale_Multi-Format_Multi-Type_Multi-Layout_Multi-Language_Multi-Annotation_Category_Dataset_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ieWACpWL8WM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - }, - { - "title": "Disentangling Writer and Character Styles for Handwriting Generation", - "base_url": null, - "title_page": null, - "repo": "dailenson/SDT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dai_Disentangling_Writer_and_Character_Styles_for_Handwriting_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14736", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mKbYLEwa4dI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Document Analysis and Understanding" - } -] \ No newline at end of file diff --git a/json_data/efficient-and-scalable-vision.json b/json_data/efficient-and-scalable-vision.json deleted file mode 100644 index 9817630..0000000 --- a/json_data/efficient-and-scalable-vision.json +++ /dev/null @@ -1,1202 +0,0 @@ -[ - { - "title": "DisWOT: Student Architecture Search for Distillation WithOut Training", - "base_url": null, - "title_page": null, - "repo": "lilujunai/DisWOT-CVPR2023", - "web_page": null, - "github_page": "https://lilujunai.github.io/DisWOT-CVPR2023/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dong_DisWOT_Student_Architecture_Search_for_Distillation_WithOut_Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15678", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Stitchable Neural Networks", - "base_url": null, - "title_page": null, - "repo": "ziplab/SN-Net", - "web_page": null, - "github_page": "https://snnet.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pan_Stitchable_Neural_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.06586", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SfpHVWWLREM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "NIRVANA: Neural Implicit Representations of Videos with Adaptive Networks and Autoregressive Patch-Wise Modeling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.cs.umd.edu/~shishira/Nirvana/nirvana.html", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Maiya_NIRVANA_Neural_Implicit_Representations_of_Videos_With_Adaptive_Networks_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.14593", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "cJOt3p2WLj0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "ResFormer: Scaling ViTs with Multi-Resolution Training", - "base_url": null, - "title_page": null, - "repo": "ruitian12/resformer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tian_ResFormer_Scaling_ViTs_With_Multi-Resolution_Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.00776", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tx5bSpeRcrE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "PD-Quant: Post-Training Quantization based on Prediction Difference Metric", - "base_url": null, - "title_page": null, - "repo": "hustvl/PD-Quant", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_PD-Quant_Post-Training_Quantization_Based_on_Prediction_Difference_Metric_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07048", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5OEmjFcqNPo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "DepGraph: Towards any Structural Pruning", - "base_url": null, - "title_page": null, - "repo": "VainF/Torch-Pruning", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fang_DepGraph_Towards_Any_Structural_Pruning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.12900", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Towards Professional Level Crowd Annotation of Expert Domain Data", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Towards_Professional_Level_Crowd_Annotation_of_Expert_Domain_Data_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jRQVuAytdwA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "GENIE: Show Me the Data for Quantization", - "base_url": null, - "title_page": null, - "repo": "SamsungLabs/Genie", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jeon_Genie_Show_Me_the_Data_for_Quantization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04780", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Boost Vision Transformer with GPU-Friendly Sparsity and Quantization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_Boost_Vision_Transformer_With_GPU-Friendly_Sparsity_and_Quantization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.10727", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gilS4ELhi9M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "MobileOne: An Improved One Millisecond Mobile Backbone", - "base_url": null, - "title_page": null, - "repo": "apple/ml-mobileone", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Vasu_MobileOne_An_Improved_One_Millisecond_Mobile_Backbone_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.04040", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SDOUtpEvTgg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "1% VS 100%: Parameter-Efficient Low Rank Adapter for Dense Predictions", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yin_1_VS_100_Parameter-Efficient_Low_Rank_Adapter_for_Dense_Predictions_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Discriminator-Cooperated Feature Map Distillation for GAN Compression", - "base_url": null, - "title_page": null, - "repo": "poopit/DCD-official", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Discriminator-Cooperated_Feature_Map_Distillation_for_GAN_Compression_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.14169", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "EfficientViT: Memory Efficient Vision Transformer with Cascaded Group Attention", - "base_url": null, - "title_page": null, - "repo": "microsoft/Cream", - "web_page": null, - "github_page": "https://github.com/microsoft/Cream/tree/main/EfficientViT", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_EfficientViT_Memory_Efficient_Vision_Transformer_With_Cascaded_Group_Attention_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.07027", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZYATsJboyhM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "itKD: Interchange Transfer-based Knowledge Distillation for 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "hyeon-jo/interchange-transfer-KD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cho_itKD_Interchange_Transfer-Based_Knowledge_Distillation_for_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.15531", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "a4oBLiJ62XI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Slimmable Dataset Condensation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Slimmable_Dataset_Condensation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zvcdG80p1-s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Dynamic Inference with Grounding based Vision and Language Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Uzkent_Dynamic_Inference_With_Grounding_Based_Vision_and_Language_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": "https://www.amazon.science/publications/dynamic-inference-with-grounding-based-vision-and-language-models", - "youtube_id": "3uoHUR25Ht4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "ScaleDet: A Scalable Multi-Dataset Object Detector", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_ScaleDet_A_Scalable_Multi-Dataset_Object_Detector_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.04849", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vy3DVdlSTaw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Learning to Zoom and Unzoom", - "base_url": null, - "title_page": null, - "repo": "tchittesh/lzu", - "web_page": null, - "github_page": "https://tchittesh.github.io/lzu/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Thavamani_Learning_To_Zoom_and_Unzoom_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15390", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wALSrBZiUgc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Generic-to-Specific Distillation of Masked Autoencoders", - "base_url": null, - "title_page": null, - "repo": "pengzhiliang/G2SD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Generic-to-Specific_Distillation_of_Masked_Autoencoders_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14771", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "k3-eJiuRxBE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Post-Training Quantization on Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "42Shawn/PTQ4DM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shang_Post-Training_Quantization_on_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15736", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EkCvrRcLzOc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Global Vision Transformer Pruning with Hessian-Aware Saliency", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Global_Vision_Transformer_Pruning_With_Hessian-Aware_Saliency_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2110.04869", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0D8O7yBw4h4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Network Expansion for Practical Training Acceleration", - "base_url": null, - "title_page": null, - "repo": "huawei-noah/Efficient-Computing", - "web_page": null, - "github_page": "https://github.com/huawei-noah/Efficient-Computing/tree/master/TrainingAcceleration/NetworkExpansion", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ding_Network_Expansion_for_Practical_Training_Acceleration_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Compacting Binary Neural Networks by Sparse Kernel Selection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://yikaiw.github.io/projects/CVPR23-Sparks/slides.pdf", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Compacting_Binary_Neural_Networks_by_Sparse_Kernel_Selection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14470", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wFfW5dUZo-Y", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "PointDistiller: Structured Knowledge Distillation Towards Efficient and Compact 3D Detection", - "base_url": null, - "title_page": null, - "repo": "RunpeiDong/PointDistiller", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_PointDistiller_Structured_Knowledge_Distillation_Towards_Efficient_and_Compact_3D_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.11098", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_zWyXXZwDVc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Practical Network Acceleration with Tiny Sets", - "base_url": null, - "title_page": null, - "repo": "DoctorKey/Practise", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Practical_Network_Acceleration_With_Tiny_Sets_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2202.07861", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZMjT9YZDhTw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Memory-Friendly Scalable Super-Resolution via Rewinding Lottery Ticket Hypothesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Memory-Friendly_Scalable_Super-Resolution_via_Rewinding_Lottery_Ticket_Hypothesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Fast Point Cloud Generation with Straight Flows", - "base_url": null, - "title_page": null, - "repo": "klightz/PSF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Fast_Point_Cloud_Generation_With_Straight_Flows_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.01747", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Rethinking Federated Learning with Domain Shift: A Prototype View", - "base_url": null, - "title_page": null, - "repo": "WenkeHuang/RethinkFL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Rethinking_Federated_Learning_With_Domain_Shift_A_Prototype_View_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UGitdEfrPk0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Solving Oscillation Problem in Post-Training Quantization through a Theoretical Perspective", - "base_url": null, - "title_page": null, - "repo": "bytedance/MRECG", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ma_Solving_Oscillation_Problem_in_Post-Training_Quantization_Through_a_Theoretical_Perspective_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11906", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EA7QSOY2_co", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "ScaleKD: Distilling Scale-Aware Knowledge in Small Object Detector", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_ScaleKD_Distilling_Scale-Aware_Knowledge_in_Small_Object_Detector_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Adaptive Channel Sparsity for Federated Learning under System Heterogeneity", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liao_Adaptive_Channel_Sparsity_for_Federated_Learning_Under_System_Heterogeneity_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GRUA0y_kzN0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "A-la-carte Prompt Tuning (APT): Combining Distinct Data via Composable Prompting", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bowman_A-La-Carte_Prompt_Tuning_APT_Combining_Distinct_Data_via_Composable_Prompting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.07994", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "FQ8s-0HDtTE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "NoisyQuant: Noisy Bias-Enhanced Post-Training Activation Quantization for Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "kriskrisliu/NoisyQuant", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_NoisyQuant_Noisy_Bias-Enhanced_Post-Training_Activation_Quantization_for_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16056", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-b2aBYOdsSU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "NIPQ: Noise Proxy-based Integrated Pseudo-Quantization", - "base_url": null, - "title_page": null, - "repo": "ECoLab-POSTECH/NIPQ", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shin_NIPQ_Noise_Proxy-Based_Integrated_Pseudo-Quantization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.00820", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "FlatFormer: Flattened Window Attention for Efficient Point Cloud Transformer", - "base_url": null, - "title_page": null, - "repo": "mit-han-lab/flatformer", - "web_page": "https://flatformer.mit.edu/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_FlatFormer_Flattened_Window_Attention_for_Efficient_Point_Cloud_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.08739", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "SparseViT: Revisiting Activation Sparsity for Efficient High-Resolution Vision Transformer", - "base_url": null, - "title_page": null, - "repo": "mit-han-lab/sparsevit", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_SparseViT_Revisiting_Activation_Sparsity_for_Efficient_High-Resolution_Vision_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17605", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Efficient On-Device Training via Gradient Filtering", - "base_url": null, - "title_page": null, - "repo": "SLDGroup/GradientFilter-CVPR23", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Efficient_On-Device_Training_via_Gradient_Filtering_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.00330", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UGcKdzeTAnk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Towards High-Quality and Efficient Video Super-Resolution via Spatial-Temporal Data Overfitting", - "base_url": null, - "title_page": null, - "repo": "coulsonlee/STDO-CVPR2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Towards_High-Quality_and_Efficient_Video_Super-Resolution_via_Spatial-Temporal_Data_Overfitting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08331", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tnuOxvrqogI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "You Need Multiple Exiting: Dynamic Early Exiting for Accelerating Unified Vision Language Model", - "base_url": null, - "title_page": null, - "repo": "ncsu-dk-lab/MuE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_You_Need_Multiple_Exiting_Dynamic_Early_Exiting_for_Accelerating_Unified_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11152", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2op5v3-0EA4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Adaptive Data-Free Quantization", - "base_url": null, - "title_page": null, - "repo": "hfutqian/AdaDFQ", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qian_Adaptive_Data-Free_Quantization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06869", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Train-Once-for-All Personalization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Train-Once-for-All_Personalization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Neural Rate Estimator and Unsupervised Learning for Efficient Distributed Image Analytics in Split-DNN Models", - "base_url": null, - "title_page": null, - "repo": "intellabs/spic", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ahuja_Neural_Rate_Estimator_and_Unsupervised_Learning_for_Efficient_Distributed_Image_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YWuJKhei0oo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Sparsifiner: Learning Sparse Instance-Dependent Attention for Efficient Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "lim142857/Sparsifiner", - "web_page": null, - "github_page": "https://lim142857.github.io/lim142857.github.io-sparsifiner/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_Sparsifiner_Learning_Sparse_Instance-Dependent_Attention_for_Efficient_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13755", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "pUISIydZFHU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "FFCV: Accelerating Training by Removing Data Bottlenecks", - "base_url": null, - "title_page": null, - "repo": "libffcv/ffcv", - "web_page": "https://ffcv.io/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Leclerc_FFCV_Accelerating_Training_by_Removing_Data_Bottlenecks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.12517", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Samples with Low Loss Curvature Improve Data Efficiency", - "base_url": null, - "title_page": null, - "repo": "isha-garg/SLo-Curves", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Garg_Samples_With_Low_Loss_Curvature_Improve_Data_Efficiency_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mGagNmTaRy8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Decentralized Learning with Multi-Headed Distillation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhmoginov_Decentralized_Learning_With_Multi-Headed_Distillation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15774", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Bit-Shrinking: Limiting Instantaneous Sharpness for Improving Post-Training Quantization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Bit-Shrinking_Limiting_Instantaneous_Sharpness_for_Improving_Post-Training_Quantization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - }, - { - "title": "Masked Autoencoders Enable Efficient Knowledge Distillers", - "base_url": null, - "title_page": null, - "repo": "UCSC-VLAA/DMAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bai_Masked_Autoencoders_Enable_Efficient_Knowledge_Distillers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.12256", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "63CMleVH9oY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Efficient and Scalable Vision" - } -] \ No newline at end of file diff --git a/json_data/embodied-vision-active-agents-simulation.json b/json_data/embodied-vision-active-agents-simulation.json deleted file mode 100644 index af13590..0000000 --- a/json_data/embodied-vision-active-agents-simulation.json +++ /dev/null @@ -1,352 +0,0 @@ -[ - { - "title": "Open-World Multi-Task Control through Goal-Aware Representation Learning and Adaptive Horizon Prediction", - "base_url": null, - "title_page": null, - "repo": "CraftJarvis/MC-Controller", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cai_Open-World_Multi-Task_Control_Through_Goal-Aware_Representation_Learning_and_Adaptive_Horizon_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.10034", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MRjBzRVTGAs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "Layout-based Causal Inference for Object Navigation", - "base_url": null, - "title_page": null, - "repo": "sx-zhang/Layout-based-sTDE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Layout-Based_Causal_Inference_for_Object_Navigation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LrWJnxjt1go", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "EC2: Emergent Communication for Embodied Control", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mu_EC2_Emergent_Communication_for_Embodied_Control_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.09448", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tiUvQnQtJh8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "GAPartNet: Cross-Category Domain-Generalizable Object Perception and Manipulation via Generalizable and Actionable Parts", - "base_url": null, - "title_page": null, - "repo": "PKU-EPIC/GAPartNet", - "web_page": null, - "github_page": "https://pku-epic.github.io/GAPartNet/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Geng_GAPartNet_Cross-Category_Domain-Generalizable_Object_Perception_and_Manipulation_via_Generalizable_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.05272", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "cgVFAydWpdk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "Phone2Proc: Bringing Robust Robots into Our Chaotic World", - "base_url": null, - "title_page": null, - "repo": "allenai/phone2proc", - "web_page": "https://allenai.org/project/phone2proc/home", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Deitke_Phone2Proc_Bringing_Robust_Robots_Into_Our_Chaotic_World_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04819", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "PIRLNav: Pretraining with Imitation and RL Finetuning for ObjectNav", - "base_url": null, - "title_page": null, - "repo": "Ram81/pirlnav", - "web_page": null, - "github_page": "https://ram81.github.io/projects/pirlnav", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ramrakhya_PIRLNav_Pretraining_With_Imitation_and_RL_Finetuning_for_ObjectNav_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.07302", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "63C9wpnFrCg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "CoWs on PASTURE: Baselines and Benchmarks for Language-Driven Zero-Shot Object Navigation", - "base_url": null, - "title_page": null, - "repo": "real-stanford/cow", - "web_page": "https://cow.cs.columbia.edu/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gadre_CoWs_on_Pasture_Baselines_and_Benchmarks_for_Language-Driven_Zero-Shot_Object_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2203.10421", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "3D-Aware Object Goal Navigation via Simultaneous Exploration and Identification", - "base_url": null, - "title_page": null, - "repo": "jzhzhang/3DAwareNav", - "web_page": null, - "github_page": "https://pku-epic.github.io/3D-Aware-ObjectNav/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_3D-Aware_Object_Goal_Navigation_via_Simultaneous_Exploration_and_Identification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.00338", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-50kIfOYTBM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "Modality-Invariant Visual Odometry for Embodied Vision", - "base_url": null, - "title_page": null, - "repo": "memmelma/VO-Transformer", - "web_page": null, - "github_page": "https://memmelma.github.io/vot/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Memmel_Modality-Invariant_Visual_Odometry_for_Embodied_Vision_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.00348", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kZCmdHhLkP4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "UniDexGrasp: Universal Robotic Dexterous Grasping via Learning Diverse Proposal Generation and Goal-Conditioned Policy", - "base_url": null, - "title_page": null, - "repo": "PKU-EPIC/UniDexGrasp", - "web_page": null, - "github_page": "https://pku-epic.github.io/UniDexGrasp/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_UniDexGrasp_Universal_Robotic_Dexterous_Grasping_via_Learning_Diverse_Proposal_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00938", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "HR2JqApZKBs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "EXCALIBUR: Encouraging and Evaluating Embodied Exploration", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_EXCALIBUR_Encouraging_and_Evaluating_Embodied_Exploration_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SboNjVuIUJA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "Leverage Interactive Affinity for Affordance Learning", - "base_url": null, - "title_page": null, - "repo": "lhc1224/PIAL-Net", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_Leverage_Interactive_Affinity_for_Affordance_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "LANA: A Language-Capable Navigator for Instruction Following and Generation", - "base_url": null, - "title_page": null, - "repo": "wxh1996/LANA-VLN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_LANA_A_Language-Capable_Navigator_for_Instruction_Following_and_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08409", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "BurKOFn-78g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - }, - { - "title": "Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-per-Second", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/galactic", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Berges_Galactic_Scaling_End-to-End_Reinforcement_Learning_for_Rearrangement_at_100k_Steps-per-Second_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.07552", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Embodied Vision: Active Agents, Simulation" - } -] \ No newline at end of file diff --git a/json_data/explainable-ai-for-cv.json b/json_data/explainable-ai-for-cv.json deleted file mode 100644 index 0a7a5ab..0000000 --- a/json_data/explainable-ai-for-cv.json +++ /dev/null @@ -1,602 +0,0 @@ -[ - { - "title": "Are Data-Driven Explanations Robust Against Out-of-Distribution Data?", - "base_url": null, - "title_page": null, - "repo": "tangli-udel/DRE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Are_Data-Driven_Explanations_Robust_Against_Out-of-Distribution_Data_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16390", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "logVgiC4x54", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior", - "base_url": null, - "title_page": null, - "repo": "xl-tang3/UAUDeblur", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Uncertainty-Aware_Unsupervised_Image_Deblurring_With_Deep_Residual_Prior_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.05361", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9ZfN5Jt7vVA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Teaching Matters: Investigating the Role of Supervision in Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "mwalmer-umd/vit_analysis", - "web_page": "http://www.cs.umd.edu/~sakshams/vit_analysis/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Walmer_Teaching_Matters_Investigating_the_Role_of_Supervision_in_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03862", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Adversarial Counterfactual Visual Explanations", - "base_url": null, - "title_page": null, - "repo": "guillaumejs2403/ACE", - "web_page": null, - "github_page": "https://guillaumejs2403.github.io/projects/ace.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jeanneret_Adversarial_Counterfactual_Visual_Explanations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09962", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ykTUSSTZOME", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "SketchXAI: A First Look at Explainability for Human Sketches", - "base_url": null, - "title_page": null, - "repo": "WinKawaks/SketchXAI", - "web_page": null, - "github_page": "https://sketchxai.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qu_SketchXAI_A_First_Look_at_Explainability_for_Human_Sketches_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11744", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RcY3NJlTGyE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Doubly Right Object Recognition: A why Prompt for Visual Rationales", - "base_url": null, - "title_page": null, - "repo": "cvlab-columbia/DoubleRight", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mao_Doubly_Right_Object_Recognition_A_Why_Prompt_for_Visual_Rationales_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06202", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kp47I79-o38", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Overlooked Factors in Concept-based Explanations: Dataset Choice, Concept Learnability, and Human Capability", - "base_url": null, - "title_page": null, - "repo": "princetonvisualai/OverlookedFactors", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ramaswamy_Overlooked_Factors_in_Concept-Based_Explanations_Dataset_Choice_Concept_Learnability_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.09615", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LnvyAmNW918", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Initialization Noise in Image Gradients and Saliency Maps", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.visualcomputing.informatik.uni-mainz.de/initialization-noise-in-image-gradients-and-saliency-maps/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Woerl_Initialization_Noise_in_Image_Gradients_and_Saliency_Maps_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4qshf2hZiis", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Learning Bottleneck Concepts in Image Classification", - "base_url": null, - "title_page": null, - "repo": "wbw520/BotCL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Learning_Bottleneck_Concepts_in_Image_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10131", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "W8Lsas0FJ6w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Zero-Shot Model Diagnosis", - "base_url": null, - "title_page": null, - "repo": "humansensinglab/ZOOM", - "web_page": null, - "github_page": "https://zero-shot-model-diagnosis.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_Zero-Shot_Model_Diagnosis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15441", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mmiR1UxKbPg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "OCTET: Object-Aware Counterfactual Explanations", - "base_url": null, - "title_page": null, - "repo": "valeoai/OCTET", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zemni_OCTET_Object-Aware_Counterfactual_Explanations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12380", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "X-Pruner: eXplainable Pruning for Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "vickyyu90/XPruner", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_X-Pruner_eXplainable_Pruning_for_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.04935", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IWzC3tBL-Fo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fel_Dont_Lie_to_Me_Robust_and_Efficient_Explainability_With_Verified_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2202.07728", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "CRAFT: Concept Recursive Activation FacTorization for Explainability", - "base_url": null, - "title_page": null, - "repo": "deel-ai/Craft", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fel_CRAFT_Concept_Recursive_Activation_FacTorization_for_Explainability_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10154", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "z12IffeD7yw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Grounding_Counterfactual_Explanation_of_Image_Classifiers_to_Textual_Concept_Space_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": "https://www.amazon.science/publications/grounding-counterfactual-explanation-of-image-classifier-to-textual-concept-space", - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Explaining Image Classifiers with Multiscale Directional Image Representation", - "base_url": null, - "title_page": null, - "repo": "skmda37/ShearletX", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kolek_Explaining_Image_Classifiers_With_Multiscale_Directional_Image_Representation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12857", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "524MaHHewoo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients", - "base_url": null, - "title_page": null, - "repo": "yangruo1226/idgi", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_IDGI_A_Framework_To_Eliminate_Explanation_Noise_From_Integrated_Gradients_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14242", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3L7wbMdOQiY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification", - "base_url": null, - "title_page": null, - "repo": "YueYANG1996/LaBo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Language_in_a_Bottle_Language_Model_Guided_Concept_Bottlenecks_for_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11158", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nOPy4BBm4Tw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Gradient-Based_Uncertainty_Attribution_for_Explainable_Bayesian_Deep_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04824", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lvJ_grAfwFw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "PIP-Net: Patch-based Intuitive Prototypes for Interpretable Image Classification", - "base_url": null, - "title_page": null, - "repo": "M-Nauta/PIPNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nauta_PIP-Net_Patch-Based_Intuitive_Prototypes_for_Interpretable_Image_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GfQQFQ62SLU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Shortcomings of Top-Down Randomization-based Sanity Checks for Evaluations of Deep Neural Network Explanations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Binder_Shortcomings_of_Top-Down_Randomization-Based_Sanity_Checks_for_Evaluations_of_Deep_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12486", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JKBQKBlSEJM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Spatial-Temporal Concept based Explanation of 3D ConvNets", - "base_url": null, - "title_page": null, - "repo": "yingji425/STCE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ji_Spatial-Temporal_Concept_Based_Explanation_of_3D_ConvNets_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.05275", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-53laIT9ytM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "A Practical Upper Bound for the Worst-Case Attribution Deviations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_A_Practical_Upper_Bound_for_the_Worst-Case_Attribution_Deviations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00340", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - }, - { - "title": "Adversarial Normalization: I Can Visualize Everything (ICE)", - "base_url": null, - "title_page": null, - "repo": "Hanyang-HCC-Lab/ICE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Choi_Adversarial_Normalization_I_Can_Visualize_Everything_ICE_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZeZYWmrHqIw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable AI for CV" - } -] \ No newline at end of file diff --git a/json_data/explainable-computer-vision.json b/json_data/explainable-computer-vision.json deleted file mode 100644 index 2195862..0000000 --- a/json_data/explainable-computer-vision.json +++ /dev/null @@ -1,602 +0,0 @@ -[ - { - "title": "Are Data-Driven Explanations Robust Against Out-of-Distribution Data?", - "base_url": null, - "title_page": null, - "repo": "tangli-udel/DRE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Are_Data-Driven_Explanations_Robust_Against_Out-of-Distribution_Data_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16390", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "logVgiC4x54", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Uncertainty-Aware Unsupervised Image Deblurring with Deep Residual Prior", - "base_url": null, - "title_page": null, - "repo": "xl-tang3/UAUDeblur", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Uncertainty-Aware_Unsupervised_Image_Deblurring_With_Deep_Residual_Prior_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.05361", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9ZfN5Jt7vVA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Teaching Matters: Investigating the Role of Supervision in Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "mwalmer-umd/vit_analysis", - "web_page": "http://www.cs.umd.edu/~sakshams/vit_analysis/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Walmer_Teaching_Matters_Investigating_the_Role_of_Supervision_in_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03862", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Adversarial Counterfactual Visual Explanations", - "base_url": null, - "title_page": null, - "repo": "guillaumejs2403/ACE", - "web_page": null, - "github_page": "https://guillaumejs2403.github.io/projects/ace.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jeanneret_Adversarial_Counterfactual_Visual_Explanations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09962", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ykTUSSTZOME", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "SketchXAI: A First Look at Explainability for Human Sketches", - "base_url": null, - "title_page": null, - "repo": "WinKawaks/SketchXAI", - "web_page": null, - "github_page": "https://sketchxai.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qu_SketchXAI_A_First_Look_at_Explainability_for_Human_Sketches_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11744", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RcY3NJlTGyE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Doubly Right Object Recognition: A why Prompt for Visual Rationales", - "base_url": null, - "title_page": null, - "repo": "cvlab-columbia/DoubleRight", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mao_Doubly_Right_Object_Recognition_A_Why_Prompt_for_Visual_Rationales_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06202", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kp47I79-o38", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Overlooked Factors in Concept-based Explanations: Dataset Choice, Concept Learnability, and Human Capability", - "base_url": null, - "title_page": null, - "repo": "princetonvisualai/OverlookedFactors", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ramaswamy_Overlooked_Factors_in_Concept-Based_Explanations_Dataset_Choice_Concept_Learnability_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.09615", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LnvyAmNW918", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Initialization Noise in Image Gradients and Saliency Maps", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.visualcomputing.informatik.uni-mainz.de/initialization-noise-in-image-gradients-and-saliency-maps/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Woerl_Initialization_Noise_in_Image_Gradients_and_Saliency_Maps_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4qshf2hZiis", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Learning Bottleneck Concepts in Image Classification", - "base_url": null, - "title_page": null, - "repo": "wbw520/BotCL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Learning_Bottleneck_Concepts_in_Image_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10131", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "W8Lsas0FJ6w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Zero-Shot Model Diagnosis", - "base_url": null, - "title_page": null, - "repo": "humansensinglab/ZOOM", - "web_page": null, - "github_page": "https://zero-shot-model-diagnosis.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_Zero-Shot_Model_Diagnosis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15441", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mmiR1UxKbPg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "OCTET: Object-Aware Counterfactual Explanations", - "base_url": null, - "title_page": null, - "repo": "valeoai/OCTET", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zemni_OCTET_Object-Aware_Counterfactual_Explanations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12380", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "X-Pruner: eXplainable Pruning for Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "vickyyu90/XPruner", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_X-Pruner_eXplainable_Pruning_for_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.04935", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IWzC3tBL-Fo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Don't Lie to Me! Robust and Efficient Explainability with Verified Perturbation Analysis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fel_Dont_Lie_to_Me_Robust_and_Efficient_Explainability_With_Verified_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2202.07728", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "CRAFT: Concept Recursive Activation FacTorization for Explainability", - "base_url": null, - "title_page": null, - "repo": "deel-ai/Craft", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fel_CRAFT_Concept_Recursive_Activation_FacTorization_for_Explainability_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10154", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "z12IffeD7yw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Grounding Counterfactual Explanation of Image Classifiers to Textual Concept Space", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Grounding_Counterfactual_Explanation_of_Image_Classifiers_to_Textual_Concept_Space_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": "https://www.amazon.science/publications/grounding-counterfactual-explanation-of-image-classifier-to-textual-concept-space", - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Explaining Image Classifiers with Multiscale Directional Image Representation", - "base_url": null, - "title_page": null, - "repo": "skmda37/ShearletX", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kolek_Explaining_Image_Classifiers_With_Multiscale_Directional_Image_Representation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12857", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "524MaHHewoo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "IDGI: A Framework to Eliminate Explanation Noise from Integrated Gradients", - "base_url": null, - "title_page": null, - "repo": "yangruo1226/idgi", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_IDGI_A_Framework_To_Eliminate_Explanation_Noise_From_Integrated_Gradients_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14242", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3L7wbMdOQiY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Language in a Bottle: Language Model Guided Concept Bottlenecks for Interpretable Image Classification", - "base_url": null, - "title_page": null, - "repo": "YueYANG1996/LaBo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Language_in_a_Bottle_Language_Model_Guided_Concept_Bottlenecks_for_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11158", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nOPy4BBm4Tw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Gradient-based Uncertainty Attribution for Explainable Bayesian Deep Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Gradient-Based_Uncertainty_Attribution_for_Explainable_Bayesian_Deep_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04824", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lvJ_grAfwFw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "PIP-Net: Patch-based Intuitive Prototypes for Interpretable Image Classification", - "base_url": null, - "title_page": null, - "repo": "M-Nauta/PIPNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nauta_PIP-Net_Patch-Based_Intuitive_Prototypes_for_Interpretable_Image_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GfQQFQ62SLU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Shortcomings of Top-Down Randomization-based Sanity Checks for Evaluations of Deep Neural Network Explanations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Binder_Shortcomings_of_Top-Down_Randomization-Based_Sanity_Checks_for_Evaluations_of_Deep_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12486", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JKBQKBlSEJM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Spatial-Temporal Concept based Explanation of 3D ConvNets", - "base_url": null, - "title_page": null, - "repo": "yingji425/STCE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ji_Spatial-Temporal_Concept_Based_Explanation_of_3D_ConvNets_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.05275", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-53laIT9ytM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "A Practical Upper Bound for the Worst-Case Attribution Deviations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_A_Practical_Upper_Bound_for_the_Worst-Case_Attribution_Deviations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00340", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - }, - { - "title": "Adversarial Normalization: I Can Visualize Everything (ICE)", - "base_url": null, - "title_page": null, - "repo": "Hanyang-HCC-Lab/ICE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Choi_Adversarial_Normalization_I_Can_Visualize_Everything_ICE_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZeZYWmrHqIw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Explainable Computer Vision" - } -] \ No newline at end of file diff --git a/json_data/image-and-video-synthesis-and-generation.json b/json_data/image-and-video-synthesis-and-generation.json deleted file mode 100644 index 0fc30fd..0000000 --- a/json_data/image-and-video-synthesis-and-generation.json +++ /dev/null @@ -1,4627 +0,0 @@ -[ - { - "title": "Towards Universal Fake Image Detectors That Generalize Across Generative Models", - "base_url": null, - "title_page": null, - "repo": "Yuheng-Li/UniversalFakeDetect", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ojha_Towards_Universal_Fake_Image_Detectors_That_Generalize_Across_Generative_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.10174", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Implicit Diffusion Models for Continuous Super-Resolution", - "base_url": null, - "title_page": null, - "repo": "Ree1s/IDM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_Implicit_Diffusion_Models_for_Continuous_Super-Resolution_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16491", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "High-Fidelity Guided Image Synthesis With Latent Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "1jsingh/GradOP-Guided-Image-Synthesis", - "web_page": null, - "github_page": "https://1jsingh.github.io/gradop", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Singh_High-Fidelity_Guided_Image_Synthesis_With_Latent_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.17084", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Yk83RPCOa2o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "DBARF: Deep Bundle-Adjusting Generalizable Neural Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "AIBluefisher/dbarf", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_DBARF_Deep_Bundle-Adjusting_Generalizable_Neural_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14478", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wFPO403wtAg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Deep Arbitrary-Scale Image Super-Resolution via Scale-Equivariance Pursuit", - "base_url": null, - "title_page": null, - "repo": "neuralchen/EQSR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Deep_Arbitrary-Scale_Image_Super-Resolution_via_Scale-Equivariance_Pursuit_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Pq9eI5kxqUE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Balanced Spherical Grid for Egocentric View Synthesis", - "base_url": null, - "title_page": null, - "repo": "changwoonchoi/EgoNeRF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Choi_Balanced_Spherical_Grid_for_Egocentric_View_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12408", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "D-lsBhVP8zw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "SDFusion: Multimodal 3D Shape Completion, Reconstruction, and Generation", - "base_url": null, - "title_page": null, - "repo": "yccyenchicheng/SDFusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cheng_SDFusion_Multimodal_3D_Shape_Completion_Reconstruction_and_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04493", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6EvHJRlUMFQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "DreamBooth: Fine Tuning Text-to-Image Diffusion Models for Subject-Driven Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://dreambooth.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ruiz_DreamBooth_Fine_Tuning_Text-to-Image_Diffusion_Models_for_Subject-Driven_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.12242", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "82x4XTSFwBQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Self-Guided Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "dongzhuoyao/self-guided-diffusion-models", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Self-Guided_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.06462", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zwkn640t-u8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Multi-Concept Customization of Text-to-Image Diffusion", - "base_url": null, - "title_page": null, - "repo": "adobe-research/custom-diffusion", - "web_page": null, - "github_page": "https://www.cs.cmu.edu/~custom-diffusion/dataset.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kumari_Multi-Concept_Customization_of_Text-to-Image_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04488", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WWNA_IPLO84", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "3D-Aware Conditional Image Synthesis", - "base_url": null, - "title_page": null, - "repo": "dunbar12138/pix2pix3D", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Deng_3D-Aware_Conditional_Image_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.08509", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dDRoI1gjbzk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "QuantArt: Quantizing Image Style Transfer Towards High Visual Fidelity", - "base_url": null, - "title_page": null, - "repo": "siyuhuang/QuantArt", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_QuantArt_Quantizing_Image_Style_Transfer_Towards_High_Visual_Fidelity_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.10431", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WWNA_IPLO84", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "SceneComposer: Any-Level Semantic Image Synthesis", - "base_url": null, - "title_page": null, - "repo": "zengxianyu/scenec", - "web_page": null, - "github_page": "https://zengyu.me/scenec/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zeng_SceneComposer_Any-Level_Semantic_Image_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11742", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ky0LWZ_USRA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "DiffCollage: Parallel Generation of Large Content With Diffusion Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://research.nvidia.com/labs/dir/diffcollage/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_DiffCollage_Parallel_Generation_of_Large_Content_With_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17076", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Putting People in Their Place: Affordance-Aware Human Insertion Into Scenes", - "base_url": null, - "title_page": null, - "repo": "adobe-research/affordance-insertion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kulal_Putting_People_in_Their_Place_Affordance-Aware_Human_Insertion_Into_Scenes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.14406", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Hybrid Neural Rendering for Large-Scale Scenes With Motion Blur", - "base_url": null, - "title_page": null, - "repo": "CVMI-Lab/HybridNeuralRendering", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dai_Hybrid_Neural_Rendering_for_Large-Scale_Scenes_With_Motion_Blur_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.12652", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hAhFfKRqDgE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Binary Latent Diffusion", - "base_url": null, - "title_page": null, - "repo": "ZeWang95/BinaryLatentDiffusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Binary_Latent_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04820", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "channel/UCzkUNNsV1TYuf6U_wGnMlnw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "StyleRes: Transforming the Residuals for Real Image Editing With StyleGAN", - "base_url": null, - "title_page": null, - "repo": "hamzapehlivan/StyleRes", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pehlivan_StyleRes_Transforming_the_Residuals_for_Real_Image_Editing_With_StyleGAN_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.14359", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "S9ZswKv8enw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "KD-DLGAN: Data Limited Image Generation via Knowledge Distillation", - "base_url": null, - "title_page": null, - "repo": "cuikaiwen18/KD_DLGAN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cui_KD-DLGAN_Data_Limited_Image_Generation_via_Knowledge_Distillation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17158", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "SeaThru-NeRF: Neural Radiance Fields in Scattering Media", - "base_url": null, - "title_page": null, - "repo": "deborahLevy130/seathru_NeRF", - "web_page": null, - "github_page": "https://sea-thru-nerf.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Levy_SeaThru-NeRF_Neural_Radiance_Fields_in_Scattering_Media_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.07743", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dXKCJS4cscg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "PointAvatar: Deformable Point-Based Head Avatars From Videos", - "base_url": null, - "title_page": null, - "repo": "zhengyuf/PointAvatar", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zheng_PointAvatar_Deformable_Point-Based_Head_Avatars_From_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08377", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wll_XtgpU7U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "3DAvatarGAN: Bridging Domains for Personalized Editable Avatars", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://rameenabdal.github.io/3DAvatarGAN/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Abdal_3DAvatarGAN_Bridging_Domains_for_Personalized_Editable_Avatars_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02700", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Neural Preset for Color Style Transfer", - "base_url": null, - "title_page": null, - "repo": "ZHKKKe/NeuralPreset", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ke_Neural_Preset_for_Color_Style_Transfer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13511", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "x6fLAvTPesk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Zero-Shot Generative Model Adaptation via Image-Specific Prompt Learning", - "base_url": null, - "title_page": null, - "repo": "Picsart-AI-Research/IPL-Zero-Shot-Generative-Model-Adaptation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Guo_Zero-Shot_Generative_Model_Adaptation_via_Image-Specific_Prompt_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03119", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vw9-C3Sz5nM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "DyNCA: Real-Time Dynamic Texture Synthesis Using Neural Cellular Automata", - "base_url": null, - "title_page": null, - "repo": "IVRL/DyNCA", - "web_page": null, - "github_page": "https://dynca.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pajouheshgar_DyNCA_Real-Time_Dynamic_Texture_Synthesis_Using_Neural_Cellular_Automata_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11417", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ELZC2mX5Z9U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Exploring Incompatible Knowledge Transfer in Few-Shot Image Generation", - "base_url": null, - "title_page": null, - "repo": "yunqing-me/RICK", - "web_page": null, - "github_page": "https://yunqing-me.github.io/RICK/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Exploring_Incompatible_Knowledge_Transfer_in_Few-Shot_Image_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.07574", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "s14bA8filtw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "HouseDiffusion: Vector Floorplan Generation via a Diffusion Model With Discrete and Continuous Denoising", - "base_url": null, - "title_page": null, - "repo": "aminshabani/house_diffusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shabani_HouseDiffusion_Vector_Floorplan_Generation_via_a_Diffusion_Model_With_Discrete_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13287", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ku6_gr94n5Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Towards Accurate Image Coding: Improved Autoregressive Image Generation With Dynamic Vector Quantization", - "base_url": null, - "title_page": null, - "repo": "CrossmodalGroup/DynamicVectorQuantization", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Towards_Accurate_Image_Coding_Improved_Autoregressive_Image_Generation_With_Dynamic_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.11718", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ir60YW9JCjU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "RiDDLE: Reversible and Diversified De-Identification With Latent Encryptor", - "base_url": null, - "title_page": null, - "repo": "ldz666666/RiDDLE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_RiDDLE_Reversible_and_Diversified_De-Identification_With_Latent_Encryptor_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05171", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gqs9Q6ReEn0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "LayoutDiffusion: Controllable Diffusion Model for Layout-to-Image Generation", - "base_url": null, - "title_page": null, - "repo": "ZGCTroy/LayoutDiffusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zheng_LayoutDiffusion_Controllable_Diffusion_Model_for_Layout-to-Image_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17189", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bJOpJnvhw3s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "LipFormer: High-Fidelity and Generalizable Talking Face Generation With a Pre-Learned Facial Codebook", - "base_url": null, - "title_page": null, - "repo": "DaddyJin/awesome-faceReenactment", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_LipFormer_High-Fidelity_and_Generalizable_Talking_Face_Generation_With_a_Pre-Learned_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Not All Image Regions Matter: Masked Vector Quantization for Autoregressive Image Generation", - "base_url": null, - "title_page": null, - "repo": "CrossmodalGroup/MaskedVectorQuantization", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Not_All_Image_Regions_Matter_Masked_Vector_Quantization_for_Autoregressive_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.13607", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "o2eyRscEejw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "GALIP: Generative Adversarial CLIPs for Text-to-Image Synthesis", - "base_url": null, - "title_page": null, - "repo": "tobran/GALIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tao_GALIP_Generative_Adversarial_CLIPs_for_Text-to-Image_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.12959", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lwhTDY4du_g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "High-Fidelity Generalized Emotional Talking Face Generation With Multi-Modal Emotion Space Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_High-Fidelity_Generalized_Emotional_Talking_Face_Generation_With_Multi-Modal_Emotion_Space_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.02572", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "eQG6ql83T0w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Consistent View Synthesis With Pose-Guided Diffusion Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://poseguided-diffusion.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tseng_Consistent_View_Synthesis_With_Pose-Guided_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17598", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "eV1jwq14lE0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "StyleSync: High-Fidelity Generalized and Personalized Lip Sync in Style-Based Generator", - "base_url": null, - "title_page": null, - "repo": "guanjz20/StyleSync", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Guan_StyleSync_High-Fidelity_Generalized_and_Personalized_Lip_Sync_in_Style-Based_Generator_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.05445", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yAPDl2dVonY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Imagic: Text-Based Real Image Editing With Diffusion Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://poseguided-diffusion.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kawar_Imagic_Text-Based_Real_Image_Editing_With_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.09276", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lOZvBGz47wQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Large-Capacity and Flexible Video Steganography via Invertible Neural Network", - "base_url": null, - "title_page": null, - "repo": "MC-E/LF-VSN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mou_Large-Capacity_and_Flexible_Video_Steganography_via_Invertible_Neural_Network_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.12300", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Quantitative Manipulation of Custom Attributes on 3D-Aware Image Synthesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Do_Quantitative_Manipulation_of_Custom_Attributes_on_3D-Aware_Image_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Learning Detailed Radiance Manifolds for High-Fidelity and 3D-Consistent Portrait Synthesis From Monocular Image", - "base_url": null, - "title_page": null, - "repo": "YuDeng/GRAMInverter", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Deng_Learning_Detailed_Radiance_Manifolds_for_High-Fidelity_and_3D-Consistent_Portrait_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13901", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nclBOg_CiJo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "CF-Font: Content Fusion for Few-Shot Font Generation", - "base_url": null, - "title_page": null, - "repo": "wangchi95/CF-Font", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_CF-Font_Content_Fusion_for_Few-Shot_Font_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14017", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "biwFd0K3X9o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "One-Shot High-Fidelity Talking-Head Synthesis With Deformable Neural Radiance Field", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.waytron.net/hidenerf/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_One-Shot_High-Fidelity_Talking-Head_Synthesis_With_Deformable_Neural_Radiance_Field_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05097", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "opLdLY8_VYQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Unsupervised Domain Adaption With Pixel-Level Discriminator for Image-Aware Layout Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Unsupervised_Domain_Adaption_With_Pixel-Level_Discriminator_for_Image-Aware_Layout_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14377", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DBHFzw02T1I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Diffusion Probabilistic Model Made Slim", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Diffusion_Probabilistic_Model_Made_Slim_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.17106", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "82N6FsRUfr4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Collaborative Diffusion for Multi-Modal Face Generation and Editing", - "base_url": null, - "title_page": null, - "repo": "ziqihuangg/Collaborative-Diffusion", - "web_page": null, - "github_page": "https://ziqihuangg.github.io/projects/collaborative-diffusion.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Collaborative_Diffusion_for_Multi-Modal_Face_Generation_and_Editing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10530", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "inLK4c8sNhc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "High-Fidelity Facial Avatar Reconstruction From Monocular Video With Generative Priors", - "base_url": null, - "title_page": null, - "repo": "bbaaii/HFA-GP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bai_High-Fidelity_Facial_Avatar_Reconstruction_From_Monocular_Video_With_Generative_Priors_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15064", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZWdF8ASl0BQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Network-Free, Unsupervised Semantic Segmentation With Synthetic Images", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_Network-Free_Unsupervised_Semantic_Segmentation_With_Synthetic_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": "https://www.amazon.science/publications/network-free-unsupervised-semantic-segmentation-with-synthetic-images", - "youtube_id": "mfFZdvaF1Tw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Visual Prompt Tuning for Generative Transfer Learning", - "base_url": null, - "title_page": null, - "repo": "google-research/generative_transfer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sohn_Visual_Prompt_Tuning_for_Generative_Transfer_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.00990", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kOza8-xop_g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Specialist Diffusion: Plug-and-Play Sample-Efficient Fine-Tuning of Text-to-Image Diffusion Models To Learn Any Unseen Style", - "base_url": null, - "title_page": null, - "repo": "Picsart-AI-Research/Specialist-Diffusion", - "web_page": null, - "github_page": "https://specialist-diffusion.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_Specialist_Diffusion_Plug-and-Play_Sample-Efficient_Fine-Tuning_of_Text-to-Image_Diffusion_Models_To_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5-hkImpVsNI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Catch Missing Details: Image Reconstruction With Frequency Augmented Variational Autoencoder", - "base_url": null, - "title_page": null, - "repo": "JiauZhang/FA-VAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Catch_Missing_Details_Image_Reconstruction_With_Frequency_Augmented_Variational_Autoencoder_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.02541", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wJ9U7tAnQEo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Towards Bridging the Performance Gaps of Joint Energy-Based Models", - "base_url": null, - "title_page": null, - "repo": "sndnyang/sadajem", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Towards_Bridging_the_Performance_Gaps_of_Joint_Energy-Based_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.07959", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "GLeaD: Improving GANs With a Generator-Leading Task", - "base_url": null, - "title_page": null, - "repo": "EzioBy/glead", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bai_GLeaD_Improving_GANs_With_a_Generator-Leading_Task_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03752", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bP8Iq_qLuU0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Structural Multiplane Image: Bridging Neural View Synthesis and 3D Reconstruction", - "base_url": null, - "title_page": null, - "repo": "mf-zhang/Structural-MPI", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Structural_Multiplane_Image_Bridging_Neural_View_Synthesis_and_3D_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05937", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8Bbl8oZKAOs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "SPARF: Neural Radiance Fields From Sparse and Noisy Poses", - "base_url": null, - "title_page": null, - "repo": "google-research/sparf", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Truong_SPARF_Neural_Radiance_Fields_From_Sparse_and_Noisy_Poses_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11738", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_s3_p2Brd_8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "DeltaEdit: Exploring Text-Free Training for Text-Driven Image Manipulation", - "base_url": null, - "title_page": null, - "repo": "Yueming6568/DeltaEdit", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lyu_DeltaEdit_Exploring_Text-Free_Training_for_Text-Driven_Image_Manipulation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06285", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8cdZSbhDMIA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Inferring and Leveraging Parts From Object Shape for Improving Semantic Image Synthesis", - "base_url": null, - "title_page": null, - "repo": "csyxwei/iPOSE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_Inferring_and_Leveraging_Parts_From_Object_Shape_for_Improving_Semantic_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.19547", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yVUmjQU9-v4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "VideoFusion: Decomposed Diffusion Models for High-Quality Video Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_VideoFusion_Decomposed_Diffusion_Models_for_High-Quality_Video_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08320", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hxA0DTZScg0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "MaskSketch: Unpaired Structure-Guided Masked Image Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bashkirova_MaskSketch_Unpaired_Structure-Guided_Masked_Image_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.05496", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2tBzEGASeo0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Affordance Diffusion: Synthesizing Hand-Object Interactions", - "base_url": null, - "title_page": null, - "repo": "NVlabs/affordance_diffusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ye_Affordance_Diffusion_Synthesizing_Hand-Object_Interactions_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12538", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "omhEoLzsopo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Interactive Cartoonization With Controllable Perceptual Factors", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ahn_Interactive_Cartoonization_With_Controllable_Perceptual_Factors_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09555", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "z8B2RiB4DyM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "MetaPortrait: Identity-Preserving Talking Head Generation With Fast Personalized Adaptation", - "base_url": null, - "title_page": null, - "repo": "Meta-Portrait/MetaPortrait", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_MetaPortrait_Identity-Preserving_Talking_Head_Generation_With_Fast_Personalized_Adaptation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08062", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DDEnjbCNNY4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Paint by Example: Exemplar-Based Image Editing With Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "Fantasy-Studio/Paint-by-Example", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Paint_by_Example_Exemplar-Based_Image_Editing_With_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13227", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "GLIGEN: Open-Set Grounded Text-to-Image Generation", - "base_url": null, - "title_page": null, - "repo": "gligen/GLIGEN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_GLIGEN_Open-Set_Grounded_Text-to-Image_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.07093", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-MCkU7IAGKs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "L-CoIns: Language-Based Colorization With Instance Awareness", - "base_url": null, - "title_page": null, - "repo": "changzheng123/L-CoIns", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chang_L-CoIns_Language-Based_Colorization_With_Instance_Awareness_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "DiffTalk: Crafting Diffusion Models for Generalized Audio-Driven Portraits Animation", - "base_url": null, - "title_page": null, - "repo": "sstzal/DiffTalk", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shen_DiffTalk_Crafting_Diffusion_Models_for_Generalized_Audio-Driven_Portraits_Animation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.03786", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tup5kbsOJXc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Evading DeepFake Detectors via Adversarial Statistical Consistency", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hou_Evading_DeepFake_Detectors_via_Adversarial_Statistical_Consistency_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11670", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "GlassesGAN: Eyewear Personalization Using Synthetic Appearance Discovery and Targeted Subspace Modeling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Plesh_GlassesGAN_Eyewear_Personalization_Using_Synthetic_Appearance_Discovery_and_Targeted_Subspace_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.14145", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "oMiV__LWV4A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "GP-VTON: Towards General Purpose Virtual Try-On via Collaborative Local-Flow Global-Parsing Learning", - "base_url": null, - "title_page": null, - "repo": "xiezhy6/GP-VTON", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_GP-VTON_Towards_General_Purpose_Virtual_Try-On_via_Collaborative_Local-Flow_Global-Parsing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13756", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "b-FDMJ0jrw0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Where Is My Spot? Few-Shot Image Generation via Latent Subspace Optimization", - "base_url": null, - "title_page": null, - "repo": "chansey0529/LSO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zheng_Where_Is_My_Spot_Few-Shot_Image_Generation_via_Latent_Subspace_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Regularized Vector Quantization for Tokenized Image Synthesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Regularized_Vector_Quantization_for_Tokenized_Image_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06424", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "EDICT: Exact Diffusion Inversion via Coupled Transformations", - "base_url": null, - "title_page": null, - "repo": "salesforce/EDICT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wallace_EDICT_Exact_Diffusion_Inversion_via_Coupled_Transformations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12446", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2k6DiE_h1eY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Scaling Up GANs for Text-to-Image Synthesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://mingukkang.github.io/GigaGAN/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kang_Scaling_Up_GANs_for_Text-to-Image_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05511", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZjxtuDQkOPY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Shape-Aware Text-Driven Layered Video Editing", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://text-video-edit.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lee_Shape-Aware_Text-Driven_Layered_Video_Editing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.13173", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "A Unified Pyramid Recurrent Network for Video Frame Interpolation", - "base_url": null, - "title_page": null, - "repo": "srcn-ivl/UPR-Net", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jin_A_Unified_Pyramid_Recurrent_Network_for_Video_Frame_Interpolation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.03456", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "clvrjUKgfhI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "TAPS3D: Text-Guided 3D Textured Shape Generation From Pseudo Supervision", - "base_url": null, - "title_page": null, - "repo": "plusmultiply/TAPS3D", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_TAPS3D_Text-Guided_3D_Textured_Shape_Generation_From_Pseudo_Supervision_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13273", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-eWBEwAkThA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Fine-Grained Face Swapping via Regional GAN Inversion", - "base_url": null, - "title_page": null, - "repo": "e4s2022/e4s", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Fine-Grained_Face_Swapping_via_Regional_GAN_Inversion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14068", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Z-cmKVeXHvY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "OTAvatar: One-Shot Talking Face Avatar With Controllable Tri-Plane Rendering", - "base_url": null, - "title_page": null, - "repo": "theEricMa/OTAvatar", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ma_OTAvatar_One-Shot_Talking_Face_Avatar_With_Controllable_Tri-Plane_Rendering_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14662", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qpIoMYFr7Aw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Deep Stereo Video Inpainting", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Deep_Stereo_Video_Inpainting_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "StyleGAN Salon: Multi-View Latent Optimization for Pose-Invariant Hairstyle Transfer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://stylegan-salon.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Khwanmuang_StyleGAN_Salon_Multi-View_Latent_Optimization_for_Pose-Invariant_Hairstyle_Transfer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02744", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Cross-GAN Auditing: Unsupervised Identification of Attribute Level Similarities and Differences Between Pretrained Generative Models", - "base_url": null, - "title_page": null, - "repo": "mattolson93/cross_gan_auditing", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Olson_Cross-GAN_Auditing_Unsupervised_Identification_of_Attribute_Level_Similarities_and_Differences_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10774", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Unsupervised Volumetric Animation", - "base_url": null, - "title_page": null, - "repo": "snap-research/unsupervised-volumetric-animation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Siarohin_Unsupervised_Volumetric_Animation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.11326", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "SINE: SINgle Image Editing With Text-to-Image Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "zhang-zx/SINE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_SINE_SINgle_Image_Editing_With_Text-to-Image_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04489", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Progressive Disentangled Representation Learning for Fine-Grained Controllable Talking Head Synthesis", - "base_url": null, - "title_page": null, - "repo": "Dorniwang/PD-FGC-inference", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Progressive_Disentangled_Representation_Learning_for_Fine-Grained_Controllable_Talking_Head_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14506", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PdSQt_zNbC4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "CAP-VSTNet: Content Affinity Preserved Versatile Style Transfer", - "base_url": null, - "title_page": null, - "repo": "linfengWen98/CAP-VSTNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wen_CAP-VSTNet_Content_Affinity_Preserved_Versatile_Style_Transfer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17867", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OTJ1wEe29Hc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "DeepVecFont-v2: Exploiting Transformers To Synthesize Vector Fonts With Higher Quality", - "base_url": null, - "title_page": null, - "repo": "yizhiwang96/deepvecfont-v2", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_DeepVecFont-v2_Exploiting_Transformers_To_Synthesize_Vector_Fonts_With_Higher_Quality_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14585", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "LEMaRT: Label-Efficient Masked Region Transform for Image Harmonization", - "base_url": null, - "title_page": null, - "repo": "yizhiwang96/deepvecfont-v2", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_LEMaRT_Label-Efficient_Masked_Region_Transform_for_Image_Harmonization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.13166", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xSS4RChu7zk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "SINE: Semantic-Driven Image-Based NeRF Editing With Prior-Guided Editing Field", - "base_url": null, - "title_page": null, - "repo": "zju3dv/SINE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bao_SINE_Semantic-Driven_Image-Based_NeRF_Editing_With_Prior-Guided_Editing_Field_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13277", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AfAR-PoZ8SM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Exploring Intra-Class Variation Factors With Learnable Cluster Prompts for Semi-Supervised Image Synthesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Exploring_Intra-Class_Variation_Factors_With_Learnable_Cluster_Prompts_for_Semi-Supervised_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Image Cropping With Spatial-Aware Feature and Rank Consistency", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/supplemental/Wang_Image_Cropping_With_CVPR_2023_supplemental.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "J8ImNnEWwGQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Picture That Sketch: Photorealistic Image Generation From Abstract Sketches", - "base_url": null, - "title_page": null, - "repo": "subhadeepkoley/PictureThatSketch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Koley_Picture_That_Sketch_Photorealistic_Image_Generation_From_Abstract_Sketches_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11162", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "k7xFbELpnv4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "MonoHuman: Animatable Human Neural Field From Monocular Video", - "base_url": null, - "title_page": null, - "repo": "Yzmblog/MonoHuman", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_MonoHuman_Animatable_Human_Neural_Field_From_Monocular_Video_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02001", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "T91fXw9dOmM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "PixHt-Lab: Pixel Height Based Light Effect Generation for Image Compositing", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sheng_PixHt-Lab_Pixel_Height_Based_Light_Effect_Generation_for_Image_Compositing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00137", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "H2B0yrEf86I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Neural Pixel Composition for 3D-4D View Synthesis From Multi-Views", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.aayushbansal.xyz/npc/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bansal_Neural_Pixel_Composition_for_3D-4D_View_Synthesis_From_Multi-Views_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.10663", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "oTJyUUH2uCk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "SpaText: Spatio-Textual Representation for Controllable Image Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://omriavrahami.com/spatext/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Avrahami_SpaText_Spatio-Textual_Representation_for_Controllable_Image_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14305", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VlieNoCwHO4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Exploring Motion Ambiguity and Alignment for High-Quality Video Frame Interpolation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Exploring_Motion_Ambiguity_and_Alignment_for_High-Quality_Video_Frame_Interpolation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2203.10291", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WoAyz1S_nTI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "MM-Diffusion: Learning Multi-Modal Diffusion Models for Joint Audio and Video Generation", - "base_url": null, - "title_page": null, - "repo": "researchmm/MM-Diffusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ruan_MM-Diffusion_Learning_Multi-Modal_Diffusion_Models_for_Joint_Audio_and_Video_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09478", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DthMxv2VogU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Synthesizing Photorealistic Virtual Humans Through Cross-Modal Disentanglement", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://ondrejtexler.github.io/synthesizing_humans/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ravichandran_Synthesizing_Photorealistic_Virtual_Humans_Through_Cross-Modal_Disentanglement_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.01320", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "oNYy2-_xuhM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Video Probabilistic Diffusion Models in Projected Latent Space", - "base_url": null, - "title_page": null, - "repo": "sihyun-yu/PVDM", - "web_page": "https://sihyun.me/PVDM/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_Video_Probabilistic_Diffusion_Models_in_Projected_Latent_Space_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.07685", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Variational Distribution Learning for Unsupervised Text-to-Image Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kang_Variational_Distribution_Learning_for_Unsupervised_Text-to-Image_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16105", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Linking Garment With Person via Semantically Associated Landmarks for Virtual Try-On", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://modelscope.cn/datasets/damo/SAL-HG/summary", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yan_Linking_Garment_With_Person_via_Semantically_Associated_Landmarks_for_Virtual_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "UV Volumes for Real-Time Rendering of Editable Free-View Human Performance", - "base_url": null, - "title_page": null, - "repo": "fanegg/UV-Volumes", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_UV_Volumes_for_Real-Time_Rendering_of_Editable_Free-View_Human_Performance_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2203.14402", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "v3PsN-rMAUw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "NULL-Text Inversion for Editing Real Images Using Guided Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "google/prompt-to-prompt", - "web_page": null, - "github_page": "https://null-text-inversion.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mokady_NULL-Text_Inversion_for_Editing_Real_Images_Using_Guided_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.09794", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qzTlzrMWU2M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Polynomial Implicit Neural Representations for Large Diverse Datasets", - "base_url": null, - "title_page": null, - "repo": "Rajhans0/Poly_INR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Singh_Polynomial_Implicit_Neural_Representations_for_Large_Diverse_Datasets_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11424", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YdFpzITgV8M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Plug-and-Play Diffusion Features for Text-Driven Image-to-Image Translation", - "base_url": null, - "title_page": null, - "repo": "MichalGeyer/plug-and-play", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tumanyan_Plug-and-Play_Diffusion_Features_for_Text-Driven_Image-to-Image_Translation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12572", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "eemzbXXU59E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Conditional Image-to-Video Generation With Latent Flow Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "nihaomiao/CVPR23_LFDM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ni_Conditional_Image-to-Video_Generation_With_Latent_Flow_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13744", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dgawtQGmMbA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Local 3D Editing via 3D Distillation of CLIP Knowledge", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hyung_Local_3D_Editing_via_3D_Distillation_of_CLIP_Knowledge_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.12570", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Private Image Generation With Dual-Purpose Auxiliary Classifier", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Private_Image_Generation_With_Dual-Purpose_Auxiliary_Classifier_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZsjYIZ2s0fw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "MAGVIT: Masked Generative Video Transformer", - "base_url": null, - "title_page": null, - "repo": "google-research/magvit", - "web_page": "https://magvit.cs.cmu.edu/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_MAGVIT_Masked_Generative_Video_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.05199", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Dimensionality-Varying Diffusion Process", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Dimensionality-Varying_Diffusion_Process_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16032", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zpNhHo3s4Eo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "VIVE3D: Viewpoint-Independent Video Editing Using 3D-Aware GANs", - "base_url": null, - "title_page": null, - "repo": "afruehstueck/VIVE3D", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fruhstuck_VIVE3D_Viewpoint-Independent_Video_Editing_Using_3D-Aware_GANs_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15893", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qfYGQwOw8pg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "LANIT: Language-Driven Image-to-Image Translation for Unlabeled Data", - "base_url": null, - "title_page": null, - "repo": "KU-CVLAB/LANIT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Park_LANIT_Language-Driven_Image-to-Image_Translation_for_Unlabeled_Data_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.14889", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "DATID-3D: Diversity-Preserved Domain Adaptation Using Text-to-Image Diffusion for 3D Generative Model", - "base_url": null, - "title_page": null, - "repo": "gwang-kim/DATID-3D", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_DATID-3D_Diversity-Preserved_Domain_Adaptation_Using_Text-to-Image_Diffusion_for_3D_Generative_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16374", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bjXQ4LTVE3E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Delving StyleGAN Inversion for Image Editing: A Foundation Latent Space Viewpoint", - "base_url": null, - "title_page": null, - "repo": "KumapowerLIU/CLCAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Delving_StyleGAN_Inversion_for_Image_Editing_A_Foundation_Latent_Space_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11448", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hsB9Wv50dm0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "High-Fidelity and Freely Controllable Talking Head Video Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_High-Fidelity_and_Freely_Controllable_Talking_Head_Video_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10168", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_syQLfiQ0_c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "SadTalker: Learning Realistic 3D Motion Coefficients for Stylized Audio-Driven Single Image Talking Face Animation", - "base_url": null, - "title_page": null, - "repo": "OpenTalker/SadTalker", - "web_page": null, - "github_page": "https://sadtalker.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_SadTalker_Learning_Realistic_3D_Motion_Coefficients_for_Stylized_Audio-Driven_Single_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12194", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TjUOalcGDtE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "StyleRF: Zero-Shot 3D Style Transfer of Neural Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "Kunhao-Liu/StyleRF", - "web_page": null, - "github_page": "https://kunhao-liu.github.io/StyleRF/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_StyleRF_Zero-Shot_3D_Style_Transfer_of_Neural_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10598", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DkbRmmzTU40", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "MOSO: Decomposing MOtion, Scene and Object for Video Prediction", - "base_url": null, - "title_page": null, - "repo": "iva-mzsun/MOSO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_MOSO_Decomposing_MOtion_Scene_and_Object_for_Video_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.03684", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5kLsKpfJFrQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Multi Domain Learning for Motion Magnification", - "base_url": null, - "title_page": null, - "repo": "jasdeep-singh-007/Multi-Domain-Learning-for-Motion-Magnification", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Singh_Multi_Domain_Learning_for_Motion_Magnification_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Sg7_sXMnRLo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "GazeNeRF: 3D-Aware Gaze Redirection With Neural Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "AlessandroRuzzi/GazeNeRF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ruzzi_GazeNeRF_3D-Aware_Gaze_Redirection_With_Neural_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04823", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JwqKbmUR3DE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Hierarchical B-Frame Video Coding Using Two-Layer CANF Without Motion Coding", - "base_url": null, - "title_page": null, - "repo": "nycu-clab/tlzmc-cvpr", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Alexandre_Hierarchical_B-Frame_Video_Coding_Using_Two-Layer_CANF_Without_Motion_Coding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02690", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Blemish-Aware and Progressive Face Retouching With Limited Paired Data", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_Blemish-Aware_and_Progressive_Face_Retouching_With_Limited_Paired_Data_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qKy6t8JbUOs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Text-Guided Unsupervised Latent Transformation for Multi-Attribute Image Manipulation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_Text-Guided_Unsupervised_Latent_Transformation_for_Multi-Attribute_Image_Manipulation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "NeuralField-LDM: Scene Generation With Hierarchical Latent Diffusion Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://research.nvidia.com/labs/toronto-ai/NFLDM/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_NeuralField-LDM_Scene_Generation_With_Hierarchical_Latent_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Fix the Noise: Disentangling Source Feature for Controllable Domain Translation", - "base_url": null, - "title_page": null, - "repo": "LeeDongYeun/FixNoise", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lee_Fix_the_Noise_Disentangling_Source_Feature_for_Controllable_Domain_Translation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11545", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VqN-rACydQw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Class-Balancing Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "qym7/CBDM-pytorch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qin_Class-Balancing_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.00562", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OWY_2OZ4e_4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "DPE: Disentanglement of Pose and Expression for General Video Portrait Editing", - "base_url": null, - "title_page": null, - "repo": "OpenTalker/DPE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pang_DPE_Disentanglement_of_Pose_and_Expression_for_General_Video_Portrait_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.06281", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vj9LELgXVJ0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Inversion-Based Style Transfer With Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "zyxElsa/InST", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Inversion-Based_Style_Transfer_With_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13203", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "W3urLYx9JZY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Deep Curvilinear Editing: Commutative and Nonlinear Image Manipulation for Pretrained Deep Generative Model", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Aoshima_Deep_Curvilinear_Editing_Commutative_and_Nonlinear_Image_Manipulation_for_Pretrained_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14573", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "iVyvQOAhLqI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "FlowGrad: Controlling the Output of Generative ODEs With Gradients", - "base_url": null, - "title_page": null, - "repo": "gnobitab/FlowGrad", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_FlowGrad_Controlling_the_Output_of_Generative_ODEs_With_Gradients_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Graph Transformer GANs for Graph-Constrained House Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Graph_Transformer_GANs_for_Graph-Constrained_House_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08225", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rwx9OPkRc4M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Master: Meta Style Transformer for Controllable Zero-Shot and Few-Shot Artistic Style Transfer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Master_Meta_Style_Transformer_for_Controllable_Zero-Shot_and_Few-Shot_Artistic_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11818", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PJaTztiUsTQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Next3D: Generative Neural Texture Rasterization for 3D-Aware Head Avatars", - "base_url": null, - "title_page": null, - "repo": "MrTornado24/Next3D", - "web_page": null, - "github_page": "https://mrtornado24.github.io/Next3D/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Next3D_Generative_Neural_Texture_Rasterization_for_3D-Aware_Head_Avatars_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11208", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0F6Pmj-1sfI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Ham2Pose: Animating Sign Language Notation Into Pose Sequences", - "base_url": null, - "title_page": null, - "repo": "rotem-shalev/Ham2Pose", - "web_page": null, - "github_page": "https://rotem-shalev.github.io/ham-to-pose/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Arkushin_Ham2Pose_Animating_Sign_Language_Notation_Into_Pose_Sequences_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13613", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_XOsxnwjo7s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Neural Transformation Fields for Arbitrary-Styled Font Generation", - "base_url": null, - "title_page": null, - "repo": "fubinfb/NTF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fu_Neural_Transformation_Fields_for_Arbitrary-Styled_Font_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Fxp8N7TDVkQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "LayoutDM: Transformer-Based Diffusion Model for Layout Generation", - "base_url": null, - "title_page": null, - "repo": "CyberAgentAILab/layout-dm", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chai_LayoutDM_Transformer-Based_Diffusion_Model_for_Layout_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.02567", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "n3akFx3mtYU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Removing Objects From Neural Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "nianticlabs/nerf-object-removal", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Weder_Removing_Objects_From_Neural_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.11966", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "J8r1jgELmsM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Person Image Synthesis via Denoising Diffusion Model", - "base_url": null, - "title_page": null, - "repo": "ankanbhunia/PIDM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bhunia_Person_Image_Synthesis_via_Denoising_Diffusion_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12500", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NsUb2uxj820", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "AdaptiveMix: Improving GAN Training via Feature Space Shrinkage", - "base_url": null, - "title_page": null, - "repo": "WentianZhang-ML/AdaptiveMix", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_AdaptiveMix_Improving_GAN_Training_via_Feature_Space_Shrinkage_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01559", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "BFKfw9rfYYU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Learning Joint Latent Space EBM Prior Model for Multi-Layer Generator", - "base_url": null, - "title_page": null, - "repo": "jcui1224/hierarchical-joint-ebm", - "web_page": null, - "github_page": "https://jcui1224.github.io/hierarchical-joint-ebm-proj/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cui_Learning_Joint_Latent_Space_EBM_Prior_Model_for_Multi-Layer_Generator_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.06323", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VGit3sZWNGM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "3D Neural Field Generation Using Triplane Diffusion", - "base_url": null, - "title_page": null, - "repo": "JRyanShue/NFD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shue_3D_Neural_Field_Generation_Using_Triplane_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16677", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nxAiyoYkTJA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "OmniAvatar: Geometry-Guided Controllable 3D Head Synthesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_OmniAvatar_Geometry-Guided_Controllable_3D_Head_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15539", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Z1aXE9q9eUI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "RWSC-Fusion: Region-Wise Style-Controlled Fusion Network for the Prohibited X-Ray Security Image Synthesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Duan_RWSC-Fusion_Region-Wise_Style-Controlled_Fusion_Network_for_the_Prohibited_X-Ray_Security_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OuOfUqWo2aQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "ObjectStitch: Object Compositing With Diffusion Model", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Song_ObjectStitch_Object_Compositing_With_Diffusion_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.00932", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tmHJVatfpn8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Persistent Nature: A Generative Model of Unbounded 3D Worlds", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://chail.github.io/persistent-nature/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chai_Persistent_Nature_A_Generative_Model_of_Unbounded_3D_Worlds_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13515", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5s1WnwRHmIs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Masked and Adaptive Transformer for Exemplar Based Image Translation", - "base_url": null, - "title_page": null, - "repo": "AiArt-HDU/MATEBIT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_Masked_and_Adaptive_Transformer_for_Exemplar_Based_Image_Translation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17123", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qCypRw-FcTM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Spider GAN: Leveraging Friendly Neighbors To Accelerate GAN Training", - "base_url": null, - "title_page": null, - "repo": "DarthSid95/SpiderStyleGAN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Asokan_Spider_GAN_Leveraging_Friendly_Neighbors_To_Accelerate_GAN_Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.07613", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EDrGSguQMBU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Re-IQA: Unsupervised Learning for Image Quality Assessment in the Wild", - "base_url": null, - "title_page": null, - "repo": "avinabsaha/ReIQA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Saha_Re-IQA_Unsupervised_Learning_for_Image_Quality_Assessment_in_the_Wild_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00451", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gHIAC-L3eFg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Align Your Latents: High-Resolution Video Synthesis With Latent Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "srpkdyy/VideoLDM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Blattmann_Align_Your_Latents_High-Resolution_Video_Synthesis_With_Latent_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08818", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "All Are Worth Words: A ViT Backbone for Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "baofff/U-ViT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bao_All_Are_Worth_Words_A_ViT_Backbone_for_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.12152", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Y2EbGfUi2SY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Few-Shot Semantic Image Synthesis With Class Affinity Transfer", - "base_url": null, - "title_page": null, - "repo": "endo-yuki-t/Fewshot-SMIS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Careil_Few-Shot_Semantic_Image_Synthesis_With_Class_Affinity_Transfer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02321", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Blowing in the Wind: CycleNet for Human Cinemagraphs From Still Images", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://hbertiche.github.io/CycleNet/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bertiche_Blowing_in_the_Wind_CycleNet_for_Human_Cinemagraphs_From_Still_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08639", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KUTJkPVwcO8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "StyleGene: Crossover and Mutation of Region-Level Facial Genes for Kinship Face Synthesis", - "base_url": null, - "title_page": null, - "repo": "CVI-SZU/StyleGene", - "web_page": null, - "github_page": "https://wmpscc.github.io/stylegene/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_StyleGene_Crossover_and_Mutation_of_Region-Level_Facial_Genes_for_Kinship_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TDqGaL79_pg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "MixNeRF: Modeling a Ray With Mixture Density for Novel View Synthesis From Sparse Inputs", - "base_url": null, - "title_page": null, - "repo": "shawn615/MixNeRF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Seo_MixNeRF_Modeling_a_Ray_With_Mixture_Density_for_Novel_View_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.08788", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PXljJordbFk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "MoStGAN-V: Video Generation With Temporal Motion Styles", - "base_url": null, - "title_page": null, - "repo": "xiaoqian-shen/MoStGAN-V", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shen_MoStGAN-V_Video_Generation_With_Temporal_Motion_Styles_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02777", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hCyaAMh0Kgk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Frame Interpolation Transformer and Uncertainty Guidance", - "base_url": null, - "title_page": null, - "repo": "zhshi0816/Video-Frame-Interpolation-Transformer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Plack_Frame_Interpolation_Transformer_and_Uncertainty_Guidance_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9KpZA-tibrU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Towards End-to-End Generative Modeling of Long Videos With Memory-Efficient Bidirectional Transformers", - "base_url": null, - "title_page": null, - "repo": "Ugness/MeBT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yoo_Towards_End-to-End_Generative_Modeling_of_Long_Videos_With_Memory-Efficient_Bidirectional_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11251", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "QTOJEO5o23k", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "HOLODIFFUSION: Training a 3D Diffusion Model Using 2D Images", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/holo_diffusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Karnewar_HOLODIFFUSION_Training_a_3D_Diffusion_Model_Using_2D_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16509", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "F65fEmvUKyc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Neural Texture Synthesis With Guided Correspondence", - "base_url": null, - "title_page": null, - "repo": "EliotChenKJ/Guided-Correspondence-Loss", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Neural_Texture_Synthesis_With_Guided_Correspondence_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "njB_O08IVCk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "PanoHead: Geometry-Aware 3D Full-Head Synthesis in 360°", - "base_url": null, - "title_page": null, - "repo": "SizheAn/PanoHead", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/An_PanoHead_Geometry-Aware_3D_Full-Head_Synthesis_in_360deg_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13071", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Y8NXiBOEWoE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "InstructPix2Pix: Learning To Follow Image Editing Instructions", - "base_url": null, - "title_page": null, - "repo": "timothybrooks/instruct-pix2pix", - "web_page": "https://www.timothybrooks.com/instruct-pix2pix/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Brooks_InstructPix2Pix_Learning_To_Follow_Image_Editing_Instructions_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.09800", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GUvD5W6tBJ4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Unpaired Image-to-Image Translation With Shortest Path Regularization", - "base_url": null, - "title_page": null, - "repo": "Mid-Push/santa", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_Unpaired_Image-to-Image_Translation_With_Shortest_Path_Regularization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tdzIUbz1JTQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Freestyle Layout-to-Image Synthesis", - "base_url": null, - "title_page": null, - "repo": "essunny310/FreestyleNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xue_Freestyle_Layout-to-Image_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14412", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EUeV3b3XHe8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "On Distillation of Guided Diffusion Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Meng_On_Distillation_of_Guided_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.03142", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Single Image Backdoor Inversion via Robust Smoothed Classifiers", - "base_url": null, - "title_page": null, - "repo": "locuslab/smoothinv", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Single_Image_Backdoor_Inversion_via_Robust_Smoothed_Classifiers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00215", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bt1yxznTXrQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Make-a-Story: Visual Memory Conditioned Consistent Story Generation", - "base_url": null, - "title_page": null, - "repo": "ubc-vision/Make-A-Story", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rahman_Make-a-Story_Visual_Memory_Conditioned_Consistent_Story_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13319", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "BXZ7LAg1sP8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Towards Practical Plug-and-Play Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "riiid/PPAP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Go_Towards_Practical_Plug-and-Play_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.05973", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mIKEfXJj9Zs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Efficient Scale-Invariant Generator With Column-Row Entangled Pixel Synthesis", - "base_url": null, - "title_page": null, - "repo": "VinAIResearch/CREPS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nguyen_Efficient_Scale-Invariant_Generator_With_Column-Row_Entangled_Pixel_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14157", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_gceZhQMc8U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Wavelet Diffusion Models Are Fast and Scalable Image Generators", - "base_url": null, - "title_page": null, - "repo": "VinAIResearch/WaveDiff", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Phung_Wavelet_Diffusion_Models_Are_Fast_and_Scalable_Image_Generators_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16152", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KaIMMamhKsU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "3D GAN Inversion With Facial Symmetry Prior", - "base_url": null, - "title_page": null, - "repo": "FeiiYin/SPI", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yin_3D_GAN_Inversion_With_Facial_Symmetry_Prior_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16927", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "pQF-cOVpQEE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Seeing What You Said: Talking Face Generation Guided by a Lip Reading Expert", - "base_url": null, - "title_page": null, - "repo": "Sxjdwang/TalkLip", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Seeing_What_You_Said_Talking_Face_Generation_Guided_by_a_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17480", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LUsRjL02ZsY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "PCT-Net: Full Resolution Image Harmonization Using Pixel-Wise Color Transformations", - "base_url": null, - "title_page": null, - "repo": "rakutentech/PCT-Net-Image-Harmonization", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Guerreiro_PCT-Net_Full_Resolution_Image_Harmonization_Using_Pixel-Wise_Color_Transformations_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "ERNIE-ViLG 2.0: Improving Text-to-Image Diffusion Model With Knowledge-Enhanced Mixture-of-Denoising-Experts", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://wenxin.baidu.com/ernie-vilg", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_ERNIE-ViLG_2.0_Improving_Text-to-Image_Diffusion_Model_With_Knowledge-Enhanced_Mixture-of-Denoising-Experts_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.15257", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Video Compression With Entropy-Constrained Neural Representations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gomes_Video_Compression_With_Entropy-Constrained_Neural_Representations_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PyxyYlwQuCw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Uncovering the Disentanglement Capability in Text-to-Image Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "UCSB-NLP-Chang/DiffusionDisentanglement", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Uncovering_the_Disentanglement_Capability_in_Text-to-Image_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08698", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "m3CVMRAt1Q0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "CoralStyleCLIP: Co-Optimized Region and Layer Selection for Image Editing", - "base_url": null, - "title_page": null, - "repo": "JiauZhang/CoralStyleCLIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Revanur_CoralStyleCLIP_Co-Optimized_Region_and_Layer_Selection_for_Image_Editing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05031", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5LTbVjuErkg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Diffusion Video Autoencoders: Toward Temporally Consistent Face Video Editing via Disentangled Video Encoding", - "base_url": null, - "title_page": null, - "repo": "man805/Diffusion-Video-Autoencoders", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Diffusion_Video_Autoencoders_Toward_Temporally_Consistent_Face_Video_Editing_via_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.02802", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ISawoMRNuRU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Sequential Training of GANs Against GAN-Classifiers Reveals Correlated Knowledge Gaps Present Among Independently Trained GAN Instances", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pathak_Sequential_Training_of_GANs_Against_GAN-Classifiers_Reveals_Correlated_Knowledge_Gaps_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15533", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "q2yOvUIaz2o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Attribute-Preserving Face Dataset Anonymization via Latent Code Optimization", - "base_url": null, - "title_page": null, - "repo": "chi0tzp/FALCO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Barattin_Attribute-Preserving_Face_Dataset_Anonymization_via_Latent_Code_Optimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11296", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qpGecrlK7_8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Shifted Diffusion for Text-to-Image Generation", - "base_url": null, - "title_page": null, - "repo": "drboog/Shifted_Diffusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Shifted_Diffusion_for_Text-to-Image_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15388", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "HandsOff: Labeled Dataset Generation With No Additional Human Annotations", - "base_url": null, - "title_page": null, - "repo": "austinxu87/handsoff", - "web_page": null, - "github_page": "https://austinxu87.github.io/handsoff/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_HandsOff_Labeled_Dataset_Generation_With_No_Additional_Human_Annotations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.12645", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Yn-1QOcrIAQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Lookahead Diffusion Probabilistic Models for Refining Mean Estimation", - "base_url": null, - "title_page": null, - "repo": "guoqiang-zhang-x/LA-DPM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Lookahead_Diffusion_Probabilistic_Models_for_Refining_Mean_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11312", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Imagen Editor and EditBench: Advancing and Evaluating Text-Guided Image Inpainting", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://imagen.research.google/editor/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Imagen_Editor_and_EditBench_Advancing_and_Evaluating_Text-Guided_Image_Inpainting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06909", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "Re-GAN: Data-Efficient GANs Training via Architectural Reconfiguration", - "base_url": null, - "title_page": null, - "repo": "IntellicentAI-Lab/Re-GAN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Saxena_Re-GAN_Data-Efficient_GANs_Training_via_Architectural_Reconfiguration_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "BBDM: Image-to-Image Translation With Brownian Bridge Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "xuekt98/BBDM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_BBDM_Image-to-Image_Translation_With_Brownian_Bridge_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.07680", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZrW88C63Suo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - }, - { - "title": "VectorFusion: Text-to-SVG by Abstracting Pixel-Based Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "ximinng/VectorFusion-pytorch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jain_VectorFusion_Text-to-SVG_by_Abstracting_Pixel-Based_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11319", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Image and Video Synthesis and Generation" - } -] \ No newline at end of file diff --git a/json_data/machine-learning-other-than-deep-learning.json b/json_data/machine-learning-other-than-deep-learning.json deleted file mode 100644 index bc05c5e..0000000 --- a/json_data/machine-learning-other-than-deep-learning.json +++ /dev/null @@ -1,352 +0,0 @@ -[ - { - "title": "Deep Incomplete Multi-View Clustering with Cross-View Partial Sample and Prototype Alignment", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jin_Deep_Incomplete_Multi-View_Clustering_With_Cross-View_Partial_Sample_and_Prototype_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15689", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Towards Better Decision Forests: Forest Alternating Optimization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Carreira-Perpinan_Towards_Better_Decision_Forests_Forest_Alternating_Optimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Class Adaptive Network Calibration", - "base_url": null, - "title_page": null, - "repo": "by-liu/CALS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Class_Adaptive_Network_Calibration_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15088", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Defining and Quantifying the Emergence of Sparse Concepts in DNNs", - "base_url": null, - "title_page": null, - "repo": "sjtu-xai-lab/aog", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ren_Defining_and_Quantifying_the_Emergence_of_Sparse_Concepts_in_DNNs_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2111.06206", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wq7eM-fcNGg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "MOT: Masked Optimal Transport for Partial Domain Adaptation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_MOT_Masked_Optimal_Transport_for_Partial_Domain_Adaptation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "L2zqUfzlqHo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Adaptive Graph Convolutional Subspace Clustering", - "base_url": null, - "title_page": null, - "repo": "weilyshmtu/AGCSC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_Adaptive_Graph_Convolutional_Subspace_Clustering_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.03414", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Reliable and Interpretable Personalized Federated Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qin_Reliable_and_Interpretable_Personalized_Federated_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "62u4Uf6uxn8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Confidence-Aware Personalized Federated Learning via Variational Expectation Maximization", - "base_url": null, - "title_page": null, - "repo": "JunyiZhu-AI/confidence_aware_PFL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_Confidence-Aware_Personalized_Federated_Learning_via_Variational_Expectation_Maximization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.12557", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EB1fw1SZnEU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Efficient Verification of Neural Networks Against LVM-based Specifications", - "base_url": null, - "title_page": null, - "repo": "hh10/Efficient-Verification-of-NNs-against-LVM-based-Specifications", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hanspal_Efficient_Verification_of_Neural_Networks_Against_LVM-Based_Specifications_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7AFTMjaYUxg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "You are Catching my Attention: Are Vision Transformers Bad Learners under Backdoor Attacks?", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yuan_You_Are_Catching_My_Attention_Are_Vision_Transformers_Bad_Learners_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Leveraging Inter-Rater Agreement for Classification in the Presence of Noisy Labels", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bucarelli_Leveraging_Inter-Rater_Agreement_for_Classification_in_the_Presence_of_Noisy_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "khpOlR9u1U8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Sliced Optimal Partial Transport", - "base_url": null, - "title_page": null, - "repo": "yikun-baio/sliced_opt", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bai_Sliced_Optimal_Partial_Transport_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08049", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "HDJ0b9NJEB4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "A Meta-Learning Approach to Predicting Performance and Data Requirements", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jain_A_Meta-Learning_Approach_to_Predicting_Performance_and_Data_Requirements_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01598", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - }, - { - "title": "Towards Effective Visual Representations for Partial-Label Learning", - "base_url": null, - "title_page": null, - "repo": "AlphaXia/PaPi", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xia_Towards_Effective_Visual_Representations_for_Partial-Label_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.06080", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Machine Learning (other than Deep Learning)" - } -] \ No newline at end of file diff --git a/json_data/medical-and-biological-vision-cell-microscopy.json b/json_data/medical-and-biological-vision-cell-microscopy.json deleted file mode 100644 index 586d348..0000000 --- a/json_data/medical-and-biological-vision-cell-microscopy.json +++ /dev/null @@ -1,1302 +0,0 @@ -[ - { - "title": "Decoupled Semantic Prototypes Enable Learning from Diverse Annotation Types for Semi-Weakly Segmentation in Expert-Driven Domains", - "base_url": null, - "title_page": null, - "repo": "Simael/DSP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Reiss_Decoupled_Semantic_Prototypes_Enable_Learning_From_Diverse_Annotation_Types_for_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Geometric Visual Similarity Learning in 3D Medical Image Self-Supervised Pre-Training", - "base_url": null, - "title_page": null, - "repo": "YutingHe-list/GVSL", - "web_page": null, - "github_page": "https://x-ark.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Geometric_Visual_Similarity_Learning_in_3D_Medical_Image_Self-Supervised_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00874", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vS0BhOpjErY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Flexible-Cm GAN: Towards Precise 3D Dose Prediction in Radiotherapy", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_Flexible-Cm_GAN_Towards_Precise_3D_Dose_Prediction_in_Radiotherapy_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jGlW1uvBF7M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Bidirectional Copy-Paste for Semi-Supervised Medical Image Segmentation", - "base_url": null, - "title_page": null, - "repo": "DeepMed-Lab-ECNU/BCP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bai_Bidirectional_Copy-Paste_for_Semi-Supervised_Medical_Image_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.00673", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lQ3UTN-SZLM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "MagicNet: Semi-Supervised Multi-Organ Segmentation via Magic-Cube Partition and Recovery", - "base_url": null, - "title_page": null, - "repo": "DeepMed-Lab-ECNU/MagicNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_MagicNet_Semi-Supervised_Multi-Organ_Segmentation_via_Magic-Cube_Partition_and_Recovery_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.14310", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "C1xiG8SS2iw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Visual Language Pretrained Multiple Instance Zero-Shot Transfer for Histopathology Images", - "base_url": null, - "title_page": null, - "repo": "mahmoodlab/MI-Zero", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_Visual_Language_Pretrained_Multiple_Instance_Zero-Shot_Transfer_for_Histopathology_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.07831", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "x8Ch5wsCJRw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Label-Free Liver Tumor Segmentation", - "base_url": null, - "title_page": null, - "repo": "MrGiovanni/SyntheticTumors", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Label-Free_Liver_Tumor_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14869", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DhZzAp7gxxw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Devil is in the Queries: Advancing Mask Transformers for Real-World Medical Image Segmentation and Out-of-Distribution Localization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yuan_Devil_Is_in_the_Queries_Advancing_Mask_Transformers_for_Real-World_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00212", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xzNxXKlYHYA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "DoNet: Deep De-Overlapping Network for Cytology Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": "DeepDoNet/DoNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_DoNet_Deep_De-Overlapping_Network_for_Cytology_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14373", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bEW4kUmClCI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "SQUID: Deep Feature In-Painting for Unsupervised Anomaly Detection", - "base_url": null, - "title_page": null, - "repo": "tiangexiang/SQUID", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiang_SQUID_Deep_Feature_In-Painting_for_Unsupervised_Anomaly_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2111.13495", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Learning Federated Visual Prompt in Null Space for MRI Reconstruction", - "base_url": null, - "title_page": null, - "repo": "chunmeifeng/FedPR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_Learning_Federated_Visual_Prompt_in_Null_Space_for_MRI_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16181", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Pseudo-Label Guided Contrastive Learning for Semi-Supervised Medical Image Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Basak_Pseudo-Label_Guided_Contrastive_Learning_for_Semi-Supervised_Medical_Image_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Image Quality-Aware Diagnosis via Meta-Knowledge Co-Embedding", - "base_url": null, - "title_page": null, - "repo": "chehx/MKCNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Che_Image_Quality-Aware_Diagnosis_via_Meta-Knowledge_Co-Embedding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15038", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Iterative Next Boundary Detection for Instance Segmentation of Tree Rings in Microscopy Images of Shrub Cross Sections", - "base_url": null, - "title_page": null, - "repo": "alexander-g/INBD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gillert_Iterative_Next_Boundary_Detection_for_Instance_Segmentation_of_Tree_Rings_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03022", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "HciQxL2K8_E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Dynamic Graph Enhanced Contrastive Learning for Chest X-Ray Report Generation", - "base_url": null, - "title_page": null, - "repo": "mlii0117/DCL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Dynamic_Graph_Enhanced_Contrastive_Learning_for_Chest_X-Ray_Report_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10323", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "aBUQbYmcp-k", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Seeing Beyond the Brain: Conditional Diffusion Model with Sparse Masked Modeling for Vision Decoding", - "base_url": null, - "title_page": null, - "repo": "zjc062/mind-vis", - "web_page": null, - "github_page": "https://mind-vis.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Seeing_Beyond_the_Brain_Conditional_Diffusion_Model_With_Sparse_Masked_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.06956", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Oh7XG_hoX34", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Bi-Directional Feature Fusion Generative Adversarial Network for Ultra-High Resolution Pathological Image Virtual Re-Staining", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Bi-Directional_Feature_Fusion_Generative_Adversarial_Network_for_Ultra-High_Resolution_Pathological_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "KiUT: Knowledge-Injected U-Transformer for Radiology Report Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_KiUT_Knowledge-Injected_U-Transformer_for_Radiology_Report_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.11345", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Weakly Supervised Segmentation with Point Annotations for Histopathology Images via Contrast-based Variational Model", - "base_url": null, - "title_page": null, - "repo": "huiqu18/WeaklySegPointAnno", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Weakly_Supervised_Segmentation_With_Point_Annotations_for_Histopathology_Images_via_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03572", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Ambiguous Medical Image Segmentation using Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "aimansnigdha/Ambiguous-Medical-Image-Segmentation-using-Diffusion-Models", - "web_page": null, - "github_page": "https://aimansnigdha.github.io/cimd/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rahman_Ambiguous_Medical_Image_Segmentation_Using_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04745", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3gVn0-IFOKs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Causally-Aware Intraoperative Imputation for Overall Survival Time Prediction", - "base_url": null, - "title_page": null, - "repo": "ChrisXLi/CaDAG", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Causally-Aware_Intraoperative_Imputation_for_Overall_Survival_Time_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SrsttIKzL84", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Best of Both Worlds: Multimodal Contrastive Learning with Tabular and Imaging Data", - "base_url": null, - "title_page": null, - "repo": "paulhager/MMCL-Tabular-Imaging", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hager_Best_of_Both_Worlds_Multimodal_Contrastive_Learning_With_Tabular_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14080", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "iHVPSMEM6WM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "GradICON: Approximate Diffeomorphisms via Gradient Inverse Consistency", - "base_url": null, - "title_page": null, - "repo": "uncbiag/ICON", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tian_GradICON_Approximate_Diffeomorphisms_via_Gradient_Inverse_Consistency_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.05897", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bt-nAYbwcW8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Fair Federated Medical Image Segmentation via Client Contribution Estimation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://github.com/NVIDIA/NVFlare/tree/main/research/fed-ce", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_Fair_Federated_Medical_Image_Segmentation_via_Client_Contribution_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16520", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zV4as47EWzg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Histopathology whole Slide Image Analysis with Heterogeneous Graph Representation Learning", - "base_url": null, - "title_page": null, - "repo": "HKU-MedAI/WSI-HGNN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chan_Histopathology_Whole_Slide_Image_Analysis_With_Heterogeneous_Graph_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.04189", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "F47ureXZ7fo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Unsupervised Contour Tracking of Live Cells by Mechanical and Cycle Consistency Losses", - "base_url": null, - "title_page": null, - "repo": "JunbongJang/contour-tracking", - "web_page": null, - "github_page": "https://junbongjang.github.io/projects/contour-tracking/index.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jang_Unsupervised_Contour_Tracking_of_Live_Cells_by_Mechanical_and_Cycle_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08364", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lA9lUx9mriM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Learning to Exploit the Sequence-Specific Prior Knowledge for Image Processing Pipelines Optimization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qin_Learning_To_Exploit_the_Sequence-Specific_Prior_Knowledge_for_Image_Processing_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Oh-kgpe-S_Y", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "RepMode: Learning to Re-Parameterize Diverse Experts for Subcellular Structure Prediction", - "base_url": null, - "title_page": null, - "repo": "Correr-Zhou/RepMode", - "web_page": null, - "github_page": "https://correr-zhou.github.io/RepMode/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_RepMode_Learning_to_Re-Parameterize_Diverse_Experts_for_Subcellular_Structure_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.10066", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Towards Trustable Skin Cancer Diagnosis via Rewriting Model's Decision", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yan_Towards_Trustable_Skin_Cancer_Diagnosis_via_Rewriting_Models_Decision_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00885", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Task-Specific Fine-Tuning via Variational Information Bottleneck for Weakly-Supervised Pathology whole Slide Image Classification", - "base_url": null, - "title_page": null, - "repo": "invoker-LL/WSI-finetuning", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Task-Specific_Fine-Tuning_via_Variational_Information_Bottleneck_for_Weakly-Supervised_Pathology_Whole_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08446", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fSLcO_Knt6Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "TINC: Tree-Structured Implicit Neural Compression", - "base_url": null, - "title_page": null, - "repo": "RichealYoung/TINC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_TINC_Tree-Structured_Implicit_Neural_Compression_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.06689", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7UZ1YOsCtrU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Topology-Guided Multi-Class Cell Context Generation for Digital Pathology", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Abousamra_Topology-Guided_Multi-Class_Cell_Context_Generation_for_Digital_Pathology_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02255", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3a5Mi6W5Vcw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Directional Connectivity-based Segmentation of Medical Images", - "base_url": null, - "title_page": null, - "repo": "Zyun-Y/DconnNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Directional_Connectivity-Based_Segmentation_of_Medical_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00145", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "C3xCL8nbEU4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "A Soma Segmentation Benchmark in Full Adult Fly Brain", - "base_url": null, - "title_page": null, - "repo": "liuxy1103/EMADS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_A_Soma_Segmentation_Benchmark_in_Full_Adult_Fly_Brain_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Constrained Evolutionary Diffusion Filter for Monocular Endoscope Tracking", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_Constrained_Evolutionary_Diffusion_Filter_for_Monocular_Endoscope_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Benchmarking Self-Supervised Learning on Diverse Pathology Datasets", - "base_url": null, - "title_page": null, - "repo": "lunit-io/benchmark-ssl-pathology", - "web_page": null, - "github_page": "https://lunit-io.github.io/research/publications/pathology_ssl/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kang_Benchmarking_Self-Supervised_Learning_on_Diverse_Pathology_Datasets_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04690", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yjIY0Xf0naU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "DualRel: Semi-Supervised Mitochondria Segmentation from a Prototype Perspective", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mai_DualRel_Semi-Supervised_Mitochondria_Segmentation_From_a_Prototype_Perspective_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "un00jmcBAbQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "SDC-UDA: Volumetric Unsupervised Domain Adaptation Framework for Slice-Direction Continuous Cross-Modality Medical Image Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shin_SDC-UDA_Volumetric_Unsupervised_Domain_Adaptation_Framework_for_Slice-Direction_Continuous_Cross-Modality_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.11012", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "R2c8sxEdjN4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "OCELOT: Overlapped Cell on Tissue Dataset for Histopathology", - "base_url": null, - "title_page": null, - "repo": "lunit-io/ocelot23algo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ryu_OCELOT_Overlapped_Cell_on_Tissue_Dataset_for_Histopathology_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13110", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "V9RjvV9JrM8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Orthogonal Annotation Benefits Barely-Supervised Medical Image Segmentation", - "base_url": null, - "title_page": null, - "repo": "HengCai-NJU/DeSCO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cai_Orthogonal_Annotation_Benefits_Barely-Supervised_Medical_Image_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13090", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UjFFGfUDpkc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "DeGPR: Deep Guided Posterior Regularization for Multi-Class Cell Detection and Counting", - "base_url": null, - "title_page": null, - "repo": "dair-iitd/DeGPR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tyagi_DeGPR_Deep_Guided_Posterior_Regularization_for_Multi-Class_Cell_Detection_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00741", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "d8TYNA8nE9c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Interactive and Explainable Region-Guided Radiology Report Generation", - "base_url": null, - "title_page": null, - "repo": "ttanida/rgrg", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tanida_Interactive_and_Explainable_Region-Guided_Radiology_Report_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08295", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "A Loopback Network for Explainable Microvascular Invasion Classification", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_A_Loopback_Network_for_Explainable_Microvascular_Invasion_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1FOadcF7Tlg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Interventional Bag Multi-Instance Learning on Whole-Slide Pathological Images", - "base_url": null, - "title_page": null, - "repo": "HHHedo/IBMIL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Interventional_Bag_Multi-Instance_Learning_on_Whole-Slide_Pathological_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06873", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7UjvDaFxiIQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "MAESTER: Masked Autoencoder Guided Segmentation at Pixel Resolution for Accurate, Self-Supervised Subcellular Structure Recognition", - "base_url": null, - "title_page": null, - "repo": "bowang-lab/MAESTER", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_MAESTER_Masked_Autoencoder_Guided_Segmentation_at_Pixel_Resolution_for_Accurate_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Neuralizer: General Neuroimage Analysis without Re-Training", - "base_url": null, - "title_page": null, - "repo": "SteffenCzolbe/neuralizer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Czolbe_Neuralizer_General_Neuroimage_Analysis_Without_Re-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.02644", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_wgCESDwjZI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Why is the Winner the Best?", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Eisenmann_Why_Is_the_Winner_the_Best_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17719", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "aURkx61EDjo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Rethinking Few-Shot Medical Segmentation: A Vector Quantization View", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Rethinking_Few-Shot_Medical_Segmentation_A_Vector_Quantization_View_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "PEFAT: Boosting Semi-Supervised Medical Image Classification via Pseudo-Loss Estimation and Feature Adversarial Training", - "base_url": null, - "title_page": null, - "repo": "maxwell0027/PEFAT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zeng_PEFAT_Boosting_Semi-Supervised_Medical_Image_Classification_via_Pseudo-Loss_Estimation_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tPOTyXY1khA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Indescribable Multi-Modal Spatial Evaluator", - "base_url": null, - "title_page": null, - "repo": "Kid-Liet/IMSE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kong_Indescribable_Multi-Modal_Spatial_Evaluator_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00369", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Multiple Instance Learning via Iterative Self-Paced Supervised Contrastive Learning", - "base_url": null, - "title_page": null, - "repo": "Kangningthu/ItS2CLR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Multiple_Instance_Learning_via_Iterative_Self-Paced_Supervised_Contrastive_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.09452", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "iDlII2RshIw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - }, - { - "title": "Hierarchical Discriminative Learning Improves Visual Representations of Biomedical Microscopy", - "base_url": null, - "title_page": null, - "repo": "MLNeurosurg/hidisc", - "web_page": "https://hidisc.mlins.org/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_Hierarchical_Discriminative_Learning_Improves_Visual_Representations_of_Biomedical_Microscopy_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01605", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PkXki83vQqg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Medical and Biological Vision; Cell Microscopy" - } -] \ No newline at end of file diff --git a/json_data/multi-modal-learning.json b/json_data/multi-modal-learning.json deleted file mode 100644 index 6ad1748..0000000 --- a/json_data/multi-modal-learning.json +++ /dev/null @@ -1,2227 +0,0 @@ -[ - { - "title": "Pix2map: Cross-Modal Retrieval for Inferring Street Maps From Images", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://pix2map.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Pix2map_Cross-Modal_Retrieval_for_Inferring_Street_Maps_From_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.04224", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "18VtggvpynY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Audio-Visual Grouping Network for Sound Localization From Mixtures", - "base_url": null, - "title_page": null, - "repo": "stoneMo/AVGN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mo_Audio-Visual_Grouping_Network_for_Sound_Localization_From_Mixtures_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17056", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xMA2vOlpaHY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Learning Semantic Relationship Among Instances for Image-Text Matching", - "base_url": null, - "title_page": null, - "repo": "CrossmodalGroup/HREM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fu_Learning_Semantic_Relationship_Among_Instances_for_Image-Text_Matching_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Identity-Preserving Talking Face Generation With Landmark and Appearance Priors", - "base_url": null, - "title_page": null, - "repo": "Weizhi-Zhong/IP_LAP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhong_Identity-Preserving_Talking_Face_Generation_With_Landmark_and_Appearance_Priors_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.08293", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jpap8rLXh94", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "ImageBind: One Embedding Space To Bind Them All", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://facebookresearch.github.io/ImageBind", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Girdhar_ImageBind_One_Embedding_Space_To_Bind_Them_All_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.05665", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "X5JCEzhdkW4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Learning To Dub Movies via Hierarchical Prosody Models", - "base_url": null, - "title_page": null, - "repo": "GalaxyCong/HPMDubbing", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cong_Learning_To_Dub_Movies_via_Hierarchical_Prosody_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04054", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "OmniMAE: Single Model Masked Pretraining on Images and Videos", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/omnivore", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Girdhar_OmniMAE_Single_Model_Masked_Pretraining_on_Images_and_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.08356", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset", - "base_url": null, - "title_page": null, - "repo": "CNVid/CNVid-3.5M", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gan_CNVid-3.5M_Build_Filter_and_Pre-Train_the_Large-Scale_Public_Chinese_Video-Text_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ywJfAg4wvr0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Egocentric Audio-Visual Object Localization", - "base_url": null, - "title_page": null, - "repo": "WikiChao/Ego-AV-Loc", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Egocentric_Audio-Visual_Object_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13471", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0-_XJJ1JLmM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Learning Visual Representations via Language-Guided Sampling", - "base_url": null, - "title_page": null, - "repo": "mbanani/lgssl", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Banani_Learning_Visual_Representations_via_Language-Guided_Sampling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.12248", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "95I8DmUoJ2s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Unite and Conquer: Plug & Play Multi-Modal Synthesis Using Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "Nithin-GK/UniteandConquer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nair_Unite_and_Conquer_Plug__Play_Multi-Modal_Synthesis_Using_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.00793", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "iQuery: Instruments As Queries for Audio-Visual Sound Separation", - "base_url": null, - "title_page": null, - "repo": "JiabenChen/iQuery", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_iQuery_Instruments_As_Queries_for_Audio-Visual_Sound_Separation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03814", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EZ9CgknV9Z4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-Identification", - "base_url": null, - "title_page": null, - "repo": "ZYK100/LLCM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Diverse_Embedding_Expansion_Network_and_Low-Light_Cross-Modality_Benchmark_for_Visible-Infrared_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14481", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "oMIRqc-Fq5c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "BLVLab/PiMAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_PiMAE_Point_Cloud_and_Image_Interactive_Masked_Autoencoders_for_3D_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08129", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rcs8DYAwugQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners", - "base_url": null, - "title_page": null, - "repo": "ZrrSkywalker/CaFo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Prompt_Generate_Then_Cache_Cascade_of_Foundation_Models_Makes_Strong_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.02151", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Non-Contrastive Learning Meets Language-Image Pre-Training", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Non-Contrastive_Learning_Meets_Language-Image_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.09304", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Highly Confident Local Structure Based Consensus Graph Learning for Incomplete Multi-View Clustering", - "base_url": null, - "title_page": null, - "repo": "ckghostwj/cvpr2023_code", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wen_Highly_Confident_Local_Structure_Based_Consensus_Graph_Learning_for_Incomplete_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8yaouwWf4ko", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Vision Transformers Are Parameter-Efficient Audio-Visual Learners", - "base_url": null, - "title_page": null, - "repo": "GenjiB/LAVISH", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Vision_Transformers_Are_Parameter-Efficient_Audio-Visual_Learners_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07983", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Teaching Structured Vision & Language Concepts to Vision & Language Models", - "base_url": null, - "title_page": null, - "repo": "SivanDoveh/TSVLC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Doveh_Teaching_Structured_Vision__Language_Concepts_to_Vision__Language_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11733", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "s_rr1RbX1Iw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Data-Free Sketch-Based Image Retrieval", - "base_url": null, - "title_page": null, - "repo": "abhrac/data-free-sbir", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chaudhuri_Data-Free_Sketch-Based_Image_Retrieval_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07775", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Align and Attend: Multimodal Summarization With Dual Contrastive Losses", - "base_url": null, - "title_page": null, - "repo": "boheumd/A2Summ", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Align_and_Attend_Multimodal_Summarization_With_Dual_Contrastive_Losses_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07284", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7EfdJx6G9rI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Efficient Multimodal Fusion via Interactive Prompting", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Efficient_Multimodal_Fusion_via_Interactive_Prompting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.06306", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MK_HJkgGnJ4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Multimodal Prompting With Missing Modalities for Visual Recognition", - "base_url": null, - "title_page": null, - "repo": "YiLunLee/missing_aware_prompts", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lee_Multimodal_Prompting_With_Missing_Modalities_for_Visual_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.03369", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jin_Learning_Instance-Level_Representation_for_Large-Scale_Multi-Modal_Pretraining_in_E-Commerce_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02853", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "What Happened 3 Seconds Ago? Inferring the Past With Thermal Imaging", - "base_url": null, - "title_page": null, - "repo": "ZitianTang/Thermal-IM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_What_Happened_3_Seconds_Ago_Inferring_the_Past_With_Thermal_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.13651", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RKptl-mUYQw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "MMANet: Margin-Aware Distillation and Modality-Aware Regularization for Incomplete Multimodal Learning", - "base_url": null, - "title_page": null, - "repo": "shicaiwei123/MMANet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_MMANet_Margin-Aware_Distillation_and_Modality-Aware_Regularization_for_Incomplete_Multimodal_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08028", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Multi-Modal Learning With Missing Modality via Shared-Specific Feature Modelling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Multi-Modal_Learning_With_Missing_Modality_via_Shared-Specific_Feature_Modelling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.14126", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wkYFpWOZaeg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "The ObjectFolder Benchmark: Multisensory Learning With Neural and Real Objects", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://objectfolder.stanford.edu/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_The_ObjectFolder_Benchmark_Multisensory_Learning_With_Neural_and_Real_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VhXDempUYgE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Position-Guided Text Prompt for Vision-Language Pre-Training", - "base_url": null, - "title_page": null, - "repo": "sail-sg/ptp", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Position-Guided_Text_Prompt_for_Vision-Language_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09737", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6FNXUSMefIQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Conditional Generation of Audio From Video via Foley Analogies", - "base_url": null, - "title_page": null, - "repo": "XYPB/CondFoleyGen", - "web_page": null, - "github_page": "https://xypb.github.io/CondFoleyGen/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Du_Conditional_Generation_of_Audio_From_Video_via_Foley_Analogies_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08490", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "OSAN: A One-Stage Alignment Network To Unify Multimodal Alignment and Unsupervised Domain Adaptation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_OSAN_A_One-Stage_Alignment_Network_To_Unify_Multimodal_Alignment_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "84H9dQZD3DY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Self-Supervised Video Forensics by Audio-Visual Anomaly Detection", - "base_url": null, - "title_page": null, - "repo": "cfeng16/audio-visual-forensics", - "web_page": null, - "github_page": "https://cfeng16.github.io/audio-visual-forensics/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_Self-Supervised_Video_Forensics_by_Audio-Visual_Anomaly_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.01767", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding", - "base_url": null, - "title_page": null, - "repo": "salesforce/ULIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_ULIP_Learning_a_Unified_Representation_of_Language_Images_and_Point_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.05171", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dgFYBVmeilk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "AVFormer: Injecting Vision Into Frozen Speech Models for Zero-Shot AV-ASR", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Seo_AVFormer_Injecting_Vision_Into_Frozen_Speech_Models_for_Zero-Shot_AV-ASR_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16501", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring", - "base_url": null, - "title_page": null, - "repo": "joannahong/AV-RelScore", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hong_Watch_or_Listen_Robust_Audio-Visual_Speech_Recognition_With_Visual_Corruption_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08536", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.pinakinathc.me/scenetrilogy/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chowdhury_SceneTrilogy_On_Human_Scene-Sketch_and_Its_Complementarity_With_Photo_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2204.11964", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_Exploring_and_Exploiting_Uncertainty_for_Incomplete_Multi-View_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05165", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "d124-SGH6bw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "EXIF As Language: Learning Cross-Modal Associations Between Images and Camera Metadata", - "base_url": null, - "title_page": null, - "repo": "hellomuffin/exif-as-language", - "web_page": null, - "github_page": "https://hellomuffin.github.io/exif-as-language/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zheng_EXIF_As_Language_Learning_Cross-Modal_Associations_Between_Images_and_Camera_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.04647", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dPHdNgxUXd4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens", - "base_url": null, - "title_page": null, - "repo": "yuxiaochen1103/FDT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Revisiting_Multimodal_Representation_in_Contrastive_Learning_From_Patch_and_Token_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14865", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PT1InnOlfmg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval", - "base_url": null, - "title_page": null, - "repo": "penghu-cs/RONO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_RONO_Robust_Discriminative_Learning_With_Noisy_Labels_for_2D-3D_Cross-Modal_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://junwenxiong.github.io/CASP-Net/index.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_CASP-Net_Rethinking_Video_Saliency_Prediction_From_an_Audio-Visual_Consistency_Perceptual_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06357", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "keeAINxmhAM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning", - "base_url": null, - "title_page": null, - "repo": "OpenNLPLab/FNAC_AVL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Learning_Audio-Visual_Source_Localization_via_False_Negative_Aware_Contrastive_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11302", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LZprwXIn-2U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/av_hubert", - "web_page": null, - "github_page": "https://wnhsu.github.io/ReVISE/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hsu_ReVISE_Self-Supervised_Speech_Resynthesis_With_Visual_Input_for_Universal_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.11377", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Alloulah_Look_Radiate_and_Learn_Self-Supervised_Localisation_via_Radio-Visual_Correspondence_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.06424", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NUV0hm03slY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Learning Emotion Representations From Verbal and Nonverbal Communication", - "base_url": null, - "title_page": null, - "repo": "Xeaver/EmotionCLIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Learning_Emotion_Representations_From_Verbal_and_Nonverbal_Communication_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.13500", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9Mcw_xf3Dk4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Enhanced Multimodal Representation Learning With Cross-Modal KD", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Enhanced_Multimodal_Representation_Learning_With_Cross-Modal_KD_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.07646", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZTELXRN5W0M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "MELTR: Meta Loss Transformer for Learning To Fine-Tune Video Foundation Models", - "base_url": null, - "title_page": null, - "repo": "mlvlab/MELTR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ko_MELTR_Meta_Loss_Transformer_for_Learning_To_Fine-Tune_Video_Foundation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13009", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nDIKwYRf-NE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Multilateral Semantic Relations Modeling for Image Text Retrieval", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Multilateral_Semantic_Relations_Modeling_for_Image_Text_Retrieval_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "GeoVLN: Learning Geometry-Enhanced Visual Representation With Slot Attention for Vision-and-Language Navigation", - "base_url": null, - "title_page": null, - "repo": "jingyanghuo/GeoVLN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huo_GeoVLN_Learning_Geometry-Enhanced_Visual_Representation_With_Slot_Attention_for_Vision-and-Language_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.17102", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "i-WjmcNMnQI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Noisy Correspondence Learning With Meta Similarity Correction", - "base_url": null, - "title_page": null, - "repo": "hhc1997/MSCN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Han_Noisy_Correspondence_Learning_With_Meta_Similarity_Correction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.06275", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DspzqtqDgmo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Improving Cross-Modal Retrieval With Set of Diverse Embeddings", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://cvlab.postech.ac.kr/research/DivE/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Improving_Cross-Modal_Retrieval_With_Set_of_Diverse_Embeddings_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16761", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment", - "base_url": null, - "title_page": null, - "repo": "postech-ami/Sound2Scene", - "web_page": null, - "github_page": "https://sound2scene.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sung-Bin_Sound_to_Visual_Scene_Generation_by_Audio-to-Visual_Latent_Alignment_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17490", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XETgkM22n6s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "MaPLe: Multi-Modal Prompt Learning", - "base_url": null, - "title_page": null, - "repo": "muzairkhattak/multimodal-prompt-learning", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Khattak_MaPLe_Multi-Modal_Prompt_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.03117", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fmULeaqAzfg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network", - "base_url": null, - "title_page": null, - "repo": "ppanzx/CHAN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pan_Fine-Grained_Image-Text_Matching_by_Cross-Modal_Hard_Aligning_Network_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DwvSv_FATjg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Towards Modality-Agnostic Person Re-Identification With Descriptive Query", - "base_url": null, - "title_page": null, - "repo": "ccq195/UNIReID", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Towards_Modality-Agnostic_Person_Re-Identification_With_Descriptive_Query_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_nQANSa7GyA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos", - "base_url": null, - "title_page": null, - "repo": "sukun1045/video-physics-sound-diffusion", - "web_page": null, - "github_page": "https://sukun1045.github.io/video-physics-sound-diffusion/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Su_Physics-Driven_Diffusion_Models_for_Impact_Sound_Synthesis_From_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16897", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8IDssk5bWmg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training", - "base_url": null, - "title_page": null, - "repo": "hssip/FashionSAP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Han_FashionSAP_Symbols_and_Attributes_Prompt_for_Fine-Grained_Fashion_Vision-Language_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05051", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model", - "base_url": null, - "title_page": null, - "repo": "IIGROUP/MAP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ji_MAP_Multimodal_Uncertainty-Aware_Vision-Language_Pre-Training_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.05335", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XZqZDqe9MYo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Egocentric Auditory Attention Localization in Conversations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://fkryan.github.io/saal", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ryan_Egocentric_Auditory_Attention_Localization_in_Conversations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16024", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Improving Zero-Shot Generalization and Robustness of Multi-Modal Models", - "base_url": null, - "title_page": null, - "repo": "gyhandy/Hierarchy-CLIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ge_Improving_Zero-Shot_Generalization_and_Robustness_of_Multi-Modal_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.01758", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6nirYCh2xA0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_Understanding_and_Constructing_Latent_Modality_Structures_in_Multi-Modal_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05952", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kEDr2zmhe3Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles", - "base_url": null, - "title_page": null, - "repo": "pleaseconnectwifi/DANCE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ye_Improving_Commonsense_in_Vision-Language_Models_via_Knowledge_Graph_Riddles_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16504", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering", - "base_url": null, - "title_page": null, - "repo": "Galaxy922/GCFAggMVC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yan_GCFAgg_Global_and_Cross-View_Feature_Aggregation_for_Multi-View_Clustering_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.06799", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency", - "base_url": null, - "title_page": null, - "repo": "xu5zhao/BiCro", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_BiCro_Noisy_Correspondence_Rectification_for_Multi-Modality_Data_via_Bi-Directional_Cross-Modal_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12419", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training", - "base_url": null, - "title_page": null, - "repo": "IDEA-Research/DisCo-CLIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_DisCo-CLIP_A_Distributed_Contrastive_Loss_for_Memory_Efficient_CLIP_Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08480", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1MTUKnqRwC0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Referring Image Matting", - "base_url": null, - "title_page": null, - "repo": "JizhiziLi/RIM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Referring_Image_Matting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.05149", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0d9J5DD7vAY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Leveraging per Image-Token Consistency for Vision-Language Pre-Training", - "base_url": null, - "title_page": null, - "repo": "gyhdog99/epic", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gou_Leveraging_per_Image-Token_Consistency_for_Vision-Language_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15398", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Seeing What You Miss: Vision-Language Pre-Training With Semantic Completion Learning", - "base_url": null, - "title_page": null, - "repo": "iigroup/scl", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ji_Seeing_What_You_Miss_Vision-Language_Pre-Training_With_Semantic_Completion_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13437", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KXqcGfozrQw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Sample-Level Multi-View Graph Clustering", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tan_Sample-Level_Multi-View_Graph_Clustering_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation", - "base_url": null, - "title_page": null, - "repo": "RitaRamo/smallcap", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ramos_SmallCap_Lightweight_Image_Captioning_Prompted_With_Retrieval_Augmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.15323", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "On the Effects of Self-Supervision and Contrastive Alignment in Deep Multi-View Clustering", - "base_url": null, - "title_page": null, - "repo": "DanielTrosten/DeepMVC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Trosten_On_the_Effects_of_Self-Supervision_and_Contrastive_Alignment_in_Deep_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09877", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YRnOo3qs28A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_SmartBrush_Text_and_Shape_Guided_Object_Inpainting_With_Diffusion_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.05034", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kzrfcKi-XCI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Novel-View Acoustic Synthesis", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/novel-view-acoustic-synthesis", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Novel-View_Acoustic_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.08730", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5X8JdLYUA8w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "MAGVLT: Masked Generative Vision-and-Language Transformer", - "base_url": null, - "title_page": null, - "repo": "kakaobrain/magvlt", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_MAGVLT_Masked_Generative_Vision-and-Language_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12208", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8dpW-V7N3-0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Reproducible Scaling Laws for Contrastive Language-Image Learning", - "base_url": null, - "title_page": null, - "repo": "LAION-AI/scaling-laws-openclip", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cherti_Reproducible_Scaling_Laws_for_Contrastive_Language-Image_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07143", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "QFNt52y6IK4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "PMR: Prototypical Modal Rebalance for Multimodal Learning", - "base_url": null, - "title_page": null, - "repo": "fanyunfeng-bit/Modal-Imbalance-PMR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fan_PMR_Prototypical_Modal_Rebalance_for_Multimodal_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.07089", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Language-Guided Music Recommendation for Video via Prompt Analogies", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.danielbmckee.com/language-guided-music-for-video/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/McKee_Language-Guided_Music_Recommendation_for_Video_via_Prompt_Analogies_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.09327", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "z6DBTAiLKzY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_RA-CLIP_Retrieval_Augmented_Contrastive_Language-Image_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gong_MMG-Ego4D_Multimodal_Generalization_in_Egocentric_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.07214", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rZoMIkIk6Gw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Open Vocabulary Semantic Segmentation With Patch Aligned Contrastive Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mukhoti_Open_Vocabulary_Semantic_Segmentation_With_Patch_Aligned_Contrastive_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04994", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "PRISE: Demystifying Deep Lucas-Kanade With Strongly Star-Convex Constraints for Multimodel Image Alignment", - "base_url": null, - "title_page": null, - "repo": "Zhang-VISLab/CVPR2023-PRISE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_PRISE_Demystifying_Deep_Lucas-Kanade_With_Strongly_Star-Convex_Constraints_for_Multimodel_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11526", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Masked Autoencoding Does Not Help Natural Language Supervision at Scale", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Weers_Masked_Autoencoding_Does_Not_Help_Natural_Language_Supervision_at_Scale_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.07836", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "CLIPPO: Image-and-Language Understanding From Pixels Only", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/clippo/README.md", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tschannen_CLIPPO_Image-and-Language_Understanding_From_Pixels_Only_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08045", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3tTbm4_EsFU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Chat2Map: Efficient Scene Mapping From Multi-Ego Conversations", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/chat2map-official", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Majumder_Chat2Map_Efficient_Scene_Mapping_From_Multi-Ego_Conversations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02184", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Critical Learning Periods for Multisensory Integration in Deep Networks", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kleinman_Critical_Learning_Periods_for_Multisensory_Integration_in_Deep_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.04643", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pei_CLIPPING_Distilling_CLIP-Based_Models_With_a_Student_Base_for_Video-Language_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN", - "base_url": null, - "title_page": null, - "repo": "kodenii/NUWA-LIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ni_NUWA-LIP_Language-Guided_Image_Inpainting_With_Defect-Free_VQGAN_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2202.05009", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_WINNER_Weakly-Supervised_hIerarchical_decompositioN_and_aligNment_for_Spatio-tEmporal_Video_gRounding_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - }, - { - "title": "Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation", - "base_url": null, - "title_page": null, - "repo": "feiyuchen7/M3NET", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Multivariate_Multi-Frequency_and_Multimodal_Rethinking_Graph_Neural_Networks_for_Emotion_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multi-Modal Learning" - } -] \ No newline at end of file diff --git a/json_data/multimodal-learning.json b/json_data/multimodal-learning.json deleted file mode 100644 index a06b2f9..0000000 --- a/json_data/multimodal-learning.json +++ /dev/null @@ -1,2227 +0,0 @@ -[ - { - "title": "Pix2map: Cross-Modal Retrieval for Inferring Street Maps From Images", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://pix2map.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Pix2map_Cross-Modal_Retrieval_for_Inferring_Street_Maps_From_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.04224", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "18VtggvpynY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Audio-Visual Grouping Network for Sound Localization From Mixtures", - "base_url": null, - "title_page": null, - "repo": "stoneMo/AVGN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mo_Audio-Visual_Grouping_Network_for_Sound_Localization_From_Mixtures_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17056", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xMA2vOlpaHY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Learning Semantic Relationship Among Instances for Image-Text Matching", - "base_url": null, - "title_page": null, - "repo": "CrossmodalGroup/HREM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fu_Learning_Semantic_Relationship_Among_Instances_for_Image-Text_Matching_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Identity-Preserving Talking Face Generation With Landmark and Appearance Priors", - "base_url": null, - "title_page": null, - "repo": "Weizhi-Zhong/IP_LAP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhong_Identity-Preserving_Talking_Face_Generation_With_Landmark_and_Appearance_Priors_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.08293", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jpap8rLXh94", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "ImageBind: One Embedding Space To Bind Them All", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://facebookresearch.github.io/ImageBind", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Girdhar_ImageBind_One_Embedding_Space_To_Bind_Them_All_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.05665", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "X5JCEzhdkW4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Learning To Dub Movies via Hierarchical Prosody Models", - "base_url": null, - "title_page": null, - "repo": "GalaxyCong/HPMDubbing", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cong_Learning_To_Dub_Movies_via_Hierarchical_Prosody_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04054", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "OmniMAE: Single Model Masked Pretraining on Images and Videos", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/omnivore", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Girdhar_OmniMAE_Single_Model_Masked_Pretraining_on_Images_and_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.08356", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "CNVid-3.5M: Build, Filter, and Pre-Train the Large-Scale Public Chinese Video-Text Dataset", - "base_url": null, - "title_page": null, - "repo": "CNVid/CNVid-3.5M", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gan_CNVid-3.5M_Build_Filter_and_Pre-Train_the_Large-Scale_Public_Chinese_Video-Text_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ywJfAg4wvr0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Egocentric Audio-Visual Object Localization", - "base_url": null, - "title_page": null, - "repo": "WikiChao/Ego-AV-Loc", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Egocentric_Audio-Visual_Object_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13471", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0-_XJJ1JLmM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Learning Visual Representations via Language-Guided Sampling", - "base_url": null, - "title_page": null, - "repo": "mbanani/lgssl", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Banani_Learning_Visual_Representations_via_Language-Guided_Sampling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.12248", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "95I8DmUoJ2s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Unite and Conquer: Plug & Play Multi-Modal Synthesis Using Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "Nithin-GK/UniteandConquer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nair_Unite_and_Conquer_Plug__Play_Multi-Modal_Synthesis_Using_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.00793", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "iQuery: Instruments As Queries for Audio-Visual Sound Separation", - "base_url": null, - "title_page": null, - "repo": "JiabenChen/iQuery", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_iQuery_Instruments_As_Queries_for_Audio-Visual_Sound_Separation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03814", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EZ9CgknV9Z4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Diverse Embedding Expansion Network and Low-Light Cross-Modality Benchmark for Visible-Infrared Person Re-Identification", - "base_url": null, - "title_page": null, - "repo": "ZYK100/LLCM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Diverse_Embedding_Expansion_Network_and_Low-Light_Cross-Modality_Benchmark_for_Visible-Infrared_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14481", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "oMIRqc-Fq5c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "PiMAE: Point Cloud and Image Interactive Masked Autoencoders for 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "BLVLab/PiMAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_PiMAE_Point_Cloud_and_Image_Interactive_Masked_Autoencoders_for_3D_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08129", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rcs8DYAwugQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Prompt, Generate, Then Cache: Cascade of Foundation Models Makes Strong Few-Shot Learners", - "base_url": null, - "title_page": null, - "repo": "ZrrSkywalker/CaFo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Prompt_Generate_Then_Cache_Cascade_of_Foundation_Models_Makes_Strong_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.02151", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Non-Contrastive Learning Meets Language-Image Pre-Training", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Non-Contrastive_Learning_Meets_Language-Image_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.09304", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Highly Confident Local Structure Based Consensus Graph Learning for Incomplete Multi-View Clustering", - "base_url": null, - "title_page": null, - "repo": "ckghostwj/cvpr2023_code", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wen_Highly_Confident_Local_Structure_Based_Consensus_Graph_Learning_for_Incomplete_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8yaouwWf4ko", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Vision Transformers Are Parameter-Efficient Audio-Visual Learners", - "base_url": null, - "title_page": null, - "repo": "GenjiB/LAVISH", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Vision_Transformers_Are_Parameter-Efficient_Audio-Visual_Learners_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07983", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Teaching Structured Vision & Language Concepts to Vision & Language Models", - "base_url": null, - "title_page": null, - "repo": "SivanDoveh/TSVLC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Doveh_Teaching_Structured_Vision__Language_Concepts_to_Vision__Language_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11733", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "s_rr1RbX1Iw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Data-Free Sketch-Based Image Retrieval", - "base_url": null, - "title_page": null, - "repo": "abhrac/data-free-sbir", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chaudhuri_Data-Free_Sketch-Based_Image_Retrieval_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07775", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Align and Attend: Multimodal Summarization With Dual Contrastive Losses", - "base_url": null, - "title_page": null, - "repo": "boheumd/A2Summ", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Align_and_Attend_Multimodal_Summarization_With_Dual_Contrastive_Losses_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07284", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7EfdJx6G9rI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Efficient Multimodal Fusion via Interactive Prompting", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Efficient_Multimodal_Fusion_via_Interactive_Prompting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.06306", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MK_HJkgGnJ4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Multimodal Prompting With Missing Modalities for Visual Recognition", - "base_url": null, - "title_page": null, - "repo": "YiLunLee/missing_aware_prompts", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lee_Multimodal_Prompting_With_Missing_Modalities_for_Visual_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.03369", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Learning Instance-Level Representation for Large-Scale Multi-Modal Pretraining in E-Commerce", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jin_Learning_Instance-Level_Representation_for_Large-Scale_Multi-Modal_Pretraining_in_E-Commerce_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02853", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "What Happened 3 Seconds Ago? Inferring the Past With Thermal Imaging", - "base_url": null, - "title_page": null, - "repo": "ZitianTang/Thermal-IM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_What_Happened_3_Seconds_Ago_Inferring_the_Past_With_Thermal_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.13651", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RKptl-mUYQw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "MMANet: Margin-Aware Distillation and Modality-Aware Regularization for Incomplete Multimodal Learning", - "base_url": null, - "title_page": null, - "repo": "shicaiwei123/MMANet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_MMANet_Margin-Aware_Distillation_and_Modality-Aware_Regularization_for_Incomplete_Multimodal_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08028", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Multi-Modal Learning With Missing Modality via Shared-Specific Feature Modelling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Multi-Modal_Learning_With_Missing_Modality_via_Shared-Specific_Feature_Modelling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.14126", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wkYFpWOZaeg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "The ObjectFolder Benchmark: Multisensory Learning With Neural and Real Objects", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://objectfolder.stanford.edu/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_The_ObjectFolder_Benchmark_Multisensory_Learning_With_Neural_and_Real_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VhXDempUYgE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Position-Guided Text Prompt for Vision-Language Pre-Training", - "base_url": null, - "title_page": null, - "repo": "sail-sg/ptp", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Position-Guided_Text_Prompt_for_Vision-Language_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09737", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6FNXUSMefIQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Conditional Generation of Audio From Video via Foley Analogies", - "base_url": null, - "title_page": null, - "repo": "XYPB/CondFoleyGen", - "web_page": null, - "github_page": "https://xypb.github.io/CondFoleyGen/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Du_Conditional_Generation_of_Audio_From_Video_via_Foley_Analogies_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08490", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "OSAN: A One-Stage Alignment Network To Unify Multimodal Alignment and Unsupervised Domain Adaptation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_OSAN_A_One-Stage_Alignment_Network_To_Unify_Multimodal_Alignment_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "84H9dQZD3DY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Self-Supervised Video Forensics by Audio-Visual Anomaly Detection", - "base_url": null, - "title_page": null, - "repo": "cfeng16/audio-visual-forensics", - "web_page": null, - "github_page": "https://cfeng16.github.io/audio-visual-forensics/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_Self-Supervised_Video_Forensics_by_Audio-Visual_Anomaly_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.01767", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "ULIP: Learning a Unified Representation of Language, Images, and Point Clouds for 3D Understanding", - "base_url": null, - "title_page": null, - "repo": "salesforce/ULIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_ULIP_Learning_a_Unified_Representation_of_Language_Images_and_Point_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.05171", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dgFYBVmeilk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "AVFormer: Injecting Vision Into Frozen Speech Models for Zero-Shot AV-ASR", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Seo_AVFormer_Injecting_Vision_Into_Frozen_Speech_Models_for_Zero-Shot_AV-ASR_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16501", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Watch or Listen: Robust Audio-Visual Speech Recognition With Visual Corruption Modeling and Reliability Scoring", - "base_url": null, - "title_page": null, - "repo": "joannahong/AV-RelScore", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hong_Watch_or_Listen_Robust_Audio-Visual_Speech_Recognition_With_Visual_Corruption_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08536", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "SceneTrilogy: On Human Scene-Sketch and Its Complementarity With Photo and Text", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.pinakinathc.me/scenetrilogy/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chowdhury_SceneTrilogy_On_Human_Scene-Sketch_and_Its_Complementarity_With_Photo_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2204.11964", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Exploring and Exploiting Uncertainty for Incomplete Multi-View Classification", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_Exploring_and_Exploiting_Uncertainty_for_Incomplete_Multi-View_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05165", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "d124-SGH6bw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "EXIF As Language: Learning Cross-Modal Associations Between Images and Camera Metadata", - "base_url": null, - "title_page": null, - "repo": "hellomuffin/exif-as-language", - "web_page": null, - "github_page": "https://hellomuffin.github.io/exif-as-language/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zheng_EXIF_As_Language_Learning_Cross-Modal_Associations_Between_Images_and_Camera_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.04647", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dPHdNgxUXd4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Revisiting Multimodal Representation in Contrastive Learning: From Patch and Token Embeddings to Finite Discrete Tokens", - "base_url": null, - "title_page": null, - "repo": "yuxiaochen1103/FDT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Revisiting_Multimodal_Representation_in_Contrastive_Learning_From_Patch_and_Token_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14865", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PT1InnOlfmg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "RONO: Robust Discriminative Learning With Noisy Labels for 2D-3D Cross-Modal Retrieval", - "base_url": null, - "title_page": null, - "repo": "penghu-cs/RONO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_RONO_Robust_Discriminative_Learning_With_Noisy_Labels_for_2D-3D_Cross-Modal_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "CASP-Net: Rethinking Video Saliency Prediction From an Audio-Visual Consistency Perceptual Perspective", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://junwenxiong.github.io/CASP-Net/index.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_CASP-Net_Rethinking_Video_Saliency_Prediction_From_an_Audio-Visual_Consistency_Perceptual_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06357", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "keeAINxmhAM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Learning Audio-Visual Source Localization via False Negative Aware Contrastive Learning", - "base_url": null, - "title_page": null, - "repo": "OpenNLPLab/FNAC_AVL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Learning_Audio-Visual_Source_Localization_via_False_Negative_Aware_Contrastive_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11302", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LZprwXIn-2U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "ReVISE: Self-Supervised Speech Resynthesis With Visual Input for Universal and Generalized Speech Regeneration", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/av_hubert", - "web_page": null, - "github_page": "https://wnhsu.github.io/ReVISE/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hsu_ReVISE_Self-Supervised_Speech_Resynthesis_With_Visual_Input_for_Universal_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.11377", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Look, Radiate, and Learn: Self-Supervised Localisation via Radio-Visual Correspondence", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Alloulah_Look_Radiate_and_Learn_Self-Supervised_Localisation_via_Radio-Visual_Correspondence_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.06424", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NUV0hm03slY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Learning Emotion Representations From Verbal and Nonverbal Communication", - "base_url": null, - "title_page": null, - "repo": "Xeaver/EmotionCLIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Learning_Emotion_Representations_From_Verbal_and_Nonverbal_Communication_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.13500", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9Mcw_xf3Dk4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Enhanced Multimodal Representation Learning With Cross-Modal KD", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Enhanced_Multimodal_Representation_Learning_With_Cross-Modal_KD_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.07646", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZTELXRN5W0M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "MELTR: Meta Loss Transformer for Learning To Fine-Tune Video Foundation Models", - "base_url": null, - "title_page": null, - "repo": "mlvlab/MELTR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ko_MELTR_Meta_Loss_Transformer_for_Learning_To_Fine-Tune_Video_Foundation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13009", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nDIKwYRf-NE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Multilateral Semantic Relations Modeling for Image Text Retrieval", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Multilateral_Semantic_Relations_Modeling_for_Image_Text_Retrieval_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "GeoVLN: Learning Geometry-Enhanced Visual Representation With Slot Attention for Vision-and-Language Navigation", - "base_url": null, - "title_page": null, - "repo": "jingyanghuo/GeoVLN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huo_GeoVLN_Learning_Geometry-Enhanced_Visual_Representation_With_Slot_Attention_for_Vision-and-Language_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.17102", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "i-WjmcNMnQI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Noisy Correspondence Learning With Meta Similarity Correction", - "base_url": null, - "title_page": null, - "repo": "hhc1997/MSCN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Han_Noisy_Correspondence_Learning_With_Meta_Similarity_Correction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.06275", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DspzqtqDgmo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Improving Cross-Modal Retrieval With Set of Diverse Embeddings", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://cvlab.postech.ac.kr/research/DivE/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Improving_Cross-Modal_Retrieval_With_Set_of_Diverse_Embeddings_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16761", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Sound to Visual Scene Generation by Audio-to-Visual Latent Alignment", - "base_url": null, - "title_page": null, - "repo": "postech-ami/Sound2Scene", - "web_page": null, - "github_page": "https://sound2scene.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sung-Bin_Sound_to_Visual_Scene_Generation_by_Audio-to-Visual_Latent_Alignment_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17490", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XETgkM22n6s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "MaPLe: Multi-Modal Prompt Learning", - "base_url": null, - "title_page": null, - "repo": "muzairkhattak/multimodal-prompt-learning", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Khattak_MaPLe_Multi-Modal_Prompt_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.03117", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fmULeaqAzfg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Fine-Grained Image-Text Matching by Cross-Modal Hard Aligning Network", - "base_url": null, - "title_page": null, - "repo": "ppanzx/CHAN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pan_Fine-Grained_Image-Text_Matching_by_Cross-Modal_Hard_Aligning_Network_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DwvSv_FATjg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Towards Modality-Agnostic Person Re-Identification With Descriptive Query", - "base_url": null, - "title_page": null, - "repo": "ccq195/UNIReID", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Towards_Modality-Agnostic_Person_Re-Identification_With_Descriptive_Query_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_nQANSa7GyA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Physics-Driven Diffusion Models for Impact Sound Synthesis From Videos", - "base_url": null, - "title_page": null, - "repo": "sukun1045/video-physics-sound-diffusion", - "web_page": null, - "github_page": "https://sukun1045.github.io/video-physics-sound-diffusion/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Su_Physics-Driven_Diffusion_Models_for_Impact_Sound_Synthesis_From_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16897", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8IDssk5bWmg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training", - "base_url": null, - "title_page": null, - "repo": "hssip/FashionSAP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Han_FashionSAP_Symbols_and_Attributes_Prompt_for_Fine-Grained_Fashion_Vision-Language_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05051", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "MAP: Multimodal Uncertainty-Aware Vision-Language Pre-Training Model", - "base_url": null, - "title_page": null, - "repo": "IIGROUP/MAP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ji_MAP_Multimodal_Uncertainty-Aware_Vision-Language_Pre-Training_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.05335", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XZqZDqe9MYo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Egocentric Auditory Attention Localization in Conversations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://fkryan.github.io/saal", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ryan_Egocentric_Auditory_Attention_Localization_in_Conversations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16024", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Improving Zero-Shot Generalization and Robustness of Multi-Modal Models", - "base_url": null, - "title_page": null, - "repo": "gyhandy/Hierarchy-CLIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ge_Improving_Zero-Shot_Generalization_and_Robustness_of_Multi-Modal_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.01758", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6nirYCh2xA0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Understanding and Constructing Latent Modality Structures in Multi-Modal Representation Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_Understanding_and_Constructing_Latent_Modality_Structures_in_Multi-Modal_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05952", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kEDr2zmhe3Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Improving Commonsense in Vision-Language Models via Knowledge Graph Riddles", - "base_url": null, - "title_page": null, - "repo": "pleaseconnectwifi/DANCE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ye_Improving_Commonsense_in_Vision-Language_Models_via_Knowledge_Graph_Riddles_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16504", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "GCFAgg: Global and Cross-View Feature Aggregation for Multi-View Clustering", - "base_url": null, - "title_page": null, - "repo": "Galaxy922/GCFAggMVC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yan_GCFAgg_Global_and_Cross-View_Feature_Aggregation_for_Multi-View_Clustering_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.06799", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "BiCro: Noisy Correspondence Rectification for Multi-Modality Data via Bi-Directional Cross-Modal Similarity Consistency", - "base_url": null, - "title_page": null, - "repo": "xu5zhao/BiCro", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_BiCro_Noisy_Correspondence_Rectification_for_Multi-Modality_Data_via_Bi-Directional_Cross-Modal_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12419", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "DisCo-CLIP: A Distributed Contrastive Loss for Memory Efficient CLIP Training", - "base_url": null, - "title_page": null, - "repo": "IDEA-Research/DisCo-CLIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_DisCo-CLIP_A_Distributed_Contrastive_Loss_for_Memory_Efficient_CLIP_Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08480", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1MTUKnqRwC0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Referring Image Matting", - "base_url": null, - "title_page": null, - "repo": "JizhiziLi/RIM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Referring_Image_Matting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.05149", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0d9J5DD7vAY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Leveraging per Image-Token Consistency for Vision-Language Pre-Training", - "base_url": null, - "title_page": null, - "repo": "gyhdog99/epic", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gou_Leveraging_per_Image-Token_Consistency_for_Vision-Language_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15398", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Seeing What You Miss: Vision-Language Pre-Training With Semantic Completion Learning", - "base_url": null, - "title_page": null, - "repo": "iigroup/scl", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ji_Seeing_What_You_Miss_Vision-Language_Pre-Training_With_Semantic_Completion_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13437", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KXqcGfozrQw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Sample-Level Multi-View Graph Clustering", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tan_Sample-Level_Multi-View_Graph_Clustering_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "SmallCap: Lightweight Image Captioning Prompted With Retrieval Augmentation", - "base_url": null, - "title_page": null, - "repo": "RitaRamo/smallcap", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ramos_SmallCap_Lightweight_Image_Captioning_Prompted_With_Retrieval_Augmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.15323", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "On the Effects of Self-Supervision and Contrastive Alignment in Deep Multi-View Clustering", - "base_url": null, - "title_page": null, - "repo": "DanielTrosten/DeepMVC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Trosten_On_the_Effects_of_Self-Supervision_and_Contrastive_Alignment_in_Deep_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09877", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YRnOo3qs28A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "SmartBrush: Text and Shape Guided Object Inpainting With Diffusion Model", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_SmartBrush_Text_and_Shape_Guided_Object_Inpainting_With_Diffusion_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.05034", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kzrfcKi-XCI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Novel-View Acoustic Synthesis", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/novel-view-acoustic-synthesis", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Novel-View_Acoustic_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.08730", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5X8JdLYUA8w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "MAGVLT: Masked Generative Vision-and-Language Transformer", - "base_url": null, - "title_page": null, - "repo": "kakaobrain/magvlt", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_MAGVLT_Masked_Generative_Vision-and-Language_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12208", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8dpW-V7N3-0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Reproducible Scaling Laws for Contrastive Language-Image Learning", - "base_url": null, - "title_page": null, - "repo": "LAION-AI/scaling-laws-openclip", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cherti_Reproducible_Scaling_Laws_for_Contrastive_Language-Image_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07143", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "QFNt52y6IK4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "PMR: Prototypical Modal Rebalance for Multimodal Learning", - "base_url": null, - "title_page": null, - "repo": "fanyunfeng-bit/Modal-Imbalance-PMR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fan_PMR_Prototypical_Modal_Rebalance_for_Multimodal_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.07089", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Language-Guided Music Recommendation for Video via Prompt Analogies", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.danielbmckee.com/language-guided-music-for-video/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/McKee_Language-Guided_Music_Recommendation_for_Video_via_Prompt_Analogies_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.09327", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "z6DBTAiLKzY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "RA-CLIP: Retrieval Augmented Contrastive Language-Image Pre-Training", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_RA-CLIP_Retrieval_Augmented_Contrastive_Language-Image_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "MMG-Ego4D: Multimodal Generalization in Egocentric Action Recognition", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gong_MMG-Ego4D_Multimodal_Generalization_in_Egocentric_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.07214", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rZoMIkIk6Gw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Open Vocabulary Semantic Segmentation With Patch Aligned Contrastive Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mukhoti_Open_Vocabulary_Semantic_Segmentation_With_Patch_Aligned_Contrastive_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04994", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "PRISE: Demystifying Deep Lucas-Kanade With Strongly Star-Convex Constraints for Multimodel Image Alignment", - "base_url": null, - "title_page": null, - "repo": "Zhang-VISLab/CVPR2023-PRISE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_PRISE_Demystifying_Deep_Lucas-Kanade_With_Strongly_Star-Convex_Constraints_for_Multimodel_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11526", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Masked Autoencoding Does Not Help Natural Language Supervision at Scale", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Weers_Masked_Autoencoding_Does_Not_Help_Natural_Language_Supervision_at_Scale_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.07836", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "CLIPPO: Image-and-Language Understanding From Pixels Only", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://github.com/google-research/big_vision/blob/main/big_vision/configs/proj/clippo/README.md", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tschannen_CLIPPO_Image-and-Language_Understanding_From_Pixels_Only_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08045", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3tTbm4_EsFU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Chat2Map: Efficient Scene Mapping From Multi-Ego Conversations", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/chat2map-official", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Majumder_Chat2Map_Efficient_Scene_Mapping_From_Multi-Ego_Conversations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02184", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Critical Learning Periods for Multisensory Integration in Deep Networks", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kleinman_Critical_Learning_Periods_for_Multisensory_Integration_in_Deep_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.04643", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "CLIPPING: Distilling CLIP-Based Models With a Student Base for Video-Language Retrieval", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pei_CLIPPING_Distilling_CLIP-Based_Models_With_a_Student_Base_for_Video-Language_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "NUWA-LIP: Language-Guided Image Inpainting With Defect-Free VQGAN", - "base_url": null, - "title_page": null, - "repo": "kodenii/NUWA-LIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ni_NUWA-LIP_Language-Guided_Image_Inpainting_With_Defect-Free_VQGAN_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2202.05009", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "WINNER: Weakly-Supervised hIerarchical decompositioN and aligNment for Spatio-tEmporal Video gRounding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_WINNER_Weakly-Supervised_hIerarchical_decompositioN_and_aligNment_for_Spatio-tEmporal_Video_gRounding_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - }, - { - "title": "Multivariate, Multi-Frequency and Multimodal: Rethinking Graph Neural Networks for Emotion Recognition in Conversation", - "base_url": null, - "title_page": null, - "repo": "feiyuchen7/M3NET", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Multivariate_Multi-Frequency_and_Multimodal_Rethinking_Graph_Neural_Networks_for_Emotion_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Multimodal Learning" - } -] \ No newline at end of file diff --git a/json_data/navigation-and-autonomous-driving.json b/json_data/navigation-and-autonomous-driving.json deleted file mode 100644 index 0987d15..0000000 --- a/json_data/navigation-and-autonomous-driving.json +++ /dev/null @@ -1,1727 +0,0 @@ -[ - { - "title": "GraVoS: Voxel Selection for 3D Point-Cloud Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shrout_GraVoS_Voxel_Selection_for_3D_Point-Cloud_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.08780", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8rVLxIT-2wQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "BEV@DC: Bird's-Eye View Assisted Training for Depth Completion", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_BEVDC_Birds-Eye_View_Assisted_Training_for_Depth_Completion_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IvhaqXL1NNY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Are we Ready for Vision-Centric Driving Streaming Perception? The ASAP Benchmark", - "base_url": null, - "title_page": null, - "repo": "JeffWang987/ASAP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Are_We_Ready_for_Vision-Centric_Driving_Streaming_Perception_The_ASAP_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.08914", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YjNkmvm83ww", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "PVT-SSD: Single-Stage 3D Object Detector with Point-Voxel Transformer", - "base_url": null, - "title_page": null, - "repo": "Nightmare-n/PVT-SSD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_PVT-SSD_Single-Stage_3D_Object_Detector_With_Point-Voxel_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.06621", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "J1FVUpmW9JA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "End-to-End Vectorized HD-Map Construction with Piecewise Bezier Curve", - "base_url": null, - "title_page": null, - "repo": "er-muyue/BeMapNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qiao_End-to-End_Vectorized_HD-Map_Construction_With_Piecewise_Bezier_Curve_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.09700", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "MoDAR: Using Motion Forecasting for 3D Object Detection in Point Cloud Sequences", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_MoDAR_Using_Motion_Forecasting_for_3D_Object_Detection_in_Point_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.03206", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xIPWjmGzaqU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "LaserMix for Semi-Supervised LiDAR Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "ldkong1205/LaserMix", - "web_page": "https://ldkong.com/LaserMix", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kong_LaserMix_for_Semi-Supervised_LiDAR_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.00026", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7-zvIHKqkl0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "MSMDFusion: Fusing LiDAR and Camera at Multiple Scales with Multi-Depth Seeds for 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "SxJyJay/MSMDFusion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiao_MSMDFusion_Fusing_LiDAR_and_Camera_at_Multiple_Scales_With_Multi-Depth_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.03102", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5mkacK_wsqY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "LiDAR2Map: In Defense of LiDAR-based Semantic Map Construction using Online Camera Distillation", - "base_url": null, - "title_page": null, - "repo": "songw-zju/LiDAR2Map", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_LiDAR2Map_In_Defense_of_LiDAR-Based_Semantic_Map_Construction_Using_Online_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11379", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nr25xFZbx8U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Think Twice Before Driving: Towards Scalable Decoders for End-to-End Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "OpenDriveLab/ThinkTwice", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jia_Think_Twice_Before_Driving_Towards_Scalable_Decoders_for_End-to-End_Autonomous_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.06242", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Planning-Oriented Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "OpenDriveLab/UniAD", - "web_page": null, - "github_page": "https://opendrivelab.github.io/UniAD/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Planning-Oriented_Autonomous_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.10156", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "R4iuq3zDBL4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Distilling Focal Knowledge from Imperfect Expert for 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "OpenDriveLab/Birds-eye-view-Perception", - "web_page": null, - "github_page": "https://github.com/OpenDriveLab/Birds-eye-view-Perception/blob/master/nuScenes_playground/FocalDistiller/README.md", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zeng_Distilling_Focal_Knowledge_From_Imperfect_Expert_for_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Np9_pEzleG4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Anchor3DLane: Learning to Regress 3D Anchors for Monocular 3D Lane Detection", - "base_url": null, - "title_page": null, - "repo": "tusen-ai/Anchor3DLane", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Anchor3DLane_Learning_To_Regress_3D_Anchors_for_Monocular_3D_Lane_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02371", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5ceKZ6q5TVc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "SliceMatch: Geometry-Guided Aggregation for Cross-View Pose Estimation", - "base_url": null, - "title_page": null, - "repo": "tudelft-iv/SliceMatch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lentsch_SliceMatch_Geometry-Guided_Aggregation_for_Cross-View_Pose_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14651", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gql1dkQQNrA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Azimuth Super-Resolution for FMCW Radar in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "yujheli/Pitt-Radar", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Azimuth_Super-Resolution_for_FMCW_Radar_in_Autonomous_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "V2V4Real: A Real-World Large-Scale Dataset for Vehicle-to-Vehicle Cooperative Perception", - "base_url": null, - "title_page": null, - "repo": "ucla-mobility/V2V4Real", - "web_page": "https://mobility-lab.seas.ucla.edu/v2v4real/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_V2V4Real_A_Real-World_Large-Scale_Dataset_for_Vehicle-to-Vehicle_Cooperative_Perception_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07601", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "67N0epSAvRA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Implicit Occupancy Flow Fields for Perception and Prediction in Self-Driving", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/implicito/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Agro_Implicit_Occupancy_Flow_Fields_for_Perception_and_Prediction_in_Self-Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2308.01471", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Coaching a Teachable Student", - "base_url": null, - "title_page": null, - "repo": "h2xlab/CaT", - "web_page": null, - "github_page": "https://catdrive.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Coaching_a_Teachable_Student_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.10014", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5tmkDHfgqvU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "BEV-SAN: Accurate BEV 3D Object Detection via Slice Attention Networks", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chi_BEV-SAN_Accurate_BEV_3D_Object_Detection_via_Slice_Attention_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.01231", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UYGZoi490GI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Center Focusing Network for Real-Time LiDAR Panoptic Segmentation", - "base_url": null, - "title_page": null, - "repo": "gangzhang842/cfnet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Center_Focusing_Network_for_Real-Time_LiDAR_Panoptic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2311.09499", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LHaQhrVysDo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "IPCC-TP: Utilizing Incremental Pearson Correlation Coefficient for Joint Multi-Agent Trajectory Prediction", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_IPCC-TP_Utilizing_Incremental_Pearson_Correlation_Coefficient_for_Joint_Multi-Agent_Trajectory_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00575", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0eQUiil3AXs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Weakly Supervised Monocular 3D Object Detection using Multi-View Projection and Direction Consistency", - "base_url": null, - "title_page": null, - "repo": "weakmono3d/weakmono3d", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tao_Weakly_Supervised_Monocular_3D_Object_Detection_Using_Multi-View_Projection_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08686", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AXBa5Rn58j4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "CXTrack: Improving 3D Point Cloud Tracking with Contextual Information", - "base_url": null, - "title_page": null, - "repo": "slothfulxtx/cxtrack3d", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_CXTrack_Improving_3D_Point_Cloud_Tracking_With_Contextual_Information_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.08542", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9CbtQt4umws", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "ReasonNet: End-to-End Driving with Temporal and Global Reasoning", - "base_url": null, - "title_page": null, - "repo": "opendilab/DOS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shao_ReasonNet_End-to-End_Driving_With_Temporal_and_Global_Reasoning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.10507", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "59wCGdrHGE4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Seeing with Sound: Long-Range Acoustic Beamforming for Multimodal Scene Understanding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://light.princeton.edu/publication/seeingwithsound/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chakravarthula_Seeing_With_Sound_Long-range_Acoustic_Beamforming_for_Multimodal_Scene_Understanding_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "N5QinjRhKYQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "LinK: Linear Kernel for LiDAR-based 3D Perception", - "base_url": null, - "title_page": null, - "repo": "MCG-NJU/LinK", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_LinK_Linear_Kernel_for_LiDAR-Based_3D_Perception_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16094", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UM2W7rHE6V4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Understanding the Robustness of 3D Object Detection with Bird's-Eye-View Representations in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "zzj403/BEV_Robust", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_Understanding_the_Robustness_of_3D_Object_Detection_With_Birds-Eye-View_Representations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17297", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TqoR7gwzTXQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Tri-Perspective View for Vision-based 3D Semantic Occupancy Prediction", - "base_url": null, - "title_page": null, - "repo": "wzzheng/TPVFormer", - "web_page": "https://wzzheng.net/TPVFormer/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Tri-Perspective_View_for_Vision-Based_3D_Semantic_Occupancy_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.07817", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XWVNn0_6iJg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "SkyEye: Self-Supervised Bird's-Eye-View Semantic Mapping using Monocular Frontal View Images", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "http://skyeye.cs.uni-freiburg.de/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gosala_SkyEye_Self-Supervised_Birds-Eye-View_Semantic_Mapping_Using_Monocular_Frontal_View_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.04233", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PGne5XG4f_8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "BEV-LaneDet: An Efficient 3D Lane Detection based on Virtual Camera via Key-Points", - "base_url": null, - "title_page": null, - "repo": "gigo-team/bev_lane_det", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_BEV-LaneDet_An_Efficient_3D_Lane_Detection_Based_on_Virtual_Camera_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.06006", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "OcTr: Octree-based Transformer for 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_OcTr_Octree-Based_Transformer_for_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12621", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NgCI8s7Kh8M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Instant Domain Augmentation for LiDAR Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "kwonyoung9120/LiDomAug", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ryu_Instant_Domain_Augmentation_for_LiDAR_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14378", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tnheIfyQkqc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "ViP3D: End-to-End Visual Trajectory Prediction via 3D Agent Queries", - "base_url": null, - "title_page": null, - "repo": "Tsinghua-MARS-Lab/ViP3D", - "web_page": null, - "github_page": "https://tsinghua-mars-lab.github.io/ViP3D/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gu_ViP3D_End-to-End_Visual_Trajectory_Prediction_via_3D_Agent_Queries_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.01582", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1apYGKgeWdc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "UniSim: A Neural Closed-Loop Sensor Simulator", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/unisim/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_UniSim_A_Neural_Closed-Loop_Sensor_Simulator_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2308.01898", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3OwjE1Mv_3I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Learning Compact Representations for LiDAR Completion and Generation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/ultralidar/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_Learning_Compact_Representations_for_LiDAR_Completion_and_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2311.01448", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CWOfT3Wrxh4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Towards Unsupervised Object Detection from LiDAR Point Clouds", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/research/oyster", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Towards_Unsupervised_Object_Detection_From_LiDAR_Point_Clouds_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2311.02007", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gUQZmIhCxVM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Standing Between Past and Future: Spatio-Temporal Modeling for Multi-Camera 3D Multi-Object Tracking", - "base_url": null, - "title_page": null, - "repo": "TRI-ML/PF-Track", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pang_Standing_Between_Past_and_Future_Spatio-Temporal_Modeling_for_Multi-Camera_3D_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.03802", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AP46BbkJ7vY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Benchmarking Robustness of 3D Object Detection to Common Corruptions in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "thu-ml/3D_Corruptions_AD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dong_Benchmarking_Robustness_of_3D_Object_Detection_to_Common_Corruptions_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11040", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xIRQhg3I1-A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "X3KD: Knowledge Distillation Across Modalities, Tasks and Stages for Multi-Camera 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Klingner_X3KD_Knowledge_Distillation_Across_Modalities_Tasks_and_Stages_for_Multi-Camera_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.02203", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1do9DPFmr38", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "PeakConv: Learning Peak Receptive Field for Radar Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "zlw9161/PKC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_PeakConv_Learning_Peak_Receptive_Field_for_Radar_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "GD-MAE: Generative Decoder for MAE Pre-Training on LiDAR Point Clouds", - "base_url": null, - "title_page": null, - "repo": "Nightmare-n/GD-MAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_GD-MAE_Generative_Decoder_for_MAE_Pre-Training_on_LiDAR_Point_Clouds_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03010", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "k8JE6CDjyng", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Neural Map Prior for Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "Tsinghua-MARS-Lab/neural_map_prior", - "web_page": null, - "github_page": "https://tsinghua-mars-lab.github.io/neural_map_prior/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_Neural_Map_Prior_for_Autonomous_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08481", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "FpzxaBVw3L0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Lift3D: Synthesize 3D Training Data by Lifting 2D GAN to 3D Generative Radiance Field", - "base_url": null, - "title_page": null, - "repo": "Len-Li/Lift3D", - "web_page": null, - "github_page": "https://len-li.github.io/lift3d-web/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Lift3D_Synthesize_3D_Training_Data_by_Lifting_2D_GAN_to_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03526", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Continuous Pseudo-Label Rectified Domain Adaptive Semantic Segmentation with Implicit Neural Representations", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gong_Continuous_Pseudo-Label_Rectified_Domain_Adaptive_Semantic_Segmentation_With_Implicit_Neural_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Single Domain Generalization for LiDAR Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "gzgzys9887/DGLSS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Single_Domain_Generalization_for_LiDAR_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XUe-N3p5btc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Uncertainty-Aware Vision-based Metric Cross-View Geolocalization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://fferflo.github.io/projects/vismetcvgl23/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fervers_Uncertainty-Aware_Vision-Based_Metric_Cross-View_Geolocalization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12145", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1vHFiA0prL0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "MixSim: A Hierarchical Framework for Mixed Reality Traffic Simulation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://waabi.ai/mixsim/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Suo_MixSim_A_Hierarchical_Framework_for_Mixed_Reality_Traffic_Simulation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "PillarNeXt: Rethinking Network Designs for 3D Object Detection in LiDAR Point Clouds", - "base_url": null, - "title_page": null, - "repo": "qcraftai/pillarnext", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_PillarNeXt_Rethinking_Network_Designs_for_3D_Object_Detection_in_LiDAR_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.04925", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zdMSqNvi-KM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Uni3D: A Unified Baseline for Multi-Dataset 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "PJLab-ADG/3DTrans", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Uni3D_A_Unified_Baseline_for_Multi-Dataset_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06880", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "CAPE: Camera View Position Embedding for Multi-View 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "kaixinbear/CAPE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiong_CAPE_Camera_View_Position_Embedding_for_Multi-View_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10209", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "LiDAR-in-the-Loop Hyperparameter Optimization", - "base_url": null, - "title_page": null, - "repo": "princeton-computational-imaging/LITL-Optimization", - "web_page": "https://light.princeton.edu/publication/lidar-in-the-loop-hyperparameter-optimization/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Goudreault_LiDAR-in-the-Loop_Hyperparameter_Optimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8IjqoctJgOs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Bi3D: Bi-Domain Active Learning for Cross-Domain 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "PJLab-ADG/3DTrans", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yuan_Bi3D_Bi-Domain_Active_Learning_for_Cross-Domain_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05886", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "FEND: A Future Enhanced Distribution-Aware Contrastive Learning Framework for Long-Tail Trajectory Prediction", - "base_url": null, - "title_page": null, - "repo": "ynw2021/FEND", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_FEND_A_Future_Enhanced_Distribution-Aware_Contrastive_Learning_Framework_for_Long-Tail_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16574", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "31Put0T54qI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Temporal Consistent 3D LiDAR Representation Learning for Semantic Perception in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "PRBonn/TARL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nunes_Temporal_Consistent_3D_LiDAR_Representation_Learning_for_Semantic_Perception_in_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0CtDbwRYLeo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Density-Insensitive Unsupervised Domain Adaption on 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "WoodwindHu/DTS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Density-Insensitive_Unsupervised_Domain_Adaption_on_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.09446", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Zb020nG6sD0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "SGLoc: Scene Geometry Encoding for Outdoor LiDAR Localization", - "base_url": null, - "title_page": null, - "repo": "liw95/SGLoc", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_SGLoc_Scene_Geometry_Encoding_for_Outdoor_LiDAR_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Tek6yA20N7M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "TBP-Former: Learning Temporal Bird's-Eye-View Pyramid for Joint Perception and Prediction in Vision-Centric Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "MediaBrain-SJTU/TBP-Former", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fang_TBP-Former_Learning_Temporal_Birds-Eye-View_Pyramid_for_Joint_Perception_and_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09998", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RlS2rDlaM9w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Localized Semantic Feature Mixers for Efficient Pedestrian Detection in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Khan_Localized_Semantic_Feature_Mixers_for_Efficient_Pedestrian_Detection_in_Autonomous_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4jSlqKnTemw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Deep Dive Into Gradients: Better Optimization for 3D Object Detection with Gradient-Corrected IoU Supervision", - "base_url": null, - "title_page": null, - "repo": "ming71/GCIoU-loss", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ming_Deep_Dive_Into_Gradients_Better_Optimization_for_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "ProphNet: Efficient Agent-Centric Motion Forecasting with Anchor-Informed Proposals", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_ProphNet_Efficient_Agent-Centric_Motion_Forecasting_With_Anchor-Informed_Proposals_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12071", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "BEVHeight: A Robust Framework for Vision-based Roadside 3D Object Detection", - "base_url": null, - "title_page": null, - "repo": "ADLab-AutoDrive/BEVHeight", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_BEVHeight_A_Robust_Framework_for_Vision-Based_Roadside_3D_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08498", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "W-y-MIrdXQc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "VoxFormer: Sparse Voxel Transformer for Camera-based 3D Semantic Scene Completion", - "base_url": null, - "title_page": null, - "repo": "NVlabs/VoxFormer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_VoxFormer_Sparse_Voxel_Transformer_for_Camera-Based_3D_Semantic_Scene_Completion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.12251", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "L0M9ayR316g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Hidden Gems: 4D Radar Scene Flow Learning using Cross-Modal Supervision", - "base_url": null, - "title_page": null, - "repo": "Toytiny/CMFlow", - "web_page": null, - "github_page": "https://toytiny.github.io/publication/23-cmflow-cvpr/index.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ding_Hidden_Gems_4D_Radar_Scene_Flow_Learning_Using_Cross-Modal_Supervision_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00462", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hHgzBhy6NVQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Self-Supervised Image-to-Point Distillation via Semantically Tolerant Contrastive Loss", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mahmoud_Self-Supervised_Image-to-Point_Distillation_via_Semantically_Tolerant_Contrastive_Loss_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.05709", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Query-Centric Trajectory Prediction", - "base_url": null, - "title_page": null, - "repo": "ZikangZhou/QCNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Query-Centric_Trajectory_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "i46Sj0PUwyI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Efficient Hierarchical Entropy Model for Learned Point Cloud Compression", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Song_Efficient_Hierarchical_Entropy_Model_for_Learned_Point_Cloud_Compression_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MSnZRJ94CM8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "Novel Class Discovery for 3D Point Cloud Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "LuigiRiz/NOPS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Riz_Novel_Class_Discovery_for_3D_Point_Cloud_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11610", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kRp1F-_emj8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "MotionDiffuser: Controllable Multi-Agent Motion Prediction using Diffusion", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_MotionDiffuser_Controllable_Multi-Agent_Motion_Prediction_Using_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.03083", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IfGTZwm1abg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - }, - { - "title": "FJMP: Factorized Joint Multi-Agent Motion Prediction Over Learned Directed Acyclic Interaction Graphs", - "base_url": null, - "title_page": null, - "repo": "RLuke22/FJMP", - "web_page": null, - "github_page": "https://rluke22.github.io/FJMP/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rowe_FJMP_Factorized_Joint_Multi-Agent_Motion_Prediction_Over_Learned_Directed_Acyclic_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16197", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "asmCOhPQuNw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Navigation and Autonomous Driving" - } -] \ No newline at end of file diff --git a/json_data/optimization-methods-other-than-deep-learning.json b/json_data/optimization-methods-other-than-deep-learning.json deleted file mode 100644 index e8cacb7..0000000 --- a/json_data/optimization-methods-other-than-deep-learning.json +++ /dev/null @@ -1,302 +0,0 @@ -[ - { - "title": "Pose Synchronization under Multiple Pair-Wise Relative Poses", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Pose_Synchronization_Under_Multiple_Pair-Wise_Relative_Poses_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vo0DGKuyoKk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "Adaptive Global Decay Process for Event Cameras", - "base_url": null, - "title_page": null, - "repo": "neuromorphic-paris/event_batch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nunes_Adaptive_Global_Decay_Process_for_Event_Cameras_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "Wide-Angle Rectification via Content-Aware Conformal Mapping", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Wide-Angle_Rectification_via_Content-Aware_Conformal_Mapping_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NninwkQJVQ4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "On the Convergence of IRLS and its Variants in Outlier-Robust Estimation", - "base_url": null, - "title_page": null, - "repo": "liangzu/IRLS-CVPR2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Peng_On_the_Convergence_of_IRLS_and_Its_Variants_in_Outlier-Robust_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "eGsksvd13vU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "A General Regret Bound of Preconditioned Gradient Method for DNN Training", - "base_url": null, - "title_page": null, - "repo": "Yonghongwei/AdaBK", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yong_A_General_Regret_Bound_of_Preconditioned_Gradient_Method_for_DNN_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "Robust and Scalable Gaussian Process Regression and its Applications", - "base_url": null, - "title_page": null, - "repo": "YifanLu2000/Robust-Scalable-GPR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_Robust_and_Scalable_Gaussian_Process_Regression_and_Its_Applications_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mYGugBSJugk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "EMT-NAS: Transferring Architectural Knowledge between Tasks from Different Datasets", - "base_url": null, - "title_page": null, - "repo": "PengLiao12/EMT-NAS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liao_EMT-NASTransferring_Architectural_Knowledge_Between_Tasks_From_Different_Datasets_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "Transformer-based Learned Optimization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gartner_Transformer-Based_Learned_Optimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.01055", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jt_B5nN4CO8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "Efficient Robust Principal Component Analysis via Block Krylov Iteration and CUR Decomposition", - "base_url": null, - "title_page": null, - "repo": "Crrrrrayon/efficient_RPCA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fang_Efficient_Robust_Principal_Component_Analysis_via_Block_Krylov_Iteration_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "m5_YV3cqHbk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "Solving Relaxations of MAP-MRF Problems: Combinatorial In-Face Frank-Wolfe Directions", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://pub.ista.ac.at/~vnk/papers/IN-FACE-FW.html", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kolmogorov_Solving_Relaxations_of_MAP-MRF_Problems_Combinatorial_In-Face_Frank-Wolfe_Directions_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2010.09567", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "Robust Generalization Against Photon-Limited Corruptions via Worst-Case Sharpness Minimization", - "base_url": null, - "title_page": null, - "repo": "zhuohuangai/SharpDRO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Robust_Generalization_Against_Photon-Limited_Corruptions_via_Worst-Case_Sharpness_Minimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13087", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dlKW_IMAKfE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - }, - { - "title": "Elastic Aggregation for Federated Optimization", - "base_url": null, - "title_page": null, - "repo": "alibaba/Elastic-Federated-Learning-Solution", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Elastic_Aggregation_for_Federated_Optimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UacxoH1tF0k", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Optimization Methods (other than Deep Learning)" - } -] \ No newline at end of file diff --git a/json_data/others.json b/json_data/others.json deleted file mode 100644 index 8798e39..0000000 --- a/json_data/others.json +++ /dev/null @@ -1,302 +0,0 @@ -[ - { - "title": "A Bag-of-Prototypes Representation for Dataset-Level Applications", - "base_url": null, - "title_page": null, - "repo": "Klaus-Tu/Bag-of-Prototypes", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tu_A_Bag-of-Prototypes_Representation_for_Dataset-Level_Applications_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13251", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kSB0GO9pEYE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "Learning to Retain While Acquiring: Combating Distribution-Shift in Adversarial Data-Free Knowledge Distillation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Patel_Learning_To_Retain_While_Acquiring_Combating_Distribution-Shift_in_Adversarial_Data-Free_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14290", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VwEKrqMym4k", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "Label Information Bottleneck for Label Enhancement", - "base_url": null, - "title_page": null, - "repo": "qinghai-zheng/LIBLE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Label_Information_Bottleneck_for_Label_Enhancement_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06836", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YGWGU3m4whc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "DISC: Learning from Noisy Labels via Dynamic Instance-Specific Selection and Correction", - "base_url": null, - "title_page": null, - "repo": "JackYFL/DISC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_DISC_Learning_From_Noisy_Labels_via_Dynamic_Instance-Specific_Selection_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YGWGU3m4whc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "Restoration of Hand-Drawn Architectural Drawings using Latent Space Mapping with Degradation Generator", - "base_url": null, - "title_page": null, - "repo": "Nakkwan/pytorch-Restoration-Floorplan", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Choi_Restoration_of_Hand-Drawn_Architectural_Drawings_Using_Latent_Space_Mapping_With_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "DaFKD: Domain-Aware Federated Knowledge Distillation", - "base_url": null, - "title_page": null, - "repo": "haozhaowang/DaFKD2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_DaFKD_Domain-Aware_Federated_Knowledge_Distillation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NxmLN6uWUBA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "Enhanced Stable View Synthesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://suryanshkumar.github.io/Enhanced_Stable_View_Synthesis/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jain_Enhanced_Stable_View_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17094", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CZW6HLDQRD4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "ScaleFL: Resource-Adaptive Federated Learning with Heterogeneous Clients", - "base_url": null, - "title_page": null, - "repo": "git-disl/scale-fl", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ilhan_ScaleFL_Resource-Adaptive_Federated_Learning_With_Heterogeneous_Clients_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "GradMA: A Gradient-Memory-based Accelerated Federated Learning with Alleviated Catastrophic Forgetting", - "base_url": null, - "title_page": null, - "repo": "lkyddd/GradMA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_GradMA_A_Gradient-Memory-Based_Accelerated_Federated_Learning_With_Alleviated_Catastrophic_Forgetting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14307", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kzZH_5eSsZ4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "High-Resolution Image Reconstruction with Latent Diffusion Models from Human Brain Activity", - "base_url": null, - "title_page": null, - "repo": "yu-takagi/StableDiffusionReconstruction", - "web_page": "https://sites.google.com/view/stablediffusion-with-brain/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Takagi_High-Resolution_Image_Reconstruction_With_Latent_Diffusion_Models_From_Human_Brain_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "A Unified Knowledge Distillation Framework for Deep Directed Graphical Models", - "base_url": null, - "title_page": null, - "repo": "YizhuoChen99/KD4DGM-CVPR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_A_Unified_Knowledge_Distillation_Framework_for_Deep_Directed_Graphical_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - }, - { - "title": "How to Prevent the Poor Performance Clients for Personalized Federated Learning?", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qu_How_To_Prevent_the_Poor_Performance_Clients_for_Personalized_Federated_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Others" - } -] \ No newline at end of file diff --git a/json_data/photogrammetry-and-remote-sensing.json b/json_data/photogrammetry-and-remote-sensing.json deleted file mode 100644 index 9dd2aca..0000000 --- a/json_data/photogrammetry-and-remote-sensing.json +++ /dev/null @@ -1,202 +0,0 @@ -[ - { - "title": "MethaneMapper: Spectral Absorption Aware Hyperspectral Transformer for Methane Detection", - "base_url": null, - "title_page": null, - "repo": "UCSB-VRL/MethaneMapper-Spectral-Absorption-aware-Hyperspectral-Transformer-for-Methane-Detection", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kumar_MethaneMapper_Spectral_Absorption_Aware_Hyperspectral_Transformer_for_Methane_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02767", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "N_faP8AWhBQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Photogrammetry and Remote Sensing" - }, - { - "title": "Probability-based Global Cross-Modal Upsampling for Pansharpening", - "base_url": null, - "title_page": null, - "repo": "Zeyu-Zhu/PGCU", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_Probability-Based_Global_Cross-Modal_Upsampling_for_Pansharpening_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13659", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Photogrammetry and Remote Sensing" - }, - { - "title": "Learning Correspondence Uncertainty via Differentiable Nonlinear Least Squares", - "base_url": null, - "title_page": null, - "repo": "DominikMuhle/dnls_covs", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Muhle_Learning_Correspondence_Uncertainty_via_Differentiable_Nonlinear_Least_Squares_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.09527", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_wDUresP6v8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Photogrammetry and Remote Sensing" - }, - { - "title": "Dynamic Coarse-to-Fine Learning for Oriented Tiny Object Detection", - "base_url": null, - "title_page": null, - "repo": "Chasel-Tsui/mmrotate-dcfl", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Dynamic_Coarse-To-Fine_Learning_for_Oriented_Tiny_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08876", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "diic4cEKbtw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Photogrammetry and Remote Sensing" - }, - { - "title": "ViTs for SITS: Vision Transformers for Satellite Image Time Series", - "base_url": null, - "title_page": null, - "repo": "michaeltrs/DeepSatModels", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tarasiou_ViTs_for_SITS_Vision_Transformers_for_Satellite_Image_Time_Series_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.04944", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "u1bjplvB7Vk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Photogrammetry and Remote Sensing" - }, - { - "title": "Quantum-Inspired Spectral-Spatial Pyramid Network for Hyperspectral Image Classification", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Quantum-Inspired_Spectral-Spatial_Pyramid_Network_for_Hyperspectral_Image_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Photogrammetry and Remote Sensing" - }, - { - "title": "TopDiG: Class-Agnostic Topological Directional Graph Extraction from Remote Sensing Images", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_TopDiG_Class-Agnostic_Topological_Directional_Graph_Extraction_From_Remote_Sensing_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "B2lJcBjaJAA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Photogrammetry and Remote Sensing" - }, - { - "title": "OmniCity: Omnipotent City Understanding with Multi-Level and Multi-View Images", - "base_url": null, - "title_page": null, - "repo": "sysu-lwj-lab/OmniCity-v1.0", - "web_page": null, - "github_page": "https://city-super.github.io/omnicity/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_OmniCity_Omnipotent_City_Understanding_With_Multi-Level_and_Multi-View_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.00928", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-lrFgcyyCHQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Photogrammetry and Remote Sensing" - } -] \ No newline at end of file diff --git a/json_data/physics-based-vision-and-shape-from-x.json b/json_data/physics-based-vision-and-shape-from-x.json deleted file mode 100644 index 199d5f0..0000000 --- a/json_data/physics-based-vision-and-shape-from-x.json +++ /dev/null @@ -1,302 +0,0 @@ -[ - { - "title": "Learning Anchor Transformations for 3D Garment Animation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://semanticdh.github.io/AnchorDEF/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Learning_Anchor_Transformations_for_3D_Garment_Animation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00761", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "High-Fidelity Event-Radiance Recovery via Transient Event Frequency", - "base_url": null, - "title_page": null, - "repo": "hjynwa/TEF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Han_High-Fidelity_Event-Radiance_Recovery_via_Transient_Event_Frequency_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wf138eAoazE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "Complementary Intrinsics from Neural Radiance Fields and CNNs for Outdoor Scene Relighting", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Complementary_Intrinsics_From_Neural_Radiance_Fields_and_CNNs_for_Outdoor_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "88DIFRZlPDE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "Fresnel Microfacet BRDF: Unification of Polari-Radiometric Surface-Body Reflection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ichikawa_Fresnel_Microfacet_BRDF_Unification_of_Polari-Radiometric_Surface-Body_Reflection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04483", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "BYyDM-6s3Jc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "Event-based Shape from Polarization", - "base_url": null, - "title_page": null, - "repo": "uzh-rpg/esfp", - "web_page": "https://rpg.ifi.uzh.ch/esfp.html", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Muglikar_Event-Based_Shape_From_Polarization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.06855", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "sF3Ue2Zkpec", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "Weakly-Supervised Single-View Image Relighting", - "base_url": null, - "title_page": null, - "repo": "renjiaoyi/imagerelighting", - "web_page": null, - "github_page": "https://renjiaoyi.github.io/relighting/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yi_Weakly-Supervised_Single-View_Image_Relighting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13852", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LetskpBfOjM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "DANI-Net: Uncalibrated Photometric Stereo by Differentiable Shadow Handling, Anisotropic Reflectance Modeling, and Neural Inverse Rendering", - "base_url": null, - "title_page": null, - "repo": "LMozart/CVPR2023-DANI-Net", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_DANI-Net_Uncalibrated_Photometric_Stereo_by_Differentiable_Shadow_Handling_Anisotropic_Reflectance_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15101", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4HSLZi7bfPA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "Learning Accurate 3D Shape based on Stereo Polarimetric Imaging", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://tyhuang98.github.io/learn_stereo_sfp/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Learning_Accurate_3D_Shape_Based_on_Stereo_Polarimetric_Imaging_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "Visibility Constrained Wide-Band Illumination Spectrum Design for Seeing-in-the-Dark", - "base_url": null, - "title_page": null, - "repo": "MyNiuuu/VCSD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Niu_Visibility_Constrained_Wide-Band_Illumination_Spectrum_Design_for_Seeing-in-the-Dark_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11642", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "M91Ag6vW9nw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "Light Source Separation and Intrinsic Image Decomposition Under AC Illumination", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yoshida_Light_Source_Separation_and_Intrinsic_Image_Decomposition_Under_AC_Illumination_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "v8TjCzoI97s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "OReX: Object Reconstruction from Planar Cross-Sections using Neural Fields", - "base_url": null, - "title_page": null, - "repo": "haimsaw/OReX", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sawdayee_OReX_Object_Reconstruction_From_Planar_Cross-Sections_Using_Neural_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12886", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2IZKlqUZK4Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - }, - { - "title": "Unsupervised Intrinsic Image Decomposition with LiDAR Intensity", - "base_url": null, - "title_page": null, - "repo": "ntthilab-cv/NTT-intrinsic-dataset", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sato_Unsupervised_Intrinsic_Image_Decomposition_With_LiDAR_Intensity_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10820", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AoNh79glieU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Physics-based Vision and Shape-from-X" - } -] \ No newline at end of file diff --git a/json_data/robotics.json b/json_data/robotics.json deleted file mode 100644 index 6ca02df..0000000 --- a/json_data/robotics.json +++ /dev/null @@ -1,577 +0,0 @@ -[ - { - "title": "Object-Goal Visual Navigation via Effective Exploration of Relations among Historical Navigation States", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Du_Object-Goal_Visual_Navigation_via_Effective_Exploration_of_Relations_Among_Historical_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "TTA-COPE: Test-Time Adaptation for Category-Level Object Pose Estimation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://sites.google.com/view/taeyeop-lee/ttacope", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lee_TTA-COPE_Test-Time_Adaptation_for_Category-Level_Object_Pose_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16730", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MUgQ0yithis", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Meta-Explore: Exploratory Hierarchical Vision-and-Language Navigation using Scene Object Spectrum Grounding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://rllab-snu.github.io/projects/Meta-Explore/doc.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hwang_Meta-Explore_Exploratory_Hierarchical_Vision-and-Language_Navigation_Using_Scene_Object_Spectrum_Grounding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.04077", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nxWUedX5VpQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Learning Human-to-Robot Handovers from Point Clouds", - "base_url": null, - "title_page": null, - "repo": "NVlabs/handover-sim2real", - "web_page": null, - "github_page": "https://handover-sim2real.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Christen_Learning_Human-to-Robot_Handovers_From_Point_Clouds_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17592", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IsjCdoIAA7s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Robot Structure Prior Guided Temporal Attention for Camera-to-Robot Pose Estimation from Image Sequence", - "base_url": null, - "title_page": null, - "repo": "Nimolty/SGTAPose", - "web_page": "https://sites.google.com/view/sgtapose", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tian_Robot_Structure_Prior_Guided_Temporal_Attention_for_Camera-to-Robot_Pose_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.12106", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5fQp-yBubZs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "PartManip: Learning Cross-Category Generalizable Part Manipulation Policy from Point Cloud Observations", - "base_url": null, - "title_page": null, - "repo": "PKU-EPIC/PartManip", - "web_page": null, - "github_page": "https://pku-epic.github.io/PartManip/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Geng_PartManip_Learning_Cross-Category_Generalizable_Part_Manipulation_Policy_From_Point_Cloud_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16958", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "k0LbcO1B-ac", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "DexArt: Benchmarking Generalizable Dexterous Manipulation with Articulated Objects", - "base_url": null, - "title_page": null, - "repo": "Kami-code/dexart-release", - "web_page": "https://www.chenbao.tech/dexart/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bao_DexArt_Benchmarking_Generalizable_Dexterous_Manipulation_With_Articulated_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.05706", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "V_EYQJO1W_U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "PyPose: A Library for Robot Learning with Physics-based Optimization", - "base_url": null, - "title_page": null, - "repo": "pypose/pypose", - "web_page": "https://pypose.org/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_PyPose_A_Library_for_Robot_Learning_With_Physics-Based_Optimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.15428", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XDtUDIWuGng", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Target-Referenced Reactive Grasping for Dynamic Objects", - "base_url": null, - "title_page": null, - "repo": "Todibo99/Target-referenced-Reactive-Grasping-for-Dynamic-Objects", - "web_page": "https://graspnet.net/reactive", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Target-Referenced_Reactive_Grasping_for_Dynamic_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Autonomous Manipulation Learning for Similar Deformable Objects via only One Demonstration", - "base_url": null, - "title_page": null, - "repo": "renyu2016/DLCDO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ren_Autonomous_Manipulation_Learning_for_Similar_Deformable_Objects_via_Only_One_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Y0FD0ihdEN0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Renderable Neural Radiance Map for Visual Navigation", - "base_url": null, - "title_page": null, - "repo": "rllab-snu/RNR-Map", - "web_page": null, - "github_page": "https://rllab-snu.github.io/projects/RNR-Map/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kwon_Renderable_Neural_Radiance_Map_for_Visual_Navigation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00304", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1SF8_6BsA1c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Efficient Map Sparsification based on 2D and 3D Discretized Grids", - "base_url": null, - "title_page": null, - "repo": "fishmarch/SLAM_Map_Compression", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Efficient_Map_Sparsification_Based_on_2D_and_3D_Discretized_Grids_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10882", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gG1nFddFf-s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Policy Adaptation from Foundation Model Feedback", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://geyuying.github.io/PAFF/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ge_Policy_Adaptation_From_Foundation_Model_Feedback_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07398", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5IZkbUFB2cM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "NeRF in the Palm of Your Hand: Corrective Augmentation for Robotics via Novel-View Synthesis", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://bland.website/spartn/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_NeRF_in_the_Palm_of_Your_Hand_Corrective_Augmentation_for_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.08556", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Markerless Camera-to-Robot Pose Estimation via Self-Supervised Sim-to-Real Transfer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_Markerless_Camera-to-Robot_Pose_Estimation_via_Self-Supervised_Sim-to-Real_Transfer_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14332", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Affordances from Human Videos as a Versatile Representation for Robotics", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://vision-robotics-bridge.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bahl_Affordances_From_Human_Videos_as_a_Versatile_Representation_for_Robotics_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08488", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WdMYGESu8Ak", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "DeepMapping2: Self-Supervised Large-Scale LiDAR Map Optimization", - "base_url": null, - "title_page": null, - "repo": "ai4ce/DeepMapping2", - "web_page": null, - "github_page": "https://ai4ce.github.io/DeepMapping2/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_DeepMapping2_Self-Supervised_Large-Scale_LiDAR_Map_Optimization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06331", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2NJ81JwY48o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "GrowSP: Unsupervised Semantic Segmentation of 3D Point Clouds", - "base_url": null, - "title_page": null, - "repo": "vLAR-group/GrowSP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_GrowSP_Unsupervised_Semantic_Segmentation_of_3D_Point_Clouds_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.16404", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "x_UW7hU3Ows", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Neural Volumetric Memory for Visual Locomotion Control", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://rchalyang.github.io/NVM/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Neural_Volumetric_Memory_for_Visual_Locomotion_Control_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.01201", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vJdt610GSGk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Multi-Object Manipulation via Object-Centric Neural Scattering Functions", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://s-tian.github.io/projects/actionosf/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tian_Multi-Object_Manipulation_via_Object-Centric_Neural_Scattering_Functions_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.08748", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yRZ2YVJHhGY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Local-Guided Global: Paired Similarity Representation for Visual Reinforcement Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Choi_Local-Guided_Global_Paired_Similarity_Representation_for_Visual_Reinforcement_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "HypLiLoc: Towards Effective LiDAR Pose Regression with Hyperbolic Fusion", - "base_url": null, - "title_page": null, - "repo": "sijieaaa/HypLiLoc", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_HypLiLoc_Towards_Effective_LiDAR_Pose_Regression_With_Hyperbolic_Fusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00932", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "d8FMbENBmBA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - }, - { - "title": "Imitation Learning as State Matching via Differentiable Physics", - "base_url": null, - "title_page": null, - "repo": "sail-sg/ILD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Imitation_Learning_As_State_Matching_via_Differentiable_Physics_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6iNFJHPO8Hc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Robotics" - } -] \ No newline at end of file diff --git a/json_data/scene-analysis-and-understanding.json b/json_data/scene-analysis-and-understanding.json deleted file mode 100644 index 7faf3da..0000000 --- a/json_data/scene-analysis-and-understanding.json +++ /dev/null @@ -1,1352 +0,0 @@ -[ - { - "title": "You Only Segment Once: Towards Real-Time Panoptic Segmentation", - "base_url": null, - "title_page": null, - "repo": "hujiecpp/YOSO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_You_Only_Segment_Once_Towards_Real-Time_Panoptic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14651", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wQCKerE_NmQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "IS-GGT: Iterative Scene Graph Generation with Generative Transformers", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://saakur.github.io/Projects/IS_GGT/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kundu_IS-GGT_Iterative_Scene_Graph_Generation_With_Generative_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CZ9aCrqgY9E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Disentangling Orthogonal Planes for Indoor Panoramic Room Layout Estimation with Cross-Scale Distortion Awareness", - "base_url": null, - "title_page": null, - "repo": "zhijieshen-bjtu/DOPNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shen_Disentangling_Orthogonal_Planes_for_Indoor_Panoramic_Room_Layout_Estimation_With_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00971", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Panoptic Video Scene Graph Generation", - "base_url": null, - "title_page": null, - "repo": "LilyDaytoy/OpenPVSG", - "web_page": null, - "github_page": "https://jingkang50.github.io/PVSG/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Panoptic_Video_Scene_Graph_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2311.17058", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZvKeIZ8LHVw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "3D Spatial Multimodal Knowledge Accumulation for Scene Graph Prediction in Point Cloud", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_3D_Spatial_Multimodal_Knowledge_Accumulation_for_Scene_Graph_Prediction_in_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "srvsnfCZTQI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "JacobiNeRF: NeRF Shaping with Mutual Information Gradients", - "base_url": null, - "title_page": null, - "repo": "xxm19/jacobinerf", - "web_page": null, - "github_page": "https://xxm19.github.io/jnerf/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_JacobiNeRF_NeRF_Shaping_With_Mutual_Information_Gradients_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00341", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "uKU9UdVL6GQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Learning Geometric-Aware Properties in 2D Representation using Lightweight CAD Models, or Zero Real 3D Pairs", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://geoaware2drepusingcad.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Arsomngern_Learning_Geometric-Aware_Properties_in_2D_Representation_Using_Lightweight_CAD_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nTb1RC9T-0I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Learning and Aggregating Lane Graphs for Urban Automated Driving", - "base_url": null, - "title_page": null, - "repo": "jzuern/lanegnn", - "web_page": "http://urbanlanegraph.cs.uni-freiburg.de/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Buchner_Learning_and_Aggregating_Lane_Graphs_for_Urban_Automated_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.06175", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zHkbF_pjfdg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "MIME: Human-Aware 3D Scene Generation", - "base_url": null, - "title_page": null, - "repo": "yhw-yhw/MIME", - "web_page": "https://mime.is.tue.mpg.de/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yi_MIME_Human-Aware_3D_Scene_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04360", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Connecting the Dots: Floorplan Reconstruction using Two-Level Queries", - "base_url": null, - "title_page": null, - "repo": "ywyue/RoomFormer", - "web_page": null, - "github_page": "https://ywyue.github.io/RoomFormer/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yue_Connecting_the_Dots_Floorplan_Reconstruction_Using_Two-Level_Queries_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15658", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yzYe4yVN1NU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "NeRF-RPN: A General Framework for Object Detection in NeRFs", - "base_url": null, - "title_page": null, - "repo": "lyclyc52/NeRF_RPN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_NeRF-RPN_A_General_Framework_for_Object_Detection_in_NeRFs_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11646", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "M8_4Ih1CJjE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Relational Context Learning for Human-Object Interaction Detection", - "base_url": null, - "title_page": null, - "repo": "OreoChocolate/MUREN", - "web_page": "https://cvlab.postech.ac.kr/research/MUREN/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Relational_Context_Learning_for_Human-Object_Interaction_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04997", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "u-5EmiGWbsA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Symmetric Shape-Preserving Autoencoder for Unsupervised Real Scene Point Cloud Completion", - "base_url": null, - "title_page": null, - "repo": "murcherful/USSPA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ma_Symmetric_Shape-Preserving_Autoencoder_for_Unsupervised_Real_Scene_Point_Cloud_Completion_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1iWvKcR9DzA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Token Contrast for Weakly-Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "rulixiang/ToCo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ru_Token_Contrast_for_Weakly-Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01267", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "MM-3DScene: 3D Scene Understanding by Customizing Masked Modeling with Informative-Preserved Reconstruction and Self-Distilled Consistency", - "base_url": null, - "title_page": null, - "repo": "MingyeXu/mm-3dscene", - "web_page": null, - "github_page": "https://mingyexu.github.io/mm3dscene/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_MM-3DScene_3D_Scene_Understanding_by_Customizing_Masked_Modeling_With_Informative-Preserved_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09948", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MxRJG9EUR5Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Primitive Generation and Semantic-related Alignment for Universal Zero-Shot Segmentation", - "base_url": null, - "title_page": null, - "repo": "heshuting555/PADing", - "web_page": null, - "github_page": "https://henghuiding.github.io/PADing/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Primitive_Generation_and_Semantic-Related_Alignment_for_Universal_Zero-Shot_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.11087", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yZp-i7ZgU_M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "CLIP2Scene: Towards Label-Efficient 3D Scene Understanding by CLIP", - "base_url": null, - "title_page": null, - "repo": "runnanchen/CLIP2Scene", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_CLIP2Scene_Towards_Label-Efficient_3D_Scene_Understanding_by_CLIP_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.04926", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OT6AvAVlNNs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Multispectral Video Semantic Segmentation: A Benchmark Dataset and Baseline", - "base_url": null, - "title_page": null, - "repo": "jiwei0921/MVSS-Baseline", - "web_page": null, - "github_page": "https://jiwei0921.github.io/Multispectral-Video-Semantic-Segmentation/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ji_Multispectral_Video_Semantic_Segmentation_A_Benchmark_Dataset_and_Baseline_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Optimal Transport Minimization: Crowd Localization on Density Maps for Semi-Supervised Counting", - "base_url": null, - "title_page": null, - "repo": "Elin24/OT-M", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Optimal_Transport_Minimization_Crowd_Localization_on_Density_Maps_for_Semi-Supervised_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "415yW0YBC0I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Indiscernible Object Counting in Underwater Scenes", - "base_url": null, - "title_page": null, - "repo": "GuoleiSun/Indiscernible-Object-Counting", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Indiscernible_Object_Counting_in_Underwater_Scenes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11677", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3-XRKmGh154", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Long Range Pooling for 3D Large-Scale Scene Understanding", - "base_url": null, - "title_page": null, - "repo": "Visual-Attention-Network/LRPNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Long_Range_Pooling_for_3D_Large-Scale_Scene_Understanding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.06962", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Delivering Arbitrary-Modal Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "jamycheung/DELIVER", - "web_page": null, - "github_page": "https://jamycheung.github.io/DELIVER.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Delivering_Arbitrary-Modal_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01480", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "X-VeSLsEToA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Images Speak in Images: A Generalist Painter for In-Context Visual Learning", - "base_url": null, - "title_page": null, - "repo": "baaivision/Painter", - "web_page": null, - "github_page": "https://github.com/baaivision/Painter/tree/main/Painter", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Images_Speak_in_Images_A_Generalist_Painter_for_In-Context_Visual_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.02499", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "SCPNet: Semantic Scene Completion on Point Cloud", - "base_url": null, - "title_page": null, - "repo": "SCPNet/Codes-for-SCPNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xia_SCPNet_Semantic_Scene_Completion_on_Point_Cloud_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06884", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "X2mHXxPM5hg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Content-Aware Token Sharing for Efficient Semantic Segmentation with Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "tue-mps/cts-segmenter", - "web_page": null, - "github_page": "https://tue-mps.github.io/CTS/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_Content-Aware_Token_Sharing_for_Efficient_Semantic_Segmentation_With_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.02095", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "omkEFGBmcqI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "OpenScene: 3D Scene Understanding with Open Vocabularies", - "base_url": null, - "title_page": null, - "repo": "pengsongyou/openscene", - "web_page": null, - "github_page": "https://pengsongyou.github.io/openscene", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Peng_OpenScene_3D_Scene_Understanding_With_Open_Vocabularies_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15654", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jZxCLHyDJf8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Devil's on the Edges: Selective Quad Attention for Scene Graph Generation", - "base_url": null, - "title_page": null, - "repo": "hesedjds/SQUAT", - "web_page": "https://cvlab.postech.ac.kr/research/SQUAT/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jung_Devils_on_the_Edges_Selective_Quad_Attention_for_Scene_Graph_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03495", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jwYNS1EM6v4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Delving into Shape-Aware Zero-Shot Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "Liuxinyv/SAZS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Delving_Into_Shape-Aware_Zero-Shot_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08491", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PxQ4hzGETZQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Category Query Learning for Human-Object Interaction Classification", - "base_url": null, - "title_page": null, - "repo": "Charles-Xie/CQL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_Category_Query_Learning_for_Human-Object_Interaction_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14005", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UbV5wtOs4DM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Nerflets: Local Radiance Fields for Efficient Structure-Aware 3D Scene Representation from 2D Supervision", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://jetd1.github.io/nerflets-web/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Nerflets_Local_Radiance_Fields_for_Efficient_Structure-Aware_3D_Scene_Representation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.03361", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rfPVNXVV_Ns", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "DejaVu: Conditional Regenerative Learning to Enhance Dense Prediction", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Borse_DejaVu_Conditional_Regenerative_Learning_To_Enhance_Dense_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01573", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "SCOOP: Self-Supervised Correspondence and Optimization-based Scene Flow", - "base_url": null, - "title_page": null, - "repo": "itailang/SCOOP", - "web_page": null, - "github_page": "https://itailang.github.io/SCOOP/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lang_SCOOP_Self-Supervised_Correspondence_and_Optimization-Based_Scene_Flow_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14020", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "b8MVWGU7V4E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Incremental 3D Semantic Scene Graph Prediction from RGB Sequences", - "base_url": null, - "title_page": null, - "repo": "ShunChengWu/MonoSSG", - "web_page": null, - "github_page": "https://shunchengwu.github.io/MonoSSG", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Incremental_3D_Semantic_Scene_Graph_Prediction_From_RGB_Sequences_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.02743", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2uALwmw6WbU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "PanelNet: Understanding 360 Indoor Environment via Panel Representation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_PanelNet_Understanding_360_Indoor_Environment_via_Panel_Representation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.09078", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "urGHusgV8Z4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Perspective Fields for Single Image Camera Calibration", - "base_url": null, - "title_page": null, - "repo": "jinlinyi/PerspectiveFields", - "web_page": null, - "github_page": "https://jinlinyi.github.io/PerspectiveFields/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jin_Perspective_Fields_for_Single_Image_Camera_Calibration_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03239", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "sN5B_ZvMva8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Open-Category Human-Object Interaction Pre-Training via Language Modeling Framework", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zheng_Open-Category_Human-Object_Interaction_Pre-Training_via_Language_Modeling_Framework_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Fast Contextual Scene Graph Generation with Unbiased Context Augmentation", - "base_url": null, - "title_page": null, - "repo": "moshuilanting/fast-context-scene-graph-generation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jin_Fast_Contextual_Scene_Graph_Generation_With_Unbiased_Context_Augmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Diffusion-based Generation, Optimization, and Planning in 3D Scenes", - "base_url": null, - "title_page": null, - "repo": "scenediffuser/Scene-Diffuser", - "web_page": null, - "github_page": "https://scenediffuser.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Diffusion-Based_Generation_Optimization_and_Planning_in_3D_Scenes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.06015", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "a0SSprBoVV4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "TopNet: Transformer-based Object Placement Network for Image Compositing", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_TopNet_Transformer-Based_Object_Placement_Network_for_Image_Compositing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03372", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KbcnGFeg-V8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Computational Flash Photography through Intrinsics", - "base_url": null, - "title_page": null, - "repo": "compphoto/IntrinsicFlashPhotography", - "web_page": null, - "github_page": "https://yaksoy.github.io/intrinsicFlash/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Maralan_Computational_Flash_Photography_Through_Intrinsics_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.06089", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Zs23PKgJCO8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Probing Neural Representations of Scene Perception in a Hippocampally Dependent Task using Artificial Neural Networks", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Frey_Probing_Neural_Representations_of_Scene_Perception_in_a_Hippocampally_Dependent_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06367", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "DeepSolo: Let Transformer Decoder with Explicit Points Solo for Text Spotting", - "base_url": null, - "title_page": null, - "repo": "ViTAE-Transformer/DeepSolo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ye_DeepSolo_Let_Transformer_Decoder_With_Explicit_Points_Solo_for_Text_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10772", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "LEGO-Net: Learning Regular Rearrangements of Objects in Rooms", - "base_url": null, - "title_page": null, - "repo": "QiuhongAnnaWei/LEGO-Net", - "web_page": "https://ivl.cs.brown.edu/research/lego-net.html", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_LEGO-Net_Learning_Regular_Rearrangements_of_Objects_in_Rooms_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.09629", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Wzy7wdyc4cI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Open-Vocabulary Point-Cloud Object Detection without 3D Annotation", - "base_url": null, - "title_page": null, - "repo": "lyhdet/OV-3DET", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_Open-Vocabulary_Point-Cloud_Object_Detection_Without_3D_Annotation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00788", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-rUBCX4sHII", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Weakly-Supervised Domain Adaptive Semantic Segmentation with Prototypical Contrastive Learning", - "base_url": null, - "title_page": null, - "repo": "anurag-198/WDASS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Das_Weakly-Supervised_Domain_Adaptive_Semantic_Segmentation_With_Prototypical_Contrastive_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Arg8p0Zrf9A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "ScanDMM: A Deep Markov Model of Scanpath Prediction for 360° Images", - "base_url": null, - "title_page": null, - "repo": "xiangjieSui/ScanDMM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sui_ScanDMM_A_Deep_Markov_Model_of_Scanpath_Prediction_for_360deg_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "noXCcFvXY2k", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Canonical Fields: Self-Supervised Learning of Pose-Canonicalized Neural Fields", - "base_url": null, - "title_page": null, - "repo": "brown-ivl/Cafi-Net", - "web_page": "https://ivl.cs.brown.edu/research/canonical-fields.html", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Agaram_Canonical_Fields_Self-Supervised_Learning_of_Pose-Canonicalized_Neural_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.02493", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vKHbky6Wcxk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "TempSAL - Uncovering Temporal Information for Deep Saliency Prediction", - "base_url": null, - "title_page": null, - "repo": "IVRL/Tempsal", - "web_page": null, - "github_page": "https://ivrl.github.io/Tempsal/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Aydemir_TempSAL_-_Uncovering_Temporal_Information_for_Deep_Saliency_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02315", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1CrgRjzfjFQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Probabilistic Debiasing of Scene Graphs", - "base_url": null, - "title_page": null, - "repo": "bashirulazam/within-triplet-debias", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Biswas_Probabilistic_Debiasing_of_Scene_Graphs_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.06444", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4tDAW0D1YE4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Towards Unified Scene Text Spotting based on Sequence Generation", - "base_url": null, - "title_page": null, - "repo": "clovaai/units", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kil_Towards_Unified_Scene_Text_Spotting_Based_on_Sequence_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03435", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Learning to Generate Language-Supervised and Open-Vocabulary Scene Graph using Pre-trained Visual-Semantic Space", - "base_url": null, - "title_page": null, - "repo": "zyong812/VS3_CVPR23", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Learning_To_Generate_Language-Supervised_and_Open-Vocabulary_Scene_Graph_Using_Pre-Trained_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jWTxcHC6ccQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Modular Memorability: Tiered Representations for Video Memorability Prediction", - "base_url": null, - "title_page": null, - "repo": "theodumont/modular-memorability", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dumont_Modular_Memorability_Tiered_Representations_for_Video_Memorability_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1ysNNMHQb1o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "Where we are and what we're Looking at: Query based Worldwide Image Geo-Localization using Hierarchies and Scenes", - "base_url": null, - "title_page": null, - "repo": "AHKerrigan/GeoGuessNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Clark_Where_We_Are_and_What_Were_Looking_At_Query_Based_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.04249", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fp3hZGbwPqk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - }, - { - "title": "HRDFuse: Monocular 360° Depth Estimation by Collaboratively Learning Holistic-with-Regional Depth Distributions", - "base_url": null, - "title_page": null, - "repo": "haoai-1997/HRDFuse", - "web_page": null, - "github_page": "https://vlis2022.github.io/HRDFuse/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ai_HRDFuse_Monocular_360deg_Depth_Estimation_by_Collaboratively_Learning_Holistic-With-Regional_Depth_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11616", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Qgxdar_MdIc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Scene Analysis and Understanding" - } -] \ No newline at end of file diff --git a/json_data/segmentation-grouping-and-shape-analysis.json b/json_data/segmentation-grouping-and-shape-analysis.json deleted file mode 100644 index c451d33..0000000 --- a/json_data/segmentation-grouping-and-shape-analysis.json +++ /dev/null @@ -1,2777 +0,0 @@ -[ - { - "title": "Efficient Semantic Segmentation by Altering Resolutions for Compressed Videos", - "base_url": null, - "title_page": null, - "repo": "THU-LYJ-Lab/AR-Seg", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_Efficient_Semantic_Segmentation_by_Altering_Resolutions_for_Compressed_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07224", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WN9ok0xd0po", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Vision Transformers Are Good Mask Auto-Labelers", - "base_url": null, - "title_page": null, - "repo": "NVlabs/mask-auto-labeler", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lan_Vision_Transformers_Are_Good_Mask_Auto-Labelers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.03992", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "n9cmRYzKNVc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Visual Recognition by Request", - "base_url": null, - "title_page": null, - "repo": "chufengt/Visual-Recognition-by-Request", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Visual_Recognition_by_Request_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.14227", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0wuVwYPcSQg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Ultra-High Resolution Segmentation With Ultra-Rich Context: A Novel Benchmark", - "base_url": null, - "title_page": null, - "repo": "jankyee/URUR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ji_Ultra-High_Resolution_Segmentation_With_Ultra-Rich_Context_A_Novel_Benchmark_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.10899", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "AttentionShift: Iteratively Estimated Part-Based Attention Map for Pointly Supervised Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": "MingXiangL/AttentionShift", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liao_AttentionShift_Iteratively_Estimated_Part-Based_Attention_Map_for_Pointly_Supervised_Instance_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "MDQE: Mining Discriminative Query Embeddings To Segment Occluded Instances on Challenging Videos", - "base_url": null, - "title_page": null, - "repo": "MinghanLi/MDQE_CVPR2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_MDQE_Mining_Discriminative_Query_Embeddings_To_Segment_Occluded_Instances_on_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14395", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "cK1SvHJgYYc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Look Before You Match: Instance Understanding Matters in Video Object Segmentation", - "base_url": null, - "title_page": null, - "repo": "suhwan-cho/awesome-video-object-segmentation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Look_Before_You_Match_Instance_Understanding_Matters_in_Video_Object_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06826", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Sd7iS5Icf30", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "SIM: Semantic-Aware Instance Mask Generation for Box-Supervised Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": "lslrh/SIM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_SIM_Semantic-Aware_Instance_Mask_Generation_for_Box-Supervised_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08578", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "EFEM: Equivariant Neural Field Expectation Maximization for 3D Object Segmentation Without Scene Supervision", - "base_url": null, - "title_page": null, - "repo": "JiahuiLei/EFEM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lei_EFEM_Equivariant_Neural_Field_Expectation_Maximization_for_3D_Object_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15440", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "chPX8_iUxEw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Camouflaged Object Detection With Feature Decomposition and Edge Reconstruction", - "base_url": null, - "title_page": null, - "repo": "ChunmingHe/FEDER", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Camouflaged_Object_Detection_With_Feature_Decomposition_and_Edge_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "LOCATE: Localize and Transfer Object Parts for Weakly Supervised Affordance Grounding", - "base_url": null, - "title_page": null, - "repo": "Reagan1311/LOCATE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_LOCATE_Localize_and_Transfer_Object_Parts_for_Weakly_Supervised_Affordance_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09665", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RLHansdFxII", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "OneFormer: One Transformer To Rule Universal Image Segmentation", - "base_url": null, - "title_page": null, - "repo": "SHI-Labs/OneFormer", - "web_page": null, - "github_page": "https://praeclarumjj3.github.io/oneformer/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jain_OneFormer_One_Transformer_To_Rule_Universal_Image_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.06220", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CIU3udcaoW4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Mask-Free Video Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": "SysCV/MaskFreeVIS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ke_Mask-Free_Video_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15904", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7P7PX3gd14I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Less Is More: Reducing Task and Model Complexity for 3D Point Cloud Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "l1997i/lim3d", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Less_Is_More_Reducing_Task_and_Model_Complexity_for_3D_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11203", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5f-waFfjsOY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "InstMove: Instance Motion for Object-Centric Video Segmentation", - "base_url": null, - "title_page": null, - "repo": "wjf5203/VNext", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_InstMove_Instance_Motion_for_Object-Centric_Video_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08132", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GzH8hLteEIY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "The Devil Is in the Points: Weakly Semi-Supervised Instance Segmentation via Point-Guided Mask Representation", - "base_url": null, - "title_page": null, - "repo": "clovaai/PointWSSIS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_The_Devil_Is_in_the_Points_Weakly_Semi-Supervised_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15062", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "iGlDjXFO6TY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Edge-Aware Regional Message Passing Controller for Image Forgery Localization", - "base_url": null, - "title_page": null, - "repo": "greatzh/Papers", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Edge-Aware_Regional_Message_Passing_Controller_for_Image_Forgery_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2pDR-hOFcQw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Interactive Segmentation As Gaussion Process Classification", - "base_url": null, - "title_page": null, - "repo": "zmhhmz/GPCIS_CVPR2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Interactive_Segmentation_As_Gaussion_Process_Classification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14578", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mapyH-WujhY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Semantic-Promoted Debiasing and Background Disambiguation for Zero-Shot Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": "heshuting555/D2Zero", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Semantic-Promoted_Debiasing_and_Background_Disambiguation_for_Zero-Shot_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.13173", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-Wci6cJAyRE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Adversarially Masking Synthetic To Mimic Real: Adaptive Noise Injection for Point Cloud Segmentation Adaptation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.guangrui.li/projects/ASM", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Adversarially_Masking_Synthetic_To_Mimic_Real_Adaptive_Noise_Injection_for_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "L0z2SOw2Yvg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Generative Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "fudan-zvg/GSS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Generative_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11316", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bw5z5RU91ps", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Modeling the Distributional Uncertainty for Salient Object Detection Models", - "base_url": null, - "title_page": null, - "repo": "txynwpu/Distributional_uncertainty_SOD", - "web_page": null, - "github_page": "https://npucvr.github.io/Distributional_uncer/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tian_Modeling_the_Distributional_Uncertainty_for_Salient_Object_Detection_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4S5tWc2uMKo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Simultaneously Short- and Long-Term Temporal Modeling for Semi-Supervised Video Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lao_Simultaneously_Short-_and_Long-Term_Temporal_Modeling_for_Semi-Supervised_Video_Semantic_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OqkRQJoh4d0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Out-of-Candidate Rectification for Weakly Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "sennnnn/Out-of-Candidate-Rectification", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cheng_Out-of-Candidate_Rectification_for_Weakly_Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12268", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JQajrSReXkU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "DynaMask: Dynamic Mask Selection for Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_DynaMask_Dynamic_Mask_Selection_for_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07868", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "MSeg3D: Multi-Modal 3D Semantic Segmentation for Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "jialeli1/lidarseg3d", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_MSeg3D_Multi-Modal_3D_Semantic_Segmentation_for_Autonomous_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08600", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "lRLxOfHrfmI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Generalizable Local Feature Pre-Training for Deformable Shape Analysis", - "base_url": null, - "title_page": null, - "repo": "pvnieo/vader", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Attaiki_Generalizable_Local_Feature_Pre-Training_for_Deformable_Shape_Analysis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15104", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Understanding and Improving Features Learned in Deep Functional Maps", - "base_url": null, - "title_page": null, - "repo": "pvnieo/clover", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Attaiki_Understanding_and_Improving_Features_Learned_in_Deep_Functional_Maps_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16527", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "G-MSM: Unsupervised Multi-Shape Matching With Graph-Based Affinity Priors", - "base_url": null, - "title_page": null, - "repo": "marvin-eisenberger/gmsm-matching", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Eisenberger_G-MSM_Unsupervised_Multi-Shape_Matching_With_Graph-Based_Affinity_Priors_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.02910", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vEE9gQ6RFoU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Continual Semantic Segmentation With Automatic Memory Sample Selection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_Continual_Semantic_Segmentation_With_Automatic_Memory_Sample_Selection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05015", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Bcrh9_76PTY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "FreeSeg: Unified, Universal and Open-Vocabulary Image Segmentation", - "base_url": null, - "title_page": null, - "repo": "bytedance/FreeSeg", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qin_FreeSeg_Unified_Universal_and_Open-Vocabulary_Image_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17225", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Object Discovery From Motion-Guided Tokens", - "base_url": null, - "title_page": null, - "repo": "zpbao/MoTok", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bao_Object_Discovery_From_Motion-Guided_Tokens_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15555", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VgTrLMQIdgg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Efficient Mask Correction for Click-Based Interactive Image Segmentation", - "base_url": null, - "title_page": null, - "repo": "feiaxyt/EMC-Click", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Du_Efficient_Mask_Correction_for_Click-Based_Interactive_Image_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Balancing Logit Variation for Long-Tailed Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "grantword8/BLV", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Balancing_Logit_Variation_for_Long-Tailed_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.02061", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Fuzzy Positive Learning for Semi-Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qiao_Fuzzy_Positive_Learning_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.08519", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PVZRs1E2pWI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Learning Open-Vocabulary Semantic Segmentation Models From Natural Language Supervision", - "base_url": null, - "title_page": null, - "repo": "Jazzcharles/OVSegmentor", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Learning_Open-Vocabulary_Semantic_Segmentation_Models_From_Natural_Language_Supervision_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.09121", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "j4FSgpEP4XM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Improving Graph Representation for Point Cloud Segmentation via Attentive Filtering", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Improving_Graph_Representation_for_Point_Cloud_Segmentation_via_Attentive_Filtering_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "BUOL: A Bottom-Up Framework With Occupancy-Aware Lifting for Panoptic 3D Scene Reconstruction From a Single Image", - "base_url": null, - "title_page": null, - "repo": "chtsy/buol", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chu_BUOL_A_Bottom-Up_Framework_With_Occupancy-Aware_Lifting_for_Panoptic_3D_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.00965", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "pOZq5YbtBww", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://lkhl.github.io/ACSeg/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_ACSeg_Adaptive_Conceptualization_for_Unsupervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.05944", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "CCuantuMM: Cycle-Consistent Quantum-Hybrid Matching of Multiple Shapes", - "base_url": null, - "title_page": null, - "repo": "HarshilBhatia/CCuantuMM", - "web_page": null, - "github_page": "https://4dqv.mpi-inf.mpg.de/CCuantuMM/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bhatia_CCuantuMM_Cycle-Consistent_Quantum-Hybrid_Matching_of_Multiple_Shapes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16202", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gwBhXkJ5W3k", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Hierarchical Dense Correlation Distillation for Few-Shot Segmentation", - "base_url": null, - "title_page": null, - "repo": "Pbihao/HDMNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Peng_Hierarchical_Dense_Correlation_Distillation_for_Few-Shot_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14652", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nFYTxfngUY0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "UniDAformer: Unified Domain Adaptive Panoptic Segmentation Transformer via Hierarchical Mask Calibration", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_UniDAformer_Unified_Domain_Adaptive_Panoptic_Segmentation_Transformer_via_Hierarchical_Mask_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.15083", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1k3bSwyaPEw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "FedSeg: Class-Heterogeneous Federated Learning for Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Miao_FedSeg_Class-Heterogeneous_Federated_Learning_for_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "v834xUST26c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Understanding Imbalanced Semantic Segmentation Through Neural Collapse", - "base_url": null, - "title_page": null, - "repo": "NeuralCollapseApplications/Semantic-Segmentation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhong_Understanding_Imbalanced_Semantic_Segmentation_Through_Neural_Collapse_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.01100", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0ZMfyRY5zjE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Revisiting Weak-to-Strong Consistency in Semi-Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "LiheYoung/UniMatch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Revisiting_Weak-to-Strong_Consistency_in_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.09910", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "PartSLIP: Low-Shot Part Segmentation for 3D Point Clouds via Pretrained Image-Language Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://colin97.github.io/PartSLIP_page/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_PartSLIP_Low-Shot_Part_Segmentation_for_3D_Point_Clouds_via_Pretrained_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.01558", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "VGORtR2mJog", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "PartDistillation: Learning Parts From Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/PartDistillation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cho_PartDistillation_Learning_Parts_From_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "5T5Z0F1J8oY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Sketch2Saliency: Learning To Detect Salient Objects From Human Drawings", - "base_url": null, - "title_page": null, - "repo": "AyanKumarBhunia/Sketch2Saliency", - "web_page": null, - "github_page": "https://ayankumarbhunia.github.io/Sketch2Saliency/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bhunia_Sketch2Saliency_Learning_To_Detect_Salient_Objects_From_Human_Drawings_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11502", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IsbE365ByYI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "FastInst: A Simple Query-Based Model for Real-Time Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": "junjiehe96/FastInst", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_FastInst_A_Simple_Query-Based_Model_for_Real-Time_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08594", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JxHuMMu6N50", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "SemiCVT: Semi-Supervised Convolutional Vision Transformer for Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_SemiCVT_Semi-Supervised_Convolutional_Vision_Transformer_for_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Semantic Human Parsing via Scalable Semantic Transfer Over Multiple Label Domains", - "base_url": null, - "title_page": null, - "repo": "yangjie-cv/SST", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Semantic_Human_Parsing_via_Scalable_Semantic_Transfer_Over_Multiple_Label_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04140", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PHRVCSAYEHU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Open-Set Semantic Segmentation for Point Clouds via Adversarial Prototype Framework", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Open-Set_Semantic_Segmentation_for_Point_Clouds_via_Adversarial_Prototype_Framework_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_wV90rUkfhU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Hunting Sparsity: Density-Guided Contrastive Learning for Semi-Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "Gavinwxy/DGCL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Hunting_Sparsity_Density-Guided_Contrastive_Learning_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "A Generalized Framework for Video Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": "miranheo/GenVIS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Heo_A_Generalized_Framework_for_Video_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.08834", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "SimpSON: Simplifying Photo Cleanup With Single-Click Distracting Object Segmentation Network", - "base_url": null, - "title_page": null, - "repo": "hmchuong/SimpSON", - "web_page": null, - "github_page": "https://simpson-cvpr23.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huynh_SimpSON_Simplifying_Photo_Cleanup_With_Single-Click_Distracting_Object_Segmentation_Network_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.17624", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "m4eIkwJUDfo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Complete-to-Partial 4D Distillation for Self-Supervised Point Cloud Sequence Representation Learning", - "base_url": null, - "title_page": null, - "repo": "dongyh20/C2P", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Complete-to-Partial_4D_Distillation_for_Self-Supervised_Point_Cloud_Sequence_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.05330", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_4C7vmLN0nM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Self-Supervised Learning for Multimodal Non-Rigid 3D Shape Matching", - "base_url": null, - "title_page": null, - "repo": "dongliangcao/Self-Supervised-Multimodal-Shape-Matching", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cao_Self-Supervised_Learning_for_Multimodal_Non-Rigid_3D_Shape_Matching_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10971", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "cQX1OOne0bk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Ultrahigh Resolution Image/Video Matting With Spatio-Temporal Sparsity", - "base_url": null, - "title_page": null, - "repo": "nowsyn/sparsemat", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Ultrahigh_Resolution_ImageVideo_Matting_With_Spatio-Temporal_Sparsity_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Style Projected Clustering for Domain Generalized Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": "https://gitee.com/mindspore/models/tree/master/research/cv/SPC-Net", - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Style_Projected_Clustering_for_Domain_Generalized_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "FVFvc8TH5eI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "MarS3D: A Plug-and-Play Motion-Aware Model for Semantic Segmentation on Multi-Scan 3D Point Clouds", - "base_url": null, - "title_page": null, - "repo": "CVMI-Lab/MarS3D", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_MarS3D_A_Plug-and-Play_Motion-Aware_Model_for_Semantic_Segmentation_on_Multi-Scan_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.09316", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PPPyZkwvsvs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Compositor: Bottom-Up Clustering and Compositing for Robust Part and Object Segmentation", - "base_url": null, - "title_page": null, - "repo": "TACJu/Compositor", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Compositor_Bottom-Up_Clustering_and_Compositing_for_Robust_Part_and_Object_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.07404", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SQlrky70y9A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Dynamic Focus-Aware Positional Queries for Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "ziplab/FASeg", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_Dynamic_Focus-Aware_Positional_Queries_for_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2204.01244", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LAut7f4mxsA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "HGFormer: Hierarchical Grouping Transformer for Domain Generalized Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "dingjiansw101/HGFormer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ding_HGFormer_Hierarchical_Grouping_Transformer_for_Domain_Generalized_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.13031", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tKMTUZAH0q0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Marching-Primitives: Shape Abstraction From Signed Distance Function", - "base_url": null, - "title_page": null, - "repo": "ChirikjianLab/Marching-Primitives", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Marching-Primitives_Shape_Abstraction_From_Signed_Distance_Function_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13190", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SeiGaEcbOUA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Multimodal Industrial Anomaly Detection via Hybrid Fusion", - "base_url": null, - "title_page": null, - "repo": "nomewang/M3DM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Multimodal_Industrial_Anomaly_Detection_via_Hybrid_Fusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00601", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "byZznDijY0U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "CLIP Is Also an Efficient Segmenter: A Text-Driven Approach for Weakly Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "linyq2117/CLIP-ES", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_CLIP_Is_Also_an_Efficient_Segmenter_A_Text-Driven_Approach_for_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09506", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "a0mm9irbeoQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Weakly Supervised Semantic Segmentation via Adversarial Learning of Classifier and Reconstructor", - "base_url": null, - "title_page": null, - "repo": "sangrockEG/ACR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kweon_Weakly_Supervised_Semantic_Segmentation_via_Adversarial_Learning_of_Classifier_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Conjugate Product Graphs for Globally Optimal 2D-3D Shape Matching", - "base_url": null, - "title_page": null, - "repo": "paul0noah/sm-2D3D", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Roetzer_Conjugate_Product_Graphs_for_Globally_Optimal_2D-3D_Shape_Matching_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11589", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qr_-n8NHWC4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Interactive Segmentation of Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "rahul-goel/isrf_code", - "web_page": null, - "github_page": "https://rahul-goel.github.io/isrf", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Goel_Interactive_Segmentation_of_Radiance_Fields_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.13545", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fPW-fPRiW24", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Boundary-Enhanced Co-Training for Weakly Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "ShenghaiRong/BECO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rong_Boundary-Enhanced_Co-Training_for_Weakly_Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "q3kJ532lbdc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Learning Multi-Modal Class-Specific Tokens for Weakly Supervised Dense Object Localization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Learning_Multi-Modal_Class-Specific_Tokens_for_Weakly_Supervised_Dense_Object_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Quantum Multi-Model Fitting", - "base_url": null, - "title_page": null, - "repo": "FarinaMatteo/qmmf", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Farina_Quantum_Multi-Model_Fitting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15444", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "m0QMGM-Awj8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Two-Shot Video Object Segmentation", - "base_url": null, - "title_page": null, - "repo": "yk-pku/Two-shot-Video-Object-Segmentation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yan_Two-Shot_Video_Object_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12078", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UMNUONtqRD0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "End-to-End Video Matting With Trimap Propagation", - "base_url": null, - "title_page": null, - "repo": "csvt32745/FTP-VM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_End-to-End_Video_Matting_With_Trimap_Propagation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3jjA4nvUc8c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "ISBNet: A 3D Point Cloud Instance Segmentation Network With Instance-Aware Sampling and Box-Aware Dynamic Convolution", - "base_url": null, - "title_page": null, - "repo": "VinAIResearch/ISBNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ngo_ISBNet_A_3D_Point_Cloud_Instance_Segmentation_Network_With_Instance-Aware_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.00246", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "uoOApyX-NUY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "On Calibrating Semantic Segmentation Models: Analyses and an Algorithm", - "base_url": null, - "title_page": null, - "repo": "dwang181/selectivecal", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_On_Calibrating_Semantic_Segmentation_Models_Analyses_and_an_Algorithm_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.12053", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Explicit Visual Prompting for Low-Level Structure Segmentations", - "base_url": null, - "title_page": null, - "repo": "NiFangBaAGe/Explicit-Visual-Prompt", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Explicit_Visual_Prompting_for_Low-Level_Structure_Segmentations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10883", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "9DdnQz4Y16E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Neural Intrinsic Embedding for Non-Rigid Point Cloud Matching", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_Neural_Intrinsic_Embedding_for_Non-Rigid_Point_Cloud_Matching_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01038", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "O6mhyFw3HLQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Incrementer: Transformer for Class-Incremental Semantic Segmentation With Knowledge Distillation Focusing on Old Class", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shang_Incrementer_Transformer_for_Class-Incremental_Semantic_Segmentation_With_Knowledge_Distillation_Focusing_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yV7XO-G-dto", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Camouflaged Instance Segmentation via Explicit De-Camouflaging", - "base_url": null, - "title_page": null, - "repo": "USTCL/DCNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_Camouflaged_Instance_Segmentation_via_Explicit_De-Camouflaging_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hUaBKw-coiM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Leveraging Hidden Positives for Unsupervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "hynnsk/HP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Seong_Leveraging_Hidden_Positives_for_Unsupervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15014", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4wFyPEhYTxE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Rethinking the Correlation in Few-Shot Segmentation: A Buoys View", - "base_url": null, - "title_page": null, - "repo": "mrkshllr/FewTURE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Rethinking_the_Correlation_in_Few-Shot_Segmentation_A_Buoys_View_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DYGAG-Ga2FI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Sparsely Annotated Semantic Segmentation With Adaptive Gaussian Mixtures", - "base_url": null, - "title_page": null, - "repo": "Luffy03/AGMM-SASS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Sparsely_Annotated_Semantic_Segmentation_With_Adaptive_Gaussian_Mixtures_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XNvGrh5BNgA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Mask-Guided Matting in the Wild", - "base_url": null, - "title_page": null, - "repo": "yucornetto/MGMatting", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Park_Mask-Guided_Matting_in_the_Wild_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Visual Dependency Transformers: Dependency Tree Emerges From Reversed Attention", - "base_url": null, - "title_page": null, - "repo": "dingmyu/DependencyViT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ding_Visual_Dependency_Transformers_Dependency_Tree_Emerges_From_Reversed_Attention_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03282", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IBZiMgsex1c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Conflict-Based Cross-View Consistency for Semi-Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "xiaoyao3302/CCVC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Conflict-Based_Cross-View_Consistency_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01276", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "g7QRZ85zMkQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Augmentation Matters: A Simple-Yet-Effective Approach to Semi-Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "ZhenZHAO/AugSeg", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Augmentation_Matters_A_Simple-Yet-Effective_Approach_to_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04976", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SY1lKHraa2o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Attention-Based Point Cloud Edge Sampling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Attention-Based_Point_Cloud_Edge_Sampling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14673", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LI33vU72BZo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "DA Wand: Distortion-Aware Selection Using Neural Mesh Parameterization", - "base_url": null, - "title_page": null, - "repo": "threedle/DA-Wand", - "web_page": null, - "github_page": "https://threedle.github.io/DA-Wand/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_DA_Wand_Distortion-Aware_Selection_Using_Neural_Mesh_Parameterization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06344", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "BmmdMlAWaf4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Extracting Class Activation Maps From Non-Discriminative Features As Well", - "base_url": null, - "title_page": null, - "repo": "zhaozhengChen/LPCAM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Extracting_Class_Activation_Maps_From_Non-Discriminative_Features_As_Well_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10334", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OuTvIgO0Rhg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Focused and Collaborative Feedback Integration for Interactive Image Segmentation", - "base_url": null, - "title_page": null, - "repo": "veizgyauzgyauz/FCFI", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_Focused_and_Collaborative_Feedback_Integration_for_Interactive_Image_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11880", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jotYi4Sho0Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Boosting Low-Data Instance Segmentation by Unsupervised Pre-Training With Saliency Prompt", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Boosting_Low-Data_Instance_Segmentation_by_Unsupervised_Pre-Training_With_Saliency_Prompt_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.01171", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NkcyeEY4Rco", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Unsupervised 3D Shape Reconstruction by Part Retrieval and Assembly", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Unsupervised_3D_Shape_Reconstruction_by_Part_Retrieval_and_Assembly_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01999", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "O7SrKYBwD6k", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "MobileVOS: Real-Time Video Object Segmentation Contrastive Learning Meets Knowledge Distillation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Miles_MobileVOS_Real-Time_Video_Object_Segmentation_Contrastive_Learning_Meets_Knowledge_Distillation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07815", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "1ilo8SYCJww", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Transformer Scale Gate for Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shi_Transformer_Scale_Gate_for_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.07056", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "PIDNet: A Real-Time Semantic Segmentation Network Inspired by PID Controllers", - "base_url": null, - "title_page": null, - "repo": "XuJiacong/PIDNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_PIDNet_A_Real-Time_Semantic_Segmentation_Network_Inspired_by_PID_Controllers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.02066", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "encrBD8yLGw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Side Adapter Network for Open-Vocabulary Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "MendelXu/SAN", - "web_page": null, - "github_page": "https://mendelxu.github.io/SAN/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Side_Adapter_Network_for_Open-Vocabulary_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.12242", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Test Time Adaptation With Regularized Loss for Weakly Supervised Salient Object Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Veksler_Test_Time_Adaptation_With_Regularized_Loss_for_Weakly_Supervised_Salient_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Feature Shrinkage Pyramid for Camouflaged Object Detection With Transformers", - "base_url": null, - "title_page": null, - "repo": "ZhouHuang23/FSPNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Feature_Shrinkage_Pyramid_for_Camouflaged_Object_Detection_With_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14816", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "M0Ucp2OBEKM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Reliability in Semantic Segmentation: Are We on the Right Track?", - "base_url": null, - "title_page": null, - "repo": "naver/relis", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/de_Jorge_Reliability_in_Semantic_Segmentation_Are_We_on_the_Right_Track_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11298", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "QbLv83vlNkc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Beyond mAP: Towards Better Evaluation of Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jena_Beyond_mAP_Towards_Better_Evaluation_of_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.01614", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Heat Diffusion Based Multi-Scale and Geometric Structure-Aware Transformer for Mesh Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wong_Heat_Diffusion_Based_Multi-Scale_and_Geometric_Structure-Aware_Transformer_for_Mesh_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Tree Instance Segmentation With Temporal Contour Graph", - "base_url": null, - "title_page": null, - "repo": "adnan0819/Tree-Instance-Segmentation-using-Temporal-Structured-Images", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Firoze_Tree_Instance_Segmentation_With_Temporal_Contour_Graph_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Exemplar-FreeSOLO: Enhancing Unsupervised Instance Segmentation With Exemplars", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ishtiak_Exemplar-FreeSOLO_Enhancing_Unsupervised_Instance_Segmentation_With_Exemplars_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "l5sMTrswceQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Omnimatte3D: Associating Objects and Their Effects in Unconstrained Monocular Video", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Suhail_Omnimatte3D_Associating_Objects_and_Their_Effects_in_Unconstrained_Monocular_Video_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zx-h4f2RXTA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Learning Orthogonal Prototypes for Generalized Few-Shot Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "lsa1997/POP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Learning_Orthogonal_Prototypes_for_Generalized_Few-Shot_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Instance-Specific and Model-Adaptive Supervision for Semi-Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": "ZhenZHAO/iMAS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Instance-Specific_and_Model-Adaptive_Supervision_for_Semi-Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.11335", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fsCC4z1qoeU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Improving Robustness of Semantic Segmentation to Motion-Blur Using Class-Centric Augmentation", - "base_url": null, - "title_page": null, - "repo": "aka-discover/CCMBA_CVPR23", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Aakanksha_Improving_Robustness_of_Semantic_Segmentation_to_Motion-Blur_Using_Class-Centric_Augmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "haypy30_jG4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "IFSeg: Image-Free Semantic Segmentation via Vision-Language Model", - "base_url": null, - "title_page": null, - "repo": "alinlab/ifseg", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yun_IFSeg_Image-Free_Semantic_Segmentation_via_Vision-Language_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14396", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "CLIP-S4: Language-Guided Self-Supervised Semantic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/He_CLIP-S4_Language-Guided_Self-Supervised_Semantic_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.01040", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rx0XvzFsI10", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - }, - { - "title": "Pruning Parameterization With Bi-Level Optimization for Efficient Semantic Segmentation on the Edge", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Pruning_Parameterization_With_Bi-Level_Optimization_for_Efficient_Semantic_Segmentation_on_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Segmentation, Grouping and Shape Analysis" - } -] \ No newline at end of file diff --git a/json_data/self-supervised-or-unsupervised-representation-learning.json b/json_data/self-supervised-or-unsupervised-representation-learning.json deleted file mode 100644 index 39d47f4..0000000 --- a/json_data/self-supervised-or-unsupervised-representation-learning.json +++ /dev/null @@ -1,1777 +0,0 @@ -[ - { - "title": "SimpleNet: A Simple Network for Image Anomaly Detection and Localization", - "base_url": null, - "title_page": null, - "repo": "DonaldRR/SimpleNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_SimpleNet_A_Simple_Network_for_Image_Anomaly_Detection_and_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15140", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "R9P4ULNBvSk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Masked Image Modeling with Local Multi-Scale Reconstruction", - "base_url": null, - "title_page": null, - "repo": "Haoqing-Wang/LocalMIM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Masked_Image_Modeling_With_Local_Multi-Scale_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.05251", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_QmCpjHMcMI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "AdaMAE: Adaptive Masking for Efficient Spatiotemporal Learning with Masked Autoencoders", - "base_url": null, - "title_page": null, - "repo": "wgcban/adamae", - "web_page": "https://www.wgcban.com/research/adamae", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bandara_AdaMAE_Adaptive_Masking_for_Efficient_Spatiotemporal_Learning_With_Masked_Autoencoders_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.09120", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "ActMAD: Activation Matching to Align Distributions for Test-Time-Training", - "base_url": null, - "title_page": null, - "repo": "jmiemirza/ActMAD", - "web_page": null, - "github_page": "https://jmiemirza.github.io/ActMAD", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mirza_ActMAD_Activation_Matching_To_Align_Distributions_for_Test-Time-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12870", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GI5auU8TpG4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Rethinking Out-of-Distribution (OOD) Detection: Masked Image Modeling is All You Need", - "base_url": null, - "title_page": null, - "repo": "JulietLJY/MOOD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Rethinking_Out-of-Distribution_OOD_Detection_Masked_Image_Modeling_Is_All_You_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.02615", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JtBZ6lO67F4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "DLBD: A Self-Supervised Direct-Learned Binary Descriptor", - "base_url": null, - "title_page": null, - "repo": "CQUPT-CV/DLBD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiao_DLBD_A_Self-Supervised_Direct-Learned_Binary_Descriptor_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "emMctSoP6Cs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Cut and Learn for Unsupervised Object Detection and Instance Segmentation", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/CutLER", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Cut_and_Learn_for_Unsupervised_Object_Detection_and_Instance_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.11320", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "y4b5wkf9vp0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Unsupervised Deep Probabilistic Approach for Partial Point Cloud Registration", - "base_url": null, - "title_page": null, - "repo": "gfmei/UDPReg", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mei_Unsupervised_Deep_Probabilistic_Approach_for_Partial_Point_Cloud_Registration_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13290", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YH9rI-kot0g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Masked Motion Encoding for Self-Supervised Video Representation Learning", - "base_url": null, - "title_page": null, - "repo": "XinyuSun/MME", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Masked_Motion_Encoding_for_Self-Supervised_Video_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.06096", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Stare at what You See: Masked Image Modeling without Reconstruction", - "base_url": null, - "title_page": null, - "repo": "OpenDriveLab/maskalign", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xue_Stare_at_What_You_See_Masked_Image_Modeling_Without_Reconstruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.08887", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "iBVc1Vvhx84", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Hard Patches Mining for Masked Image Modeling", - "base_url": null, - "title_page": null, - "repo": "Haochen-Wang409/HPM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Hard_Patches_Mining_for_Masked_Image_Modeling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05919", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ns6A-kJXPzo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Multi-Mode Online Knowledge Distillation for Self-Supervised Visual Representation Learning", - "base_url": null, - "title_page": null, - "repo": "skyoux/mokd", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Song_Multi-Mode_Online_Knowledge_Distillation_for_Self-Supervised_Visual_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.06461", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "g3WmZt0OSKs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "EVA: Exploring the Limits of Masked Visual Representation Learning at Scale", - "base_url": null, - "title_page": null, - "repo": "baaivision/EVA", - "web_page": null, - "github_page": "https://github.com/baaivision/EVA/tree/master/EVA-01", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fang_EVA_Exploring_the_Limits_of_Masked_Visual_Representation_Learning_at_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.07636", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "MAGE: MAsked Generative Encoder to Unify Representation Learning and Image Synthesis", - "base_url": null, - "title_page": null, - "repo": "LTH14/mage", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_MAGE_MAsked_Generative_Encoder_To_Unify_Representation_Learning_and_Image_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.09117", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YeroKjJq9nk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Token Boosting for Robust Self-Supervised Visual Transformer Pre-Training", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Token_Boosting_for_Robust_Self-Supervised_Visual_Transformer_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04175", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kefATZoHqNI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Unsupervised 3D Point Cloud Representation Learning by Triangle Constrained Contrast for Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pang_Unsupervised_3D_Point_Cloud_Representation_Learning_by_Triangle_Constrained_Contrast_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TWEH5LdCGTo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Masked Auto-Encoders Meet Generative Adversarial Networks and Beyond", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fei_Masked_Auto-Encoders_Meet_Generative_Adversarial_Networks_and_Beyond_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Integrally Pre-Trained Transformer Pyramid Networks", - "base_url": null, - "title_page": null, - "repo": "sunsmarterjie/iTPN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tian_Integrally_Pre-Trained_Transformer_Pyramid_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.12735", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "k7oX2m0T7OU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Mixed Autoencoder for Self-Supervised Visual Representation Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Mixed_Autoencoder_for_Self-Supervised_Visual_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17152", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ic8GYtwjSuw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Correlational Image Modeling for Self-Supervised Visual Pre-Training", - "base_url": null, - "title_page": null, - "repo": "weivision/Correlational-Image-Modeling", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Correlational_Image_Modeling_for_Self-Supervised_Visual_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12670", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ud0uKNNQ5t4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Shepherding Slots to Objects: Towards Stable and Robust Object-Centric Learning", - "base_url": null, - "title_page": null, - "repo": "object-understanding/SLASH", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Shepherding_Slots_to_Objects_Towards_Stable_and_Robust_Object-Centric_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17842", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rrxjDndltlA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Deep Fair Clustering via Maximizing and Minimizing Mutual Information: Theory, Algorithm and Metric", - "base_url": null, - "title_page": null, - "repo": "XLearning-SCU/2023-CVPR-FCMI", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zeng_Deep_Fair_Clustering_via_Maximizing_and_Minimizing_Mutual_Information_Theory_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.12396", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Evolved Part Masking for Self-Supervised Learning", - "base_url": null, - "title_page": null, - "repo": "ZhanzhouFeng/Evolved-Part-Masking", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_Evolved_Part_Masking_for_Self-Supervised_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Change-Aware Sampling and Contrastive Learning for Satellite Images", - "base_url": null, - "title_page": null, - "repo": "utkarshmall13/caco", - "web_page": "https://research.cs.cornell.edu/caco/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mall_Change-Aware_Sampling_and_Contrastive_Learning_for_Satellite_Images_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZwwGP8XD7Io", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Learning Common Rationale to Improve Self-Supervised Representation for Fine-Grained Visual Recognition Problems", - "base_url": null, - "title_page": null, - "repo": "GANPerf/LCR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shu_Learning_Common_Rationale_To_Improve_Self-Supervised_Representation_for_Fine-Grained_Visual_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01669", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "DropMAE: Masked Autoencoders with Spatial-Attention Dropout for Tracking Tasks", - "base_url": null, - "title_page": null, - "repo": "jimmy-dq/DropMAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_DropMAE_Masked_Autoencoders_With_Spatial-Attention_Dropout_for_Tracking_Tasks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00571", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "QIfY5RFJTJU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "RILS: Masked Visual Reconstruction in Language Semantic Space", - "base_url": null, - "title_page": null, - "repo": "hustvl/RILS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_RILS_Masked_Visual_Reconstruction_in_Language_Semantic_Space_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.06958", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Three Guidelines You Should know for Universally Slimmable Self-Supervised Learning", - "base_url": null, - "title_page": null, - "repo": "megvii-research/US3L-CVPR2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cao_Three_Guidelines_You_Should_Know_for_Universally_Slimmable_Self-Supervised_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06870", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EbMfGAzm5T4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "BASiS: Batch Aligned Spectral Embedding Space", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Streicher_BASiS_Batch_Aligned_Spectral_Embedding_Space_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16960", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Co-Salient Object Detection with Uncertainty-Aware Group Exchange-Masking", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Co-Salient_Object_Detection_With_Uncertainty-Aware_Group_Exchange-Masking_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YqDkInedx34", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Hyperbolic Contrastive Learning for Visual Representations beyond Objects", - "base_url": null, - "title_page": null, - "repo": "shlokk/HCL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ge_Hyperbolic_Contrastive_Learning_for_Visual_Representations_Beyond_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.00653", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "voDgTcd8qQk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Active Finetuning: Exploiting Annotation Budget in the Pretraining-Finetuning Paradigm", - "base_url": null, - "title_page": null, - "repo": "yichen928/ActiveFT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_Active_Finetuning_Exploiting_Annotation_Budget_in_the_Pretraining-Finetuning_Paradigm_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14382", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "MV-JAR: Masked Voxel Jigsaw and Reconstruction for LiDAR-based Self-Supervised Pre-Training", - "base_url": null, - "title_page": null, - "repo": "OpenRobotLab/MV-JAR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_MV-JAR_Masked_Voxel_Jigsaw_and_Reconstruction_for_LiDAR-Based_Self-Supervised_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13510", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nlZd-twMOaE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "OmniAL: A Unified CNN Framework for Unsupervised Anomaly Localization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_OmniAL_A_Unified_CNN_Framework_for_Unsupervised_Anomaly_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "TinyMIM: An Empirical Study of Distilling MIM Pre-Trained Models", - "base_url": null, - "title_page": null, - "repo": "OliverRensu/TinyMIM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ren_TinyMIM_An_Empirical_Study_of_Distilling_MIM_Pre-Trained_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.01296", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "ALSO: Automotive Lidar Self-Supervision by Occupancy Estimation", - "base_url": null, - "title_page": null, - "repo": "valeoai/ALSO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Boulch_ALSO_Automotive_Lidar_Self-Supervision_by_Occupancy_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.05867", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GGIBKlMvphw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Non-Contrastive Unsupervised Learning of Physiological Signals from Video", - "base_url": null, - "title_page": null, - "repo": "CVRL/SiNC-rPPG", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Speth_Non-Contrastive_Unsupervised_Learning_of_Physiological_Signals_From_Video_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07944", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Bg7VkxWcOhQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "CrOC: Cross-View Online Clustering for Dense Visual Representation Learning", - "base_url": null, - "title_page": null, - "repo": "stegmuel/CrOC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Stegmuller_CrOC_Cross-View_Online_Clustering_for_Dense_Visual_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13245", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "al067JbNNzw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "MOVES: Manipulated Objects in Video Enable Segmentation", - "base_url": null, - "title_page": null, - "repo": "relh/moves", - "web_page": null, - "github_page": "https://relh.github.io/moves/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Higgins_MOVES_Manipulated_Objects_in_Video_Enable_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JBz4zzQdoso", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Self-Supervised Representation Learning for CAD", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jones_Self-Supervised_Representation_Learning_for_CAD_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.10807", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ICWOmook9w8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Movies2Scenes: using Movie Metadata to Learn Scene Representation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Movies2Scenes_Using_Movie_Metadata_To_Learn_Scene_Representation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2202.10650", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NrXEIoocKFg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "PointCMP: Contrastive Mask Prediction for Self-Supervised Learning on Point Cloud Videos", - "base_url": null, - "title_page": null, - "repo": "JohnsonSign/PointCMP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shen_PointCMP_Contrastive_Mask_Prediction_for_Self-Supervised_Learning_on_Point_Cloud_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.04075", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EzI9Vn9HPNY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Texture-guided Saliency Distilling for Unsupervised Salient Object Detection", - "base_url": null, - "title_page": null, - "repo": "moothes/A2S-v2", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Texture-Guided_Saliency_Distilling_for_Unsupervised_Salient_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2207.05921", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Multi-Realism Image Compression with a Conditional Generator", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Agustsson_Multi-Realism_Image_Compression_With_a_Conditional_Generator_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.13824", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Understanding Masked Autoencoders via Hierarchical Latent Variable Models", - "base_url": null, - "title_page": null, - "repo": "martinmamql/mae_understand", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kong_Understanding_Masked_Autoencoders_via_Hierarchical_Latent_Variable_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.04898", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "004ojgVKYtA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "GeoMAE: Masked Geometric Target Prediction for Self-Supervised Point Cloud Pre-Training", - "base_url": null, - "title_page": null, - "repo": "Tsinghua-MARS-Lab/GeoMAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tian_GeoMAE_Masked_Geometric_Target_Prediction_for_Self-Supervised_Point_Cloud_Pre-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.08808", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZJ7ukv1-WEk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Siamese DETR", - "base_url": null, - "title_page": null, - "repo": "Zx55/SiameseDETR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Siamese_DETR_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.18144", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kPV-RZwgp7A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Generalizable Implicit Neural Representations via Instance Pattern Composers", - "base_url": null, - "title_page": null, - "repo": "kakaobrain/ginr-ipc", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Generalizable_Implicit_Neural_Representations_via_Instance_Pattern_Composers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13223", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Pose-Disentangled Contrastive Learning for Self-Supervised Facial Representation", - "base_url": null, - "title_page": null, - "repo": "DreamMr/PCL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Pose-Disentangled_Contrastive_Learning_for_Self-Supervised_Facial_Representation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13490", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rayPoX6I5Bc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "OT-Filter: An Optimal Transport Filter for Learning with Noisy Labels", - "base_url": null, - "title_page": null, - "repo": "ryl0427/Code-for-OT-Filter", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_OT-Filter_An_Optimal_Transport_Filter_for_Learning_With_Noisy_Labels_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Teacher-Generated Spatial-Attention Labels Boost Robustness and Accuracy of Contrastive Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://github.com/google-research/google-research/tree/master/human_attention/saliency_model_from_scratch", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yao_Teacher-Generated_Spatial-Attention_Labels_Boost_Robustness_and_Accuracy_of_Contrastive_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WyC1zfqbrgU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Spatio-Temporal Self-Supervised Learning for Point Clouds in the Wild", - "base_url": null, - "title_page": null, - "repo": "YanhaoWu/STSSL", - "web_page": null, - "github_page": "https://yanhaowu.github.io/STSSL/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Spatiotemporal_Self-Supervised_Learning_for_Point_Clouds_in_the_Wild_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16235", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ck5bShcRFwk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "BKinD-3D: Self-Supervised 3D Keypoint Discovery from Multi-View Videos", - "base_url": null, - "title_page": null, - "repo": "neuroethology/BKinD-3D", - "web_page": "https://sites.google.com/view/b-kind/3d", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_BKinD-3D_Self-Supervised_3D_Keypoint_Discovery_From_Multi-View_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07401", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CqYw1DicsTg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Learning Decorrelated Representations Efficiently using Fast Fourier Transform", - "base_url": null, - "title_page": null, - "repo": "yutaro-s/scalable-decorrelation-ssl", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shigeto_Learning_Decorrelated_Representations_Efficiently_Using_Fast_Fourier_Transform_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.01569", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ngPiU13Fg0M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Beyond Appearance: A Semantic Controllable Self-Supervised Learning Framework for Human-Centric Visual Tasks", - "base_url": null, - "title_page": null, - "repo": "tinyvision/SOLIDER", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Beyond_Appearance_A_Semantic_Controllable_Self-Supervised_Learning_Framework_for_Human-Centric_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17602", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jOCLYkEV2d0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Learning Geometry-Aware Representations by Sketching", - "base_url": null, - "title_page": null, - "repo": "illhyhl1111/LearningBySketching", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lee_Learning_Geometry-Aware_Representations_by_Sketching_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08204", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "26hCySC0354", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Improving Visual Representation Learning through Perceptual Understanding", - "base_url": null, - "title_page": null, - "repo": "tractableai/perceptual-mae", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tukra_Improving_Visual_Representation_Learning_Through_Perceptual_Understanding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.14504", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "MixMAE: Mixed and Masked Autoencoder for Efficient Pretraining of Hierarchical Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "Sense-X/MixMIM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_MixMAE_Mixed_and_Masked_Autoencoder_for_Efficient_Pretraining_of_Hierarchical_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.13137", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Unsupervised Object Localization: Observing the Background to Discover Objects", - "base_url": null, - "title_page": null, - "repo": "valeoai/FOUND", - "web_page": null, - "github_page": "https://valeoai.github.io/blog/publications/found/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Simeoni_Unsupervised_Object_Localization_Observing_the_Background_To_Discover_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07834", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jfYQfFcrJBE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "MCF: Mutual Correction Framework for Semi-Supervised Medical Image Segmentation", - "base_url": null, - "title_page": null, - "repo": "WYC-321/MCF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_MCF_Mutual_Correction_Framework_for_Semi-Supervised_Medical_Image_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ViF28ArbhFY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "DivClust: Controlling Diversity in Deep Clustering", - "base_url": null, - "title_page": null, - "repo": "ManiadisG/DivClust", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Metaxas_DivClust_Controlling_Diversity_in_Deep_Clustering_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.01042", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "UHruFy7X4RU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "On Data Scaling in Masked Image Modeling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_On_Data_Scaling_in_Masked_Image_Modeling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.04664", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Revealing the Dark Secrets of Masked Image Modeling", - "base_url": null, - "title_page": null, - "repo": "SwinTransformer/MIM-Depth-Estimation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_Revealing_the_Dark_Secrets_of_Masked_Image_Modeling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2205.13543", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Open-Set Representation Learning through Combinatorial Embedding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Open-Set_Representation_Learning_Through_Combinatorial_Embedding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2106.15278", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Coreset Sampling from Open-Set for Fine-Grained Self-Supervised Learning", - "base_url": null, - "title_page": null, - "repo": "sungnyun/openssl-simcore", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Coreset_Sampling_From_Open-Set_for_Fine-Grained_Self-Supervised_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11101", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "f_-dIVRo8Q8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "ToThePoint: Efficient Contrastive Learning of 3D Point Clouds via Recycling", - "base_url": null, - "title_page": null, - "repo": "Lyccl/Tothepoint", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_ToThePoint_Efficient_Contrastive_Learning_of_3D_Point_Clouds_via_Recycling_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "MetaViewer: Towards a Unified Multi-View Representation", - "base_url": null, - "title_page": null, - "repo": "xxLifeLover/MetaViewer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_MetaViewer_Towards_a_Unified_Multi-View_Representation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06329", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RbFTH8G-w1U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Self-Supervised Learning from Images with a Joint-Embedding Predictive Architecture", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/ijepa", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Assran_Self-Supervised_Learning_From_Images_With_a_Joint-Embedding_Predictive_Architecture_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.08243", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gPlXDlFn0U4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Understanding Masked Image Modeling via Learning Occlusion Invariant Feature", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kong_Understanding_Masked_Image_Modeling_via_Learning_Occlusion_Invariant_Feature_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.04164", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rqyhxBz_xYg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "CHMATCH: Contrastive Hierarchical Matching and Robust Adaptive Threshold Boosted Semi-Supervised Learning", - "base_url": null, - "title_page": null, - "repo": "sailist/CHMatch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_CHMATCH_Contrastive_Hierarchical_Matching_and_Robust_Adaptive_Threshold_Boosted_Semi-Supervised_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AMyJCI0PIdo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - }, - { - "title": "Regularize Implicit Neural Representation by Itself", - "base_url": null, - "title_page": null, - "repo": "YannickStruempler/inr_based_compression", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Regularize_Implicit_Neural_Representation_by_Itself_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15484", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Self-Supervised or Unsupervised Representation Learning" - } -] \ No newline at end of file diff --git a/json_data/transparency-fairness-accountability-privacy-ethics-in-vision.json b/json_data/transparency-fairness-accountability-privacy-ethics-in-vision.json deleted file mode 100644 index 4b62759..0000000 --- a/json_data/transparency-fairness-accountability-privacy-ethics-in-vision.json +++ /dev/null @@ -1,752 +0,0 @@ -[ - { - "title": "Effective Ambiguity Attack Against Passport-based DNN Intellectual Property Protection Schemes through Fully Connected Layer Substitution", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Effective_Ambiguity_Attack_Against_Passport-Based_DNN_Intellectual_Property_Protection_Schemes_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11595", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Progressive Open Space Expansion for Open-Set Model Attribution", - "base_url": null, - "title_page": null, - "repo": "ICTMCG/POSE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Progressive_Open_Space_Expansion_for_Open-Set_Model_Attribution_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.06877", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6PiuUNoDH1M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Breaching FedMD: Image Recovery via Paired-Logits Inversion Attack", - "base_url": null, - "title_page": null, - "repo": "FLAIR-THU/PairedLogitsInversion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Takahashi_Breaching_FedMD_Image_Recovery_via_Paired-Logits_Inversion_Attack_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11436", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "DartBlur: Privacy Preservation with Detection Artifact Suppression", - "base_url": null, - "title_page": null, - "repo": "JaNg2333/DartBlur", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_DartBlur_Privacy_Preservation_With_Detection_Artifact_Suppression_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "W7dX0WH32Ug", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Reinforcement Learning-based Black-Box Model Inversion Attacks", - "base_url": null, - "title_page": null, - "repo": "HanGyojin/RLB-MI", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Han_Reinforcement_Learning-Based_Black-Box_Model_Inversion_Attacks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.04625", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Model-Agnostic Gender Debiased Image Captioning", - "base_url": null, - "title_page": null, - "repo": "rebnej/LIBRA", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hirota_Model-Agnostic_Gender_Debiased_Image_Captioning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03693", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Zkk9fvgZPN8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Uncurated Image-Text Datasets: Shedding Light on Demographic Bias", - "base_url": null, - "title_page": null, - "repo": "noagarcia/phase", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Garcia_Uncurated_Image-Text_Datasets_Shedding_Light_on_Demographic_Bias_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02828", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-QWWlHc1HPc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "AltFreezing for more General Video Face Forgery Detection", - "base_url": null, - "title_page": null, - "repo": "ZhendongWang6/AltFreezing", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_AltFreezing_for_More_General_Video_Face_Forgery_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.08317", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Qe4xT46VqE4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Make Landscape Flatter in Differentially Private Federated Learning", - "base_url": null, - "title_page": null, - "repo": "YMJS-Irfan/DP-FedSAM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shi_Make_Landscape_Flatter_in_Differentially_Private_Federated_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11242", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "v2sDjUI_a6Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "DynaFed: Tackling Client Data Heterogeneity with Global Dynamics", - "base_url": null, - "title_page": null, - "repo": "pipilurj/DynaFed", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pi_DynaFed_Tackling_Client_Data_Heterogeneity_With_Global_Dynamics_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10878", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "a7rKt9I3ArM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Re-Thinking Model Inversion Attacks Against Deep Neural Networks", - "base_url": null, - "title_page": null, - "repo": "sutd-visual-computing-group/Re-thinking_MI", - "web_page": null, - "github_page": "https://ngoc-nguyen-0.github.io/re-thinking_model_inversion_attacks/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nguyen_Re-Thinking_Model_Inversion_Attacks_Against_Deep_Neural_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.01669", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "d5YrY0W6LWI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Safe Latent Diffusion: Mitigating Inappropriate Degeneration in Diffusion Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://ml-research.github.io/human-centered-genai/projects/safe-latent-diffusion/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Schramowski_Safe_Latent_Diffusion_Mitigating_Inappropriate_Degeneration_in_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.05105", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "drkpQJpmyI0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "TrojViT: Trojan Insertion in Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "mxzheng/TrojViT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zheng_TrojViT_Trojan_Insertion_in_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.13049", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Difficulty-based Sampling for Debiased Contrastive Representation Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jang_Difficulty-Based_Sampling_for_Debiased_Contrastive_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "H--ujcJahBk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Model Barrier: A Compact Un-Transferable Isolation Domain for Model Intellectual Property Protection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Model_Barrier_A_Compact_Un-Transferable_Isolation_Domain_for_Model_Intellectual_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11078", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "iIxjowjl_58", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Fair Scratch Tickets: Finding Fair Sparse Networks without Weight Training", - "base_url": null, - "title_page": null, - "repo": "HungerPWAY/Fair-Scratch-Tickets", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Fair_Scratch_Tickets_Finding_Fair_Sparse_Networks_Without_Weight_Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-u2IK3iDH5U", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "CLIP2Protect: Protecting Facial Privacy using Text-Guided Makeup via Adversarial Latent Search", - "base_url": null, - "title_page": null, - "repo": "fahadshamshad/Clip2Protect", - "web_page": null, - "github_page": "https://fahadshamshad.github.io/Clip2Protect/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shamshad_CLIP2Protect_Protecting_Facial_Privacy_Using_Text-Guided_Makeup_via_Adversarial_Latent_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CUSVyvM_-6o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Bias in Pruned Vision Models: In-Depth Analysis and Countermeasures", - "base_url": null, - "title_page": null, - "repo": "IST-DASLab/pruned-vision-model-bias", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Iofinova_Bias_in_Pruned_Vision_Models_In-Depth_Analysis_and_Countermeasures_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.12622", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Learning to Generate Image Embeddings with User-Level Differential Privacy", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Learning_To_Generate_Image_Embeddings_With_User-Level_Differential_Privacy_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10844", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Bias Mimicking: A Simple Sampling Approach for Bias Mitigation", - "base_url": null, - "title_page": null, - "repo": "mqraitem/Bias-Mimicking", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qraitem_Bias_Mimicking_A_Simple_Sampling_Approach_for_Bias_Mitigation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.15605", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nlXj96doTjM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "CaPriDe Learning: Confidential and Private Decentralized Learning based on Encryption-Friendly Distillation Loss", - "base_url": null, - "title_page": null, - "repo": "tnurbek/capride-learning", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tastan_CaPriDe_Learning_Confidential_and_Private_Decentralized_Learning_Based_on_Encryption-Friendly_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wY2ctF_foNM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "DeAR: Debiasing Vision-Language Models with Additive Residuals", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Seth_DeAR_Debiasing_Vision-Language_Models_With_Additive_Residuals_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10431", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qWJuxXk_AyQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Deep Deterministic Uncertainty: A New Simple Baseline", - "base_url": null, - "title_page": null, - "repo": "omegafragger/DDU", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mukhoti_Deep_Deterministic_Uncertainty_A_New_Simple_Baseline_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "HWLke-_eimQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Manipulating Transfer Learning for Property Inference", - "base_url": null, - "title_page": null, - "repo": "yulongt23/Transfer-Inference", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tian_Manipulating_Transfer_Learning_for_Property_Inference_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11643", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Training Debiased Subnetworks with Contrastive Weight Pruning", - "base_url": null, - "title_page": null, - "repo": "ParkGeonYeong/DCWP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Park_Training_Debiased_Subnetworks_With_Contrastive_Weight_Pruning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2210.05247", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fDXYMQMQT5s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Diffusion Art or Digital Forgery? Investigating Data Replication in Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "somepago/DCR", - "web_page": null, - "github_page": "https://somepago.github.io/diffrep.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Somepalli_Diffusion_Art_or_Digital_Forgery_Investigating_Data_Replication_in_Diffusion_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03860", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OiiuEeopXWQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "STDLens: Model Hijacking-Resilient Federated Learning for Object Detection", - "base_url": null, - "title_page": null, - "repo": "git-disl/STDLens", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chow_STDLens_Model_Hijacking-Resilient_Federated_Learning_for_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11511", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Architectural Backdoors in Neural Networks", - "base_url": null, - "title_page": null, - "repo": "QuangNguyen2609/ARCHITECTURAL-BACKDOORS-IN-NEURAL-NETWORKS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bober-Irizar_Architectural_Backdoors_in_Neural_Networks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.07840", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "vY-RB9MKv40", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "MEDIC: Remove Model Backdoors via Importance Driven Cloning", - "base_url": null, - "title_page": null, - "repo": "qiulingxu/MEDIC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_MEDIC_Remove_Model_Backdoors_via_Importance_Driven_Cloning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dhIBzpDWNX0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - }, - { - "title": "Learning Debiased Representations via Conditional Attribute Interpolation", - "base_url": null, - "title_page": null, - "repo": "ZhangYikaii/chi-square", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Learning_Debiased_Representations_via_Conditional_Attribute_Interpolation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Vbe0MrkC1qU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Transparency, Fairness, Accountability, Privacy, Ethics in Vision" - } -] \ No newline at end of file diff --git a/json_data/video-action-and-event-understanding.json b/json_data/video-action-and-event-understanding.json deleted file mode 100644 index dffe955..0000000 --- a/json_data/video-action-and-event-understanding.json +++ /dev/null @@ -1,2052 +0,0 @@ -[ - { - "title": "Open Set Action Recognition via Multi-Label Evidential Learning", - "base_url": null, - "title_page": null, - "repo": "charliezhaoyinpeng/mule", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Open_Set_Action_Recognition_via_Multi-Label_Evidential_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12698", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "S185R1vT2Qk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "FLAG3D: A 3D Fitness Activity Dataset with Language Instruction", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://andytang15.github.io/FLAG3D/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_FLAG3D_A_3D_Fitness_Activity_Dataset_With_Language_Instruction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04638", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CgdRmk0BVvM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "MoLo: Motion-Augmented Long-Short Contrastive Learning for Few-Shot Action Recognition", - "base_url": null, - "title_page": null, - "repo": "alibaba-mmai-research/MoLo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_MoLo_Motion-Augmented_Long-Short_Contrastive_Learning_for_Few-Shot_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00946", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ig1HGTrrA54", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "The Wisdom of Crowds: Temporal Progressive Attention for Early Action Prediction", - "base_url": null, - "title_page": null, - "repo": "alexandrosstergiou/progressive-action-prediction", - "web_page": null, - "github_page": "https://alexandrosstergiou.github.io/project_pages/TemPr/index.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Stergiou_The_Wisdom_of_Crowds_Temporal_Progressive_Attention_for_Early_Action_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2204.13340", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dcmd8U47BT8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Use Your Head: Improving Long-Tail Video Recognition", - "base_url": null, - "title_page": null, - "repo": "tobyperrett/lmr", - "web_page": null, - "github_page": "https://tobyperrett.github.io/lmr/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Perrett_Use_Your_Head_Improving_Long-Tail_Video_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.01143", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TXEMh99Ukmg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Decomposed Cross-Modal Distillation for RGB-based Temporal Action Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lee_Decomposed_Cross-Modal_Distillation_for_RGB-Based_Temporal_Action_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17285", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2upFWX7NVqc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Video Test-Time Adaptation for Action Recognition", - "base_url": null, - "title_page": null, - "repo": "wlin-at/ViTTA", - "web_page": null, - "github_page": "https://wlin-at.github.io/vitta", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Video_Test-Time_Adaptation_for_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.15393", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "RzdYgE1hN2o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "How Can Objects Help Action Recognition?", - "base_url": null, - "title_page": null, - "repo": "google-research/scenic", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_How_Can_Objects_Help_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.11726", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4E_X1hCj4yU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Text-Visual Prompting for Efficient 2D Temporal Video Grounding", - "base_url": null, - "title_page": null, - "repo": "intel/TVP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Text-Visual_Prompting_for_Efficient_2D_Temporal_Video_Grounding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.04995", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "zj2s_G3066s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Enlarging Instance-Specific and Class-Specific Information for Open-Set Action Recognition", - "base_url": null, - "title_page": null, - "repo": "Jun-CEN/PSL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cen_Enlarging_Instance-Specific_and_Class-Specific_Information_for_Open-Set_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15467", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SofkzNeymP4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "TimeBalance: Temporally-Invariant and Temporally-Distinctive Video Representations for Semi-Supervised Action Recognition", - "base_url": null, - "title_page": null, - "repo": "DAVEISHAN/TimeBalance", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dave_TimeBalance_Temporally-Invariant_and_Temporally-Distinctive_Video_Representations_for_Semi-Supervised_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16268", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "2c5LM6YqPKQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Learning Video Representations from Large Language Models", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/LaViLa", - "web_page": null, - "github_page": "https://facebookresearch.github.io/LaViLa/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Learning_Video_Representations_From_Large_Language_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04501", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tbQaP07xQ4c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Fine-tuned CLIP Models are Efficient Video Learners", - "base_url": null, - "title_page": null, - "repo": "muzairkhattak/ViFi-CLIP", - "web_page": null, - "github_page": "https://muzairkhattak.github.io/ViFi-CLIP/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rasheed_Fine-Tuned_CLIP_Models_Are_Efficient_Video_Learners_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03640", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "uqPLPIyWBb0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Efficient Movie Scene Detection Using State-Space Transformers", - "base_url": null, - "title_page": null, - "repo": "md-mohaiminul/TranS4mer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Islam_Efficient_Movie_Scene_Detection_Using_State-Space_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.14427", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "EOmVAByPQbE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "AdamsFormer for Spatial Action Localization in the Future", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chi_AdamsFormer_for_Spatial_Action_Localization_in_the_Future_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PK0O-ynPgr0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "A Light Weight Model for Active Speaker Detection", - "base_url": null, - "title_page": null, - "repo": "Junhua-Liao/Light-ASD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liao_A_Light_Weight_Model_for_Active_Speaker_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.04439", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "spGacmYdvYs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "System-Status-Aware Adaptive Network for Online Streaming Video Understanding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Foo_System-Status-Aware_Adaptive_Network_for_Online_Streaming_Video_Understanding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15742", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8DrTkS247xs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "STMixer: A One-Stage Sparse Action Detector", - "base_url": null, - "title_page": null, - "repo": "MCG-NJU/STMixer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_STMixer_A_One-Stage_Sparse_Action_Detector_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15879", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Sy4jozsQLM0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Revisiting Temporal Modeling for CLIP-Based Image-to-Video Knowledge Transferring", - "base_url": null, - "title_page": null, - "repo": "farewellthree/STAN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Revisiting_Temporal_Modeling_for_CLIP-Based_Image-to-Video_Knowledge_Transferring_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.11116", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kaDItcB1iFw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Distilling Vision-Language Pre-Training To Collaborate With Weakly-Supervised Temporal Action Localization", - "base_url": null, - "title_page": null, - "repo": "ju-chen/Efficient-Prompt", - "web_page": null, - "github_page": "https://voide1220.github.io/distillation_collaboration/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ju_Distilling_Vision-Language_Pre-Training_To_Collaborate_With_Weakly-Supervised_Temporal_Action_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09335", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Real-Time Multi-Person Eyeblink Detection in the Wild for Untrimmed Video", - "base_url": null, - "title_page": null, - "repo": "wenzhengzeng/MPEblink", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zeng_Real-Time_Multi-Person_Eyeblink_Detection_in_the_Wild_for_Untrimmed_Video_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16053", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ngME7dym0Uk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Modeling Video As Stochastic Processes for Fine-Grained Video Representation Learning", - "base_url": null, - "title_page": null, - "repo": "hengRUC/VSP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Modeling_Video_As_Stochastic_Processes_for_Fine-Grained_Video_Representation_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ANfWcISTPK8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Re2TAL: Rewiring Pretrained Video Backbones for Reversible Temporal Action Localization", - "base_url": null, - "title_page": null, - "repo": "coolbay/Re2TAL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Re2TAL_Rewiring_Pretrained_Video_Backbones_for_Reversible_Temporal_Action_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14053", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Oa29cFo_nMY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Learning Discriminative Representations for Skeleton based Action Recognition", - "base_url": null, - "title_page": null, - "repo": "zhysora/FR-Head", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Learning_Discriminative_Representations_for_Skeleton_Based_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.03729", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ix6rADaCjNs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Learning Procedure-Aware Video Representation from Instructional Videos and their Narrations", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/ProcedureVRL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yu_Learning_Procedure-Aware_Video_Representation_From_Instructional_Videos_and_Their_Narrations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17839", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "YPq-rziL8Jo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Collecting Cross-Modal Presence-Absence Evidence for Weakly-Supervised Audio-Visual Event Perception", - "base_url": null, - "title_page": null, - "repo": "MengyuanChen21/CVPR2023-CMPAE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_Collecting_Cross-Modal_Presence-Absence_Evidence_for_Weakly-Supervised_Audio-Visual_Event_Perception_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "PivoTAL: Prior-Driven Supervision for Weakly-Supervised Temporal Action Localization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rizve_PivoTAL_Prior-Driven_Supervision_for_Weakly-Supervised_Temporal_Action_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6kAoQjXfzio", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Cascade Evidential Learning for Open-World Weakly-Supervised Temporal Action Localization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Cascade_Evidential_Learning_for_Open-World_Weakly-Supervised_Temporal_Action_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Soft-Landing Strategy for Alleviating the Task Discrepancy Problem in Temporal Action Localization Tasks", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kang_Soft-Landing_Strategy_for_Alleviating_the_Task_Discrepancy_Problem_in_Temporal_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.06023", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "SVFormer: Semi-Supervised Video Transformer for Action Recognition", - "base_url": null, - "title_page": null, - "repo": "ChenHsing/SVFormer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xing_SVFormer_Semi-Supervised_Video_Transformer_for_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.13222", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "t5NjEvWRLVk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "AutoAD: Movie Description in Context", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.robots.ox.ac.uk/~vgg/research/autoad/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Han_AutoAD_Movie_Description_in_Context_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16899", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gMQSoib6lSI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "STMT: A Spatial-Temporal Mesh Transformer for MoCap-based Action Recognition", - "base_url": null, - "title_page": null, - "repo": "zgzxy001/STMT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_STMT_A_Spatial-Temporal_Mesh_Transformer_for_MoCap-Based_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.18177", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Jo5soeHw0RQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Boosting Weakly-Supervised Temporal Action Localization with Text Information", - "base_url": null, - "title_page": null, - "repo": "lgzlIlIlI/Boosting-WTAL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Boosting_Weakly-Supervised_Temporal_Action_Localization_With_Text_Information_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.00607", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "n8p4ZU85LXM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Aligning Step-by-Step Instructional Diagrams to Video Demonstrations", - "base_url": null, - "title_page": null, - "repo": "DavidZhang73/AssemblyVideoManualAlignment", - "web_page": "https://academic.davidz.cn/en/publication/zhang-cvpr-2023/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Aligning_Step-by-Step_Instructional_Diagrams_to_Video_Demonstrations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13800", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8iC5QyP8U6o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Improving Weakly Supervised Temporal Action Localization by Bridging Train-Test Gap in Pseudo Labels", - "base_url": null, - "title_page": null, - "repo": "zhou745/GauFuse_WSTAL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Improving_Weakly_Supervised_Temporal_Action_Localization_by_Bridging_Train-Test_Gap_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.07978", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Weakly Supervised Video Representation Learning with Unaligned Text for Sequential Videos", - "base_url": null, - "title_page": null, - "repo": "svip-lab/WeakSVR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dong_Weakly_Supervised_Video_Representation_Learning_With_Unaligned_Text_for_Sequential_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12370", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AqozSRYP7Pc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Dense-Localizing Audio-Visual Events in Untrimmed Videos: A Large-Scale Benchmark and Baseline", - "base_url": null, - "title_page": null, - "repo": "ttgeng233/UnAV", - "web_page": null, - "github_page": "https://unav100.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Geng_Dense-Localizing_Audio-Visual_Events_in_Untrimmed_Videos_A_Large-Scale_Benchmark_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12930", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "PPDywLMn1Js", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "LOGO: A Long-Form Video Dataset for Group Action Quality Assessment", - "base_url": null, - "title_page": null, - "repo": "shiyi-zh0408/LOGO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_LOGO_A_Long-Form_Video_Dataset_for_Group_Action_Quality_Assessment_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Search-Map-Search: A Frame Selection Paradigm for Action Recognition", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Search-Map-Search_A_Frame_Selection_Paradigm_for_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10316", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ywdf6di2QWo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "3Mformer: Multi-Order Multi-Mode Transformer for Skeletal Action Recognition", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_3Mformer_Multi-Order_Multi-Mode_Transformer_for_Skeletal_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14474", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_LzrzFIuaNU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "ProTeGe: Untrimmed Pretraining for Video Temporal Grounding by Video Temporal Grounding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_ProTeGe_Untrimmed_Pretraining_for_Video_Temporal_Grounding_by_Video_Temporal_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Egocentric Video Task Translation", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/EgoT2", - "web_page": "https://vision.cs.utexas.edu/projects/egot2/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xue_Egocentric_Video_Task_Translation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06301", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "HHWLMFIZ5ow", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Look Around for Anomalies: Weakly-Supervised Anomaly Detection via Context-Motion Relational Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cho_Look_Around_for_Anomalies_Weakly-Supervised_Anomaly_Detection_via_Context-Motion_Relational_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "31ccYdwGDG8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Proposal-based Multiple Instance Learning for Weakly-Supervised Temporal Action Localization", - "base_url": null, - "title_page": null, - "repo": "RenHuan1999/CVPR2023_P-MIL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ren_Proposal-Based_Multiple_Instance_Learning_for_Weakly-Supervised_Temporal_Action_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.17861", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hfHGlKyOQ68", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "TriDet: Temporal Action Detection with Relative Boundary Modeling", - "base_url": null, - "title_page": null, - "repo": "dingfengshi/TriDet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Shi_TriDet_Temporal_Action_Detection_With_Relative_Boundary_Modeling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07347", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "f1gJkUI6rA4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Actionlet-Dependent Contrastive Learning for Unsupervised Skeleton-based Action Recognition", - "base_url": null, - "title_page": null, - "repo": "LanglandsLin/ActCLR", - "web_page": null, - "github_page": "https://langlandslin.github.io/projects/ActCLR/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Actionlet-Dependent_Contrastive_Learning_for_Unsupervised_Skeleton-Based_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10904", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jwX0Zc8s10w", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "EVAL: Explainable Video Anomaly Localization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Singh_EVAL_Explainable_Video_Anomaly_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.07900", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6x8GUDWkN68", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Rethinking Video ViTs: Sparse Video Tubes for Joint Image and Video Learning", - "base_url": null, - "title_page": null, - "repo": "daniel-code/TubeViT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Piergiovanni_Rethinking_Video_ViTs_Sparse_Video_Tubes_for_Joint_Image_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03229", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Weakly Supervised Temporal Sentence Grounding with Uncertainty-guided Self-Training", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Weakly_Supervised_Temporal_Sentence_Grounding_With_Uncertainty-Guided_Self-Training_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KyXVUlBjiZ4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Leveraging Temporal Context in Low Representational Power Regimes", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://camilofosco.com/etm_website/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fosco_Leveraging_Temporal_Context_in_Low_Representational_Power_Regimes_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "a5-gWsUMVXw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "PIVOT: Prompting for Video Continual Learning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Villa_PIVOT_Prompting_for_Video_Continual_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04842", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "On the Benefits of 3D Pose and Tracking for Human Action Recognition", - "base_url": null, - "title_page": null, - "repo": "brjathu/LART", - "web_page": "https://people.eecs.berkeley.edu/~jathushan/LART/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rajasegaran_On_the_Benefits_of_3D_Pose_and_Tracking_for_Human_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.01199", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "NaQ: Leveraging Narrations as Queries to Supervise Episodic Memory", - "base_url": null, - "title_page": null, - "repo": "srama2512/NaQ", - "web_page": "https://vision.cs.utexas.edu/projects/naq/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ramakrishnan_NaQ_Leveraging_Narrations_As_Queries_To_Supervise_Episodic_Memory_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.00746", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Selective Structured State-Spaces for Long-Form Video Understanding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Selective_Structured_State-Spaces_for_Long-Form_Video_Understanding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14526", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "CcQHyaZLIpQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Frame Flexible Network", - "base_url": null, - "title_page": null, - "repo": "BeSpontaneous/FFN-pytorch", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Frame_Flexible_Network_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14817", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JFHqyw20T8M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "ASPnet: Action Segmentation with Shared-Private Representation of Multiple Data Sources", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/van_Amsterdam_ASPnet_Action_Segmentation_With_Shared-Private_Representation_of_Multiple_Data_Sources_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Unified Keypoint-based Action Recognition Framework via Structured Keypoint Pooling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hachiuma_Unified_Keypoint-Based_Action_Recognition_Framework_via_Structured_Keypoint_Pooling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15270", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Learning Transferable Spatiotemporal Representations from Natural Script Knowledge", - "base_url": null, - "title_page": null, - "repo": "TencentARC/TVTS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zeng_Learning_Transferable_Spatiotemporal_Representations_From_Natural_Script_Knowledge_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.15280", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Jlpe75bsYUg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Masked Video Distillation: Rethinking Masked Feature Modeling for Self-Supervised Video Representation Learning", - "base_url": null, - "title_page": null, - "repo": "ruiwang2021/mvd", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Masked_Video_Distillation_Rethinking_Masked_Feature_Modeling_for_Self-Supervised_Video_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04500", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "btxcb-5NfWo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Bidirectional Cross-Modal Knowledge Exploration for Video Recognition with Pre-trained Vision-Language Models", - "base_url": null, - "title_page": null, - "repo": "whwu95/BIKE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Bidirectional_Cross-Modal_Knowledge_Exploration_for_Video_Recognition_With_Pre-Trained_Vision-Language_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.00182", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "cjEvOcN-bmI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Procedure-Aware Pretraining for Instructional Video Understanding", - "base_url": null, - "title_page": null, - "repo": "salesforce/paprika", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Procedure-Aware_Pretraining_for_Instructional_Video_Understanding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.18230", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NvuPQbhC3Qo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Latency Matters: Real-Time Action Forecasting Transformer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://karttikeya.github.io/publication/RAFTformer/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Girase_Latency_Matters_Real-Time_Action_Forecasting_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0tbK36hzSM0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Generating Anomalies for Video Anomaly Detection with Prompt-based Feature Mapping", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Generating_Anomalies_for_Video_Anomaly_Detection_With_Prompt-Based_Feature_Mapping_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "iYGfdd3t4ZE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "HierVL: Learning Hierarchical Video-Language Embeddings", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/HierVL", - "web_page": "https://vision.cs.utexas.edu/projects/hiervl/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ashutosh_HierVL_Learning_Hierarchical_Video-Language_Embeddings_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02311", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "I5FIGHc_H5I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Two-Stream Networks for Weakly-Supervised Temporal Action Localization with Semantic-Aware Mechanisms", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Two-Stream_Networks_for_Weakly-Supervised_Temporal_Action_Localization_With_Semantic-Aware_Mechanisms_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "emPtOrt3v2Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Hybrid Active Learning via Deep Clustering for Video Action Detection", - "base_url": null, - "title_page": null, - "repo": "aayushjr/HybridCLAUS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rana_Hybrid_Active_Learning_via_Deep_Clustering_for_Video_Action_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nPNAUdLbmCQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Prompt-guided Zero-Shot Anomaly Action Recognition using Pretrained Deep Skeleton Features", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sato_Prompt-Guided_Zero-Shot_Anomaly_Action_Recognition_Using_Pretrained_Deep_Skeleton_Features_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15167", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Unbiased Multiple Instance Learning for Weakly Supervised Video Anomaly Detection", - "base_url": null, - "title_page": null, - "repo": "ktr-hubrt/UMIL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lv_Unbiased_Multiple_Instance_Learning_for_Weakly_Supervised_Video_Anomaly_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12369", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "GVSzmgpxDHc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking", - "base_url": null, - "title_page": null, - "repo": "OpenGVLab/VideoMAEv2", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_VideoMAE_V2_Scaling_Video_Masked_Autoencoders_With_Dual_Masking_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16727", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "PDPP: Projected Diffusion for Procedure Planning in Instructional Videos", - "base_url": null, - "title_page": null, - "repo": "MCG-NJU/PDPP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_PDPPProjected_Diffusion_for_Procedure_Planning_in_Instructional_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14676", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "_8IvuN9rjxo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Learning Action Changes by Measuring Verb-Adverb Textual Relationships", - "base_url": null, - "title_page": null, - "repo": "dmoltisanti/air-cvpr23", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Moltisanti_Learning_Action_Changes_by_Measuring_Verb-Adverb_Textual_Relationships_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15086", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "orQ3YgVMXYk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Reducing the Label Bias for Timestamp Supervised Temporal Action Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Reducing_the_Label_Bias_for_Timestamp_Supervised_Temporal_Action_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KH7lZiQgqBU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Video Event Restoration based on Keyframes for Video Anomaly Detection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Video_Event_Restoration_Based_on_Keyframes_for_Video_Anomaly_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05112", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "IXf1ERTkAH0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Active Exploration of Multimodal Complementarity for Few-Shot Action Recognition", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wanyan_Active_Exploration_of_Multimodal_Complementarity_for_Few-Shot_Action_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Skd4p5G0wgM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Vita-CLIP: Video and Text Adaptive CLIP via Multimodal Prompting", - "base_url": null, - "title_page": null, - "repo": "TalalWasim/Vita-CLIP", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wasim_Vita-CLIP_Video_and_Text_Adaptive_CLIP_via_Multimodal_Prompting_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03307", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Post-Processing Temporal Action Detection", - "base_url": null, - "title_page": null, - "repo": "sauradip/GAP", - "web_page": null, - "github_page": "https://sauradip.github.io/project_pages/GAP/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nag_Post-Processing_Temporal_Action_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.14924", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "sV4Hg46Qa-A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Relational Space-Time Query in Long-Form Videos", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Relational_Space-Time_Query_in_Long-Form_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7qtu6-u3Ggo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Therbligs in Action: Video Understanding through Motion Primitives", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dessalene_Therbligs_in_Action_Video_Understanding_Through_Motion_Primitives_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.03631", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Dual-Path Adaptation from Image to Video Transformers", - "base_url": null, - "title_page": null, - "repo": "park-jungin/DualPath", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Park_Dual-Path_Adaptation_From_Image_to_Video_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09857", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Hierarchical Semantic Contrast for Scene-Aware Video Anomaly Detection", - "base_url": null, - "title_page": null, - "repo": "shengyangsun/HSC_VAD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sun_Hierarchical_Semantic_Contrast_for_Scene-Aware_Video_Anomaly_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13051", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Exploiting Completeness and Uncertainty of Pseudo Labels for Weakly Supervised Video Anomaly Detection", - "base_url": null, - "title_page": null, - "repo": "ArielZc/CU-Net", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Exploiting_Completeness_and_Uncertainty_of_Pseudo_Labels_for_Weakly_Supervised_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.04090", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TpRkCnDyFNY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - }, - { - "title": "Unbiased Scene Graph Generation in Videos", - "base_url": null, - "title_page": null, - "repo": "sayaknag/unbiasedSGG", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nag_Unbiased_Scene_Graph_Generation_in_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00733", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "JkpfcZ6dXEA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Action and Event Understanding" - } -] \ No newline at end of file diff --git a/json_data/video-low-level-analysis-motion-and-tracking.json b/json_data/video-low-level-analysis-motion-and-tracking.json deleted file mode 100644 index 9bfee7e..0000000 --- a/json_data/video-low-level-analysis-motion-and-tracking.json +++ /dev/null @@ -1,1152 +0,0 @@ -[ - { - "title": "Uncovering the Missing Pattern: Unified Framework Towards Trajectory Imputation and Prediction", - "base_url": null, - "title_page": null, - "repo": "colorfulfuture/GC-VRNN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Uncovering_the_Missing_Pattern_Unified_Framework_Towards_Trajectory_Imputation_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16005", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fneLvMJIALo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Tracking Multiple Deformable Objects in Egocentric Videos", - "base_url": null, - "title_page": null, - "repo": "Mingzhen-Huang/DETracker", - "web_page": null, - "github_page": "https://mingzhenhuang.com/projects/detracker.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Tracking_Multiple_Deformable_Objects_in_Egocentric_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Tracking through Containers and Occluders in the Wild", - "base_url": null, - "title_page": null, - "repo": "basilevh/tcow", - "web_page": "https://tcow.cs.columbia.edu/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Van_Hoorick_Tracking_Through_Containers_and_Occluders_in_the_Wild_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.03052", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WODiwfq9d2g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "TarViS: A Unified Approach for Target-based Video Segmentation", - "base_url": null, - "title_page": null, - "repo": "Ali2500/TarViS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Athar_TarViS_A_Unified_Approach_for_Target-Based_Video_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2301.02657", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qecFRmSYq40", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "VideoTrack: Learning to Track Objects via Video Transformer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xie_VideoTrack_Learning_To_Track_Objects_via_Video_Transformer_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "v-SvFZ0FrF8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "ARKitTrack: A New Diverse Dataset for Tracking using Mobile RGB-D Data", - "base_url": null, - "title_page": null, - "repo": "lawrence-cj/ARKitTrack", - "web_page": null, - "github_page": "https://arkittrack.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_ARKitTrack_A_New_Diverse_Dataset_for_Tracking_Using_Mobile_RGB-D_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13885", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "r02f6egcpdw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "A Dynamic Multi-Scale Voxel Flow Network for Video Prediction", - "base_url": null, - "title_page": null, - "repo": "megvii-research/CVPR2023-DMVFN", - "web_page": null, - "github_page": "https://huxiaotaostasy.github.io/DMVFN/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hu_A_Dynamic_Multi-Scale_Voxel_Flow_Network_for_Video_Prediction_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.09875", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rlghCGbAqUo", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Representation Learning for Visual Object Tracking by Masked Appearance Transfer", - "base_url": null, - "title_page": null, - "repo": "difhnp/MAT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Representation_Learning_for_Visual_Object_Tracking_by_Masked_Appearance_Transfer_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "EqMotion: Equivariant Multi-Agent Motion Prediction with Invariant Interaction Reasoning", - "base_url": null, - "title_page": null, - "repo": "MediaBrain-SJTU/EqMotion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_EqMotion_Equivariant_Multi-Agent_Motion_Prediction_With_Invariant_Interaction_Reasoning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10876", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ROactuGU1YA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Semi-Supervised Video Inpainting with Cycle Consistency Constraints", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Semi-Supervised_Video_Inpainting_With_Cycle_Consistency_Constraints_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.06807", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Generalized Relation Modeling for Transformer Tracking", - "base_url": null, - "title_page": null, - "repo": "Little-Podi/GRM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gao_Generalized_Relation_Modeling_for_Transformer_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16580", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bQKN3HV-8XI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Breaking the Object in Video Object Segmentation", - "base_url": null, - "title_page": null, - "repo": "TRI-ML/VOST", - "web_page": "https://www.vostdataset.org/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tokmakov_Breaking_the_Object_in_Video_Object_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06200", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "SBdA6HCXf_M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Unifying Short and Long-Term Tracking with Graph Hierarchies", - "base_url": null, - "title_page": null, - "repo": "dvl-tum/SUSHI", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cetintas_Unifying_Short_and_Long-Term_Tracking_With_Graph_Hierarchies_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.03038", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Q1TiZukGQYQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Simple Cues Lead to a Strong Multi-Object Tracker", - "base_url": null, - "title_page": null, - "repo": "dvl-tum/GHOST", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Seidenschwarz_Simple_Cues_Lead_to_a_Strong_Multi-Object_Tracker_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.04656", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3gozhzOHwE0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Unified Mask Embedding and Correspondence Learning for Self-Supervised Video Segmentation", - "base_url": null, - "title_page": null, - "repo": "0liliulei/Mask-VOS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Unified_Mask_Embedding_and_Correspondence_Learning_for_Self-Supervised_Video_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10100", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LJj4frqBgqY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "MOTRv2: Bootstrapping End-to-End Multi-Object Tracking by Pretrained Object Detectors", - "base_url": null, - "title_page": null, - "repo": "megvii-research/MOTRv2", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_MOTRv2_Bootstrapping_End-to-End_Multi-Object_Tracking_by_Pretrained_Object_Detectors_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.09791", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7WnQgQLQLE4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "SeqTrack: Sequence to Sequence Learning for Visual Object Tracking", - "base_url": null, - "title_page": null, - "repo": "microsoft/VideoX", - "web_page": null, - "github_page": "https://github.com/microsoft/VideoX/tree/master/SeqTrack", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_SeqTrack_Sequence_to_Sequence_Learning_for_Visual_Object_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.14394", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "jb_zZqrEcJA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Joint Visual Grounding and Tracking with Natural Language Specification", - "base_url": null, - "title_page": null, - "repo": "lizhou-cs/JointNLT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhou_Joint_Visual_Grounding_and_Tracking_With_Natural_Language_Specification_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12027", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "kUN7tchiG2Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Boosting Video Object Segmentation via Space-Time Correspondence Learning", - "base_url": null, - "title_page": null, - "repo": "wenguanwang/VOS_Correspondence", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Boosting_Video_Object_Segmentation_via_Space-Time_Correspondence_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.06211", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Visual Prompt Multi-Modal Tracking", - "base_url": null, - "title_page": null, - "repo": "jiawen-zhu/ViPT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_Visual_Prompt_Multi-Modal_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10826", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "OVTrack: Open-Vocabulary Multiple Object Tracking", - "base_url": null, - "title_page": null, - "repo": "SysCV/ovtrack", - "web_page": "https://www.vis.xyz/pub/ovtrack/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_OVTrack_Open-Vocabulary_Multiple_Object_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08408", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tMQ_sh0JbpY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "TransFlow: Transformer as Flow Learner", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lu_TransFlow_Transformer_As_Flow_Learner_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11523", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "xbnyj9wspqA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Focus on Details: Online Multi-Object Tracking with Diverse Fine-grained Representation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ren_Focus_on_Details_Online_Multi-Object_Tracking_With_Diverse_Fine-Grained_Representation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14589", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "j4TJJEsqllM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Autoregressive Visual Tracking", - "base_url": null, - "title_page": null, - "repo": "MIV-XJTU/ARTrack", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wei_Autoregressive_Visual_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fOkpG5SNaX0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Bootstrapping Objectness from Videos by Relaxed Common Fate and Visual Grouping", - "base_url": null, - "title_page": null, - "repo": "TonyLianLong/RCF-UnsupVideoSeg", - "web_page": null, - "github_page": "https://rcf-video.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lian_Bootstrapping_Objectness_From_Videos_by_Relaxed_Common_Fate_and_Visual_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08025", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dyaDEvT4YkY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Tangentially Elongated Gaussian Belief Propagation for Event-based Incremental Optical Flow Estimation", - "base_url": null, - "title_page": null, - "repo": "DensoITLab/tegbp", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Nagata_Tangentially_Elongated_Gaussian_Belief_Propagation_for_Event-Based_Incremental_Optical_Flow_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rClkk5MY33A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Bridging Search Region Interaction with Template for RGB-T Tracking", - "base_url": null, - "title_page": null, - "repo": "RyanHTR/TBSI", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hui_Bridging_Search_Region_Interaction_With_Template_for_RGB-T_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Efficient RGB-T Tracking via Cross-Modality Distillation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Efficient_RGB-T_Tracking_via_Cross-Modality_Distillation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "isTrxcb1dVs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "MotionTrack: Learning Robust Short-Term and Long-Term Motions for Multi-Object Tracking", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Qin_MotionTrack_Learning_Robust_Short-Term_and_Long-Term_Motions_for_Multi-Object_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10404", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "HaS9cM75J7Y", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Self-Supervised AutoFlow", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Huang_Self-Supervised_AutoFlow_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.01762", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "e8EuIgzJeYc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "UTM: A Unified Multiple Object Tracking Model with Identity-Aware Feature Enhancement", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/You_UTM_A_Unified_Multiple_Object_Tracking_Model_With_Identity-Aware_Feature_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qLR4WJVi5O4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "BiFormer: Learning Bilateral Motion Estimation via Bilateral Transformer for 4K Video Frame Interpolation", - "base_url": null, - "title_page": null, - "repo": "JunHeum/BiFormer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Park_BiFormer_Learning_Bilateral_Motion_Estimation_via_Bilateral_Transformer_for_4K_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02225", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Spatial-then-Temporal Self-Supervised Learning for Video Correspondence", - "base_url": null, - "title_page": null, - "repo": "qianduoduolr/Spa-then-Temp", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Spatial-Then-Temporal_Self-Supervised_Learning_for_Video_Correspondence_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.07778", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tN-PRaLS_pw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown Objects", - "base_url": null, - "title_page": null, - "repo": "NVlabs/BundleSDF", - "web_page": null, - "github_page": "https://bundlesdf.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wen_BundleSDF_Neural_6-DoF_Tracking_and_3D_Reconstruction_of_Unknown_Objects_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14158", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XH5t0wEH3d0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "MED-VT: Multiscale Encoder-Decoder Video Transformer with Application to Object Segmentation", - "base_url": null, - "title_page": null, - "repo": "rkyuca/medvt", - "web_page": null, - "github_page": "https://rkyuca.github.io/medvt/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Karim_MED-VT_Multiscale_Encoder-Decoder_Video_Transformer_With_Application_To_Object_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.05930", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "nVb9aVPyr4I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Context-Aware Relative Object Queries to Unify Video Instance and Panoptic Segmentation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Choudhuri_Context-Aware_Relative_Object_Queries_To_Unify_Video_Instance_and_Panoptic_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "N6A9Q8Nji7M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Unsupervised Space-Time Network for Temporally-Consistent Segmentation of Multiple Motions", - "base_url": null, - "title_page": null, - "repo": "Etienne-Meunier-Inria/ST-Space-Time-Flow-Segmentation", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Meunier_Unsupervised_Space-Time_Network_for_Temporally-Consistent_Segmentation_of_Multiple_Motions_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "fZHEOJeDQoc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Resource-Efficient RGBD Aerial Tracking", - "base_url": null, - "title_page": null, - "repo": "yjybuaa/RGBDAerialTracking", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Resource-Efficient_RGBD_Aerial_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "yJ4Hsh8S2iA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "MMVC: Learned Multi-Mode Video Compression with Block-based Prediction Mode Selection and Density-Adaptive Entropy Coding", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_MMVC_Learned_Multi-Mode_Video_Compression_With_Block-Based_Prediction_Mode_Selection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.02273", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "mt7smZiL4CA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Streaming Video Model", - "base_url": null, - "title_page": null, - "repo": "yuzhms/Streaming-Video-Model", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhao_Streaming_Video_Model_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17228", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Weakly Supervised Class-Agnostic Motion Prediction for Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": "L1bra1/WeakMotion", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Weakly_Supervised_Class-Agnostic_Motion_Prediction_for_Autonomous_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Q6CcZ6uPqhI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "LSTFE-Net: Long Short-Term Feature Enhancement Network for Video Small Object Detection", - "base_url": null, - "title_page": null, - "repo": "xiaojs18/LSTFE-Net", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xiao_LSTFE-NetLong_Short-Term_Feature_Enhancement_Network_for_Video_Small_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "f3vX21qP_hA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "DistractFlow: Improving Optical Flow Estimation via Realistic Distractions and Pseudo-Labeling", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jeong_DistractFlow_Improving_Optical_Flow_Estimation_via_Realistic_Distractions_and_Pseudo-Labeling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14078", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "SCOTCH and SODA: A Transformer Video Shadow Detection Framework", - "base_url": null, - "title_page": null, - "repo": "lihaoliu-cambridge/scotch-and-soda", - "web_page": null, - "github_page": "https://lihaoliu-cambridge.github.io/scotch_and_soda/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_SCOTCH_and_SODA_A_Transformer_Video_Shadow_Detection_Framework_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.06885", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "ZBS: Zero-Shot Background Subtraction via Instance-Level Background Modeling and Foreground Selection", - "base_url": null, - "title_page": null, - "repo": "CASIA-IVA-Lab/ZBS", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/An_ZBS_Zero-Shot_Background_Subtraction_via_Instance-Level_Background_Modeling_and_Foreground_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14679", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "-WuowqTbFIw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - }, - { - "title": "Frame-Event Alignment and Fusion Network for High Frame Rate Tracking", - "base_url": null, - "title_page": null, - "repo": "Jee-King/AFNet", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Frame-Event_Alignment_and_Fusion_Network_for_High_Frame_Rate_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.15688", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "W7EjOiGMiAQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Video: Low-Level Analysis, Motion, and Tracking" - } -] \ No newline at end of file diff --git a/json_data/vision-and-graphics.json b/json_data/vision-and-graphics.json deleted file mode 100644 index 3e4f9ea..0000000 --- a/json_data/vision-and-graphics.json +++ /dev/null @@ -1,802 +0,0 @@ -[ - { - "title": "NeUDF: Leaning Neural Unsigned Distance Fields with Volume Rendering", - "base_url": null, - "title_page": null, - "repo": "IGLICT/NeUDF", - "web_page": "http://geometrylearning.com/neudf/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_NeUDF_Leaning_Neural_Unsigned_Distance_Fields_With_Volume_Rendering_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.10080", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "4GPjRm7PX9I", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "RaBit: Parametric Modeling of 3D Biped Cartoon Characters with a Topological-Consistent Dataset", - "base_url": null, - "title_page": null, - "repo": "zhongjinluo/RaBit", - "web_page": "https://gaplab.cuhk.edu.cn/projects/RaBit/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_RaBit_Parametric_Modeling_of_3D_Biped_Cartoon_Characters_With_a_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12564", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "sxQWx-6e4hA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "DualVector: Unsupervised Vector Font Synthesis with Dual-Part Representation", - "base_url": null, - "title_page": null, - "repo": "thuliu-yt16/dualvector", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_DualVector_Unsupervised_Vector_Font_Synthesis_With_Dual-Part_Representation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.10462", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "13fpqGBg0-A", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Magic3D: High-Resolution Text-to-3D Content Creation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://research.nvidia.com/labs/dir/magic3d/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Magic3D_High-Resolution_Text-to-3D_Content_Creation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.10440", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "F1ZNshgvWOA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Pointersect: Neural Rendering with Cloud-Ray Intersection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chang_Pointersect_Neural_Rendering_With_Cloud-Ray_Intersection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.12390", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "7gbhc7ImCps", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Humans as Light Bulbs: 3D Human Reconstruction from Thermal Reflection", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://thermal.cs.columbia.edu/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_Humans_As_Light_Bulbs_3D_Human_Reconstruction_From_Thermal_Reflection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.01652", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "ABLE-NeRF: Attention-based Rendering with Learnable Embeddings for Neural Radiance Field", - "base_url": null, - "title_page": null, - "repo": "TangZJ/able-nerf", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_ABLE-NeRF_Attention-Based_Rendering_With_Learnable_Embeddings_for_Neural_Radiance_Field_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13817", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "JAWS: Just A Wild Shot for Cinematic Transfer in Neural Radiance Fields", - "base_url": null, - "title_page": null, - "repo": "robincourant/jaws", - "web_page": "https://www.lix.polytechnique.fr/vista/projects/2023_cvpr_wang/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_JAWS_Just_a_Wild_Shot_for_Cinematic_Transfer_in_Neural_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15427", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "d0XtVqa5bdY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "LayoutDM: Discrete Diffusion Model for Controllable Layout Generation", - "base_url": null, - "title_page": null, - "repo": "CyberAgentAILab/layout-dm", - "web_page": null, - "github_page": "https://cyberagentailab.github.io/layout-dm/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Inoue_LayoutDM_Discrete_Diffusion_Model_for_Controllable_Layout_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.08137", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "bJOpJnvhw3s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "LightPainter: Interactive Portrait Relighting with Freehand Scribble", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Mei_LightPainter_Interactive_Portrait_Relighting_With_Freehand_Scribble_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12950", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "RODIN: A Generative Model for Sculpting 3D Digital Avatars using Diffusion", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://3d-avatar-diffusion.microsoft.com/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_RODIN_A_Generative_Model_for_Sculpting_3D_Digital_Avatars_Using_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.06135", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KW_EXWMjS4c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "NerVE: Neural Volumetric Edges for Parametric Curve Extraction from Point Cloud", - "base_url": null, - "title_page": null, - "repo": "uhzoaix/NerVE", - "web_page": null, - "github_page": "https://dongdu3.github.io/projects/2023/NerVE/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhu_NerVE_Neural_Volumetric_Edges_for_Parametric_Curve_Extraction_From_Point_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.16465", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tAwC23uybTM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "CAMS: CAnonicalized Manipulation Spaces for Category-Level Functional Hand-Object Manipulation Synthesis", - "base_url": null, - "title_page": null, - "repo": "cams-hoi/CAMS", - "web_page": null, - "github_page": "https://cams-hoi.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zheng_CAMS_CAnonicalized_Manipulation_Spaces_for_Category-Level_Functional_Hand-Object_Manipulation_Synthesis_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15469", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KEfhwICagcM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "VecFontSDF: Learning to Reconstruct and Synthesize High-Quality Vector Fonts via Signed Distance Functions", - "base_url": null, - "title_page": null, - "repo": "ymxbj/VecFontSDF", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xia_VecFontSDF_Learning_To_Reconstruct_and_Synthesize_High-Quality_Vector_Fonts_via_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12675", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "HyOubSJMyf0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Generalized Deep 3D Shape Prior via Part-Discretized Diffusion Process", - "base_url": null, - "title_page": null, - "repo": "colorful-liyu/3DQD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Generalized_Deep_3D_Shape_Prior_via_Part-Discretized_Diffusion_Process_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10406", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "3NEM4Sjlb9E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Latent-NeRF for Shape-Guided Generation of 3D Shapes and Textures", - "base_url": null, - "title_page": null, - "repo": "eladrich/latent-nerf", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Metzer_Latent-NeRF_for_Shape-Guided_Generation_of_3D_Shapes_and_Textures_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.07600", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WwOXzWvGNdc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Parts2Words: Learning Joint Embedding of Point Clouds and Texts by Bidirectional Matching between Parts and Words", - "base_url": null, - "title_page": null, - "repo": "JLUtangchuan/Parts2Words", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Parts2Words_Learning_Joint_Embedding_of_Point_Clouds_and_Texts_by_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2107.01872", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "cZ76xXEY6mY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Multiplicative Fourier Level of Detail", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Dou_Multiplicative_Fourier_Level_of_Detail_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "8DakAzpxecI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "SECAD-Net: Self-Supervised CAD Reconstruction by Learning Sketch-Extrude Operations", - "base_url": null, - "title_page": null, - "repo": "BunnySoCrazy/SECAD-Net", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_SECAD-Net_Self-Supervised_CAD_Reconstruction_by_Learning_Sketch-Extrude_Operations_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.10613", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "953PCsY5L98", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Transfer4D: A Framework for Frugal Motion Capture and Deformation Transfer", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://transfer4d.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Maheshwari_Transfer4D_A_Framework_for_Frugal_Motion_Capture_and_Deformation_Transfer_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "a1-cUxHwvo8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Plateau-Reduced Differentiable Path Tracing", - "base_url": null, - "title_page": null, - "repo": "mfischer-ucl/prdpt", - "web_page": null, - "github_page": "https://mfischer-ucl.github.io/prdpt/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fischer_Plateau-Reduced_Differentiable_Path_Tracing_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.17263", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "KJlJbqJ4wwY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "3D Highlighter: Localizing Regions on 3D Shapes via Text Descriptions", - "base_url": null, - "title_page": null, - "repo": "threedle/3DHighlighter", - "web_page": null, - "github_page": "https://threedle.github.io/3DHighlighter/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Decatur_3D_Highlighter_Localizing_Regions_on_3D_Shapes_via_Text_Descriptions_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.11263", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "OKPySDDCdd0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Differentiable Shadow Mapping for Efficient Inverse Graphics", - "base_url": null, - "title_page": null, - "repo": "mworchel/differentiable-shadow-mapping", - "web_page": null, - "github_page": "https://mworchel.github.io/differentiable-shadow-mapping/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Worchel_Differentiable_Shadow_Mapping_for_Efficient_Inverse_Graphics_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2308.10896", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "474Ix9ASbNA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Inverse Rendering of Translucent Objects using Physical and Neural Renderers", - "base_url": null, - "title_page": null, - "repo": "ligoudaner377/homo_translucent", - "web_page": null, - "github_page": "https://ligoudaner377.github.io/homo_translucent/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Inverse_Rendering_of_Translucent_Objects_Using_Physical_and_Neural_Renderers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.08336", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rWZLU_YqacE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "MAIR: Multi-View Attention Inverse Rendering with 3D Spatially-Varying Lighting Estimation", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://bring728.github.io/mair.project/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Choi_MAIR_Multi-View_Attention_Inverse_Rendering_With_3D_Spatially-Varying_Lighting_Estimation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12368", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "58ql5xJfN3M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Neural Fourier Filter Bank", - "base_url": null, - "title_page": null, - "repo": "ubc-vision/NFFB", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wu_Neural_Fourier_Filter_Bank_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.01735", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "uO3MxxZY6XI", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "UMat: Uncertainty-Aware Single Image High Resolution Material Capture", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://carlosrodriguezpardo.es/projects/UMat/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Rodriguez-Pardo_UMat_Uncertainty-Aware_Single_Image_High_Resolution_Material_Capture_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2305.16312", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ULbGvHFrJx4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Neural Congealing: Aligning Images to a Joint Semantic Atlas", - "base_url": null, - "title_page": null, - "repo": "dolev104/neural_congealing", - "web_page": null, - "github_page": "https://neural-congealing.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ofri-Amar_Neural_Congealing_Aligning_Images_to_a_Joint_Semantic_Atlas_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.03956", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "dlzkVB3680Q", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "PlenVDB: Memory Efficient VDB-based Radiance Fields for Fast Training and Rendering", - "base_url": null, - "title_page": null, - "repo": "wolfball/PlenVDB", - "web_page": null, - "github_page": "https://plenvdb.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yan_PlenVDB_Memory_Efficient_VDB-Based_Radiance_Fields_for_Fast_Training_and_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "y0DNT0Hahic", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "VectorFloorSeg: Two-Stream Graph Attention Network for Vectorized Roughcast Floorplan Segmentation", - "base_url": null, - "title_page": null, - "repo": "DrZiji/VecFloorSeg", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_VectorFloorSeg_Two-Stream_Graph_Attention_Network_for_Vectorized_Roughcast_Floorplan_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wkZoF5EBoiY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "Learning to Render Novel Views from Wide-Baseline Stereo Pairs", - "base_url": null, - "title_page": null, - "repo": "yilundu/cross_attention_renderer", - "web_page": null, - "github_page": "https://yilundu.github.io/wide_baseline/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Du_Learning_To_Render_Novel_Views_From_Wide-Baseline_Stereo_Pairs_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.08463", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - }, - { - "title": "CLIP-Sculptor: Zero-Shot Generation of High-Fidelity and Diverse Shapes from Natural Language", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://ivl.cs.brown.edu/research/clip-sculptor.html", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sanghi_CLIP-Sculptor_Zero-Shot_Generation_of_High-Fidelity_and_Diverse_Shapes_From_Natural_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.01427", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision and Graphics" - } -] \ No newline at end of file diff --git a/json_data/vision-applications-and-systems.json b/json_data/vision-applications-and-systems.json deleted file mode 100644 index 63ee823..0000000 --- a/json_data/vision-applications-and-systems.json +++ /dev/null @@ -1,877 +0,0 @@ -[ - { - "title": "Context De-confounded Emotion Recognition", - "base_url": null, - "title_page": null, - "repo": "ydk122024/CCIM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Context_De-Confounded_Emotion_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.11921", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "TGnI4U504Vg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Intrinsic Physical Concepts Discovery with Object-Centric Predictive Models", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Tang_Intrinsic_Physical_Concepts_Discovery_With_Object-Centric_Predictive_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01869", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "N3_YAcRPf38", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Automatic High Resolution Wire Segmentation and Removal", - "base_url": null, - "title_page": null, - "repo": "adobe-research/auto-wire-removal", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chiu_Automatic_High_Resolution_Wire_Segmentation_and_Removal_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.00221", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Class Balanced Adaptive Pseudo Labeling for Federated Semi-Supervised Learning", - "base_url": null, - "title_page": null, - "repo": "minglllli/CBAFed", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Class_Balanced_Adaptive_Pseudo_Labeling_for_Federated_Semi-Supervised_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "f8Ekx-cnNsA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Weakly Supervised Video Emotion Detection and Prediction via Cross-Modal Temporal Erasing Network", - "base_url": null, - "title_page": null, - "repo": "nku-zhichengzhang/CTEN", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Weakly_Supervised_Video_Emotion_Detection_and_Prediction_via_Cross-Modal_Temporal_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ebD_xNQLuCY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Probing Sentiment-Oriented Pre-Training Inspired by Human Sentiment Perception Mechanism", - "base_url": null, - "title_page": null, - "repo": "tinglyfeng/sentiment_pretraining", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Feng_Probing_Sentiment-Oriented_Pre-Training_Inspired_by_Human_Sentiment_Perception_Mechanism_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wyDbpXxCbKs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "DIP: Dual Incongruity Perceiving Network for Sarcasm Detection", - "base_url": null, - "title_page": null, - "repo": "downdric/MSD", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wen_DIP_Dual_Incongruity_Perceiving_Network_for_Sarcasm_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "AM94eSC-_zA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Adaptive Human Matting for Dynamic Videos", - "base_url": null, - "title_page": null, - "repo": "microsoft/AdaM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Lin_Adaptive_Human_Matting_for_Dynamic_Videos_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.06018", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "0yL6mQNUDUs", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "LayoutFormer++: Conditional Graphic Layout Generation via Constraint Serialization and Decoding Space Restriction", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Jiang_LayoutFormer_Conditional_Graphic_Layout_Generation_via_Constraint_Serialization_and_Decoding_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.08037", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Prototypical Residual Networks for Anomaly Detection and Localization", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zhang_Prototypical_Residual_Networks_for_Anomaly_Detection_and_Localization_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.02031", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ugnl25vg6K8", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Are Binary Annotations Sufficient? Video Moment Retrieval via Hierarchical Uncertainty-based Active Learning", - "base_url": null, - "title_page": null, - "repo": "renjie-liang/HUAL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ji_Are_Binary_Annotations_Sufficient_Video_Moment_Retrieval_via_Hierarchical_Uncertainty-Based_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Affordance Grounding from Demonstration Video to Target Image", - "base_url": null, - "title_page": null, - "repo": "showlab/afformer", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chen_Affordance_Grounding_From_Demonstration_Video_To_Target_Image_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14644", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ER7RtmJX8SM", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Natural Language-Assisted Sign Language Recognition", - "base_url": null, - "title_page": null, - "repo": "FangyunWei/SLRT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zuo_Natural_Language-Assisted_Sign_Language_Recognition_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12080", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "tvvT7AdxjvQ", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "CiCo: Domain-Aware Sign Language Retrieval via Cross-Lingual Contrastive Learning", - "base_url": null, - "title_page": null, - "repo": "FangyunWei/SLRT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Bao_CiCo_Domain-Aware_Sign_Language_Retrieval_via_Cross-Lingual_Contrastive_Learning_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12793", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "G4sgfXU27Sw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Mask DINO: Towards A Unified Transformer-based Framework for Object Detection and Segmentation", - "base_url": null, - "title_page": null, - "repo": "IDEA-Research/MaskDINO", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Mask_DINO_Towards_a_Unified_Transformer-Based_Framework_for_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2206.02777", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Ankel5cLZP4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Collaborative Noisy Label Cleaner: Learning Scene-Aware Trailers for Multi-Modal Highlight Detection in Movies", - "base_url": null, - "title_page": null, - "repo": "TencentYoutuResearch/HighlightDetection-CLC", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Gan_Collaborative_Noisy_Label_Cleaner_Learning_Scene-Aware_Trailers_for_Multi-Modal_Highlight_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14768", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "Pr2A0JmyKVc", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Open-Set Fine-grained Retrieval via Prompting Vision-Language Evaluator", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Open-Set_Fine-Grained_Retrieval_via_Prompting_Vision-Language_Evaluator_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "a81Ws3_0Hag", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Observation-Centric SORT: Rethinking SORT for Robust Multi-Object Tracking", - "base_url": null, - "title_page": null, - "repo": "noahcao/OC_SORT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cao_Observation-Centric_SORT_Rethinking_SORT_for_Robust_Multi-Object_Tracking_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2203.14360", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "rRE8xv4pPus", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Visual Exemplar Driven Task-Prompting for Unified Perception in Autonomous Driving", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liang_Visual_Exemplar_Driven_Task-Prompting_for_Unified_Perception_in_Autonomous_Driving_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.01788", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Exploiting Unlabelled Photos for Stronger Fine-grained SBIR", - "base_url": null, - "title_page": null, - "repo": "aneeshan95/Sketch_PVT", - "web_page": null, - "github_page": "https://aneeshan95.github.io/Sketch_PVT/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sain_Exploiting_Unlabelled_Photos_for_Stronger_Fine-Grained_SBIR_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13779", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LyM-Mw9yPHE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "What Can Human Sketches Do for Object Detection?", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": "https://www.pinakinathc.me/sketch-detect/", - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Chowdhury_What_Can_Human_Sketches_Do_for_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15149", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "MglzpOCC-3c", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Dynamic Conceptional Contrastive Learning for Generalized Category Discovery", - "base_url": null, - "title_page": null, - "repo": "TPCD/DCCL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pu_Dynamic_Conceptional_Contrastive_Learning_for_Generalized_Category_Discovery_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.17393", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "G6ZdySsOri4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Balanced Energy Regularization Loss for Out-of-Distribution Detection", - "base_url": null, - "title_page": null, - "repo": "hyunjunChhoi/Balanced_Energy", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Choi_Balanced_Energy_Regularization_Loss_for_Out-of-Distribution_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.10485", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "l53KOKb1Ovg", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Lite DETR: An Interleaved Multi-Scale Encoder for Efficient DETR", - "base_url": null, - "title_page": null, - "repo": "IDEA-Research/Lite-DETR", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Lite_DETR_An_Interleaved_Multi-Scale_Encoder_for_Efficient_DETR_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07335", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "LSBkpIY8CV4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "CLIP for All Things Zero-Shot Sketch-based Image Retrieval, Fine-grained or Not", - "base_url": null, - "title_page": null, - "repo": "aneeshan95/Sketch_LVM", - "web_page": null, - "github_page": "https://aneeshan95.github.io/Sketch_LVM/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Sain_CLIP_for_All_Things_Zero-Shot_Sketch-Based_Image_Retrieval_Fine-Grained_or_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13440", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ImcQFsS1SfE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "PosterLayout: A New Benchmark and Approach for Content-Aware Visual-Textual Presentation Layout", - "base_url": null, - "title_page": null, - "repo": "PKU-ICST-MIPL/PosterLayout-CVPR2023", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Hsu_PosterLayout_A_New_Benchmark_and_Approach_for_Content-Aware_Visual-Textual_Presentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.15937", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WyfkbmEPh1s", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Re-Thinking Federated Active Learning based on Inter-Class Diversity", - "base_url": null, - "title_page": null, - "repo": "raymin0223/LoGo", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Kim_Re-Thinking_Federated_Active_Learning_Based_on_Inter-Class_Diversity_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.12317", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "gAoKIAE-a9o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Consistent-Teacher: Towards Reducing Inconsistent Pseudo-Targets in Semi-Supervised Object Detection", - "base_url": null, - "title_page": null, - "repo": "Adamdad/ConsistentTeacher", - "web_page": null, - "github_page": "https://adamdad.github.io/consistentteacher/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Consistent-Teacher_Towards_Reducing_Inconsistent_Pseudo-Targets_in_Semi-Supervised_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2209.01589", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "ZCyM6ygGdo4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Cloud-Device Collaborative Adaptation to Continual Changing Environments in the Real-World", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pan_Cloud-Device_Collaborative_Adaptation_to_Continual_Changing_Environments_in_the_Real-World_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.00972", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Bridging Precision and Confidence: A Train-Time Loss for Calibrating Object Detection", - "base_url": null, - "title_page": null, - "repo": "akhtarvision/bpc_calibration", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Munir_Bridging_Precision_and_Confidence_A_Train-Time_Loss_for_Calibrating_Object_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14404", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "qsY2m0WOoiE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "AccelIR: Task-Aware Image Compression for Accelerating Neural Restoration", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ye_AccelIR_Task-Aware_Image_Compression_for_Accelerating_Neural_Restoration_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Multiclass Confidence and Localization Calibration for Object Detection", - "base_url": null, - "title_page": null, - "repo": "bimsarapathiraja/MCCL", - "web_page": null, - "github_page": "https://bimsarapathiraja.github.io/mccl-project-page/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Pathiraja_Multiclass_Confidence_and_Localization_Calibration_for_Object_Detection_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.08271", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WGaeUSxMS3E", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Auto-CARD: Efficient and Robust Codec Avatar Driving for Real-Time Mobile Telepresence", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fu_Auto-CARD_Efficient_and_Robust_Codec_Avatar_Driving_for_Real-Time_Mobile_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2304.11835", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "XJP5G4GqjzE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "Deep Random Projector: Accelerated Deep Image Prior", - "base_url": null, - "title_page": null, - "repo": "sun-umn/Deep-Random-Projector", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Li_Deep_Random_Projector_Accelerated_Deep_Image_Prior_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "agXKHhjl1J4", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - }, - { - "title": "SIEDOB: Semantic Image Editing by Disentangling Object and Background", - "base_url": null, - "title_page": null, - "repo": "WuyangLuo/SIEDOB", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Luo_SIEDOB_Semantic_Image_Editing_by_Disentangling_Object_and_Background_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.13062", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "o56SR0m5MUA", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision Applications and Systems" - } -] \ No newline at end of file diff --git a/json_data/vision-language-and-reasoning.json b/json_data/vision-language-and-reasoning.json deleted file mode 100644 index b4506ff..0000000 --- a/json_data/vision-language-and-reasoning.json +++ /dev/null @@ -1,402 +0,0 @@ -[ - { - "title": "Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://antoyang.github.io/vid2seq.html", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yang_Vid2Seq_Large-Scale_Pretraining_of_a_Visual_Language_Model_for_Dense_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.14115", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "hXP-2fYzq4g", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "Open-Vocabulary Panoptic Segmentation With Text-to-Image Diffusion Models", - "base_url": null, - "title_page": null, - "repo": "NVlabs/ODISE", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Xu_Open-Vocabulary_Panoptic_Segmentation_With_Text-to-Image_Diffusion_Models_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.04803", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "eW2vF8o_7p0", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "Iterative Proposal Refinement for Weakly-Supervised Video Grounding", - "base_url": null, - "title_page": null, - "repo": "ttengwang/Awesome_Long_Term_Video_Understanding", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cao_Iterative_Proposal_Refinement_for_Weakly-Supervised_Video_Grounding_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "BbGvHI_pVXk", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "MetaCLUE: Towards Comprehensive Visual Metaphors Research", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": "https://metaclue.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Akula_MetaCLUE_Towards_Comprehensive_Visual_Metaphors_Research_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.09898", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "V3TmeNETL-o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "PolyFormer: Referring Image Segmentation As Sequential Polygon Generation", - "base_url": null, - "title_page": null, - "repo": "amazon-science/polygon-transformer", - "web_page": null, - "github_page": "https://polyformer.github.io/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_PolyFormer_Referring_Image_Segmentation_As_Sequential_Polygon_Generation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2302.07387", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "6LNrqoxQR1M", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "GeneCIS: A Benchmark for General Conditional Image Similarity", - "base_url": null, - "title_page": null, - "repo": "facebookresearch/genecis", - "web_page": null, - "github_page": "https://sgvaze.github.io/genecis/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Vaze_GeneCIS_A_Benchmark_for_General_Conditional_Image_Similarity_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.07969", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wu3U2iNGIUw", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "FAME-ViL: Multi-Tasking Vision-Language Model for Heterogeneous Fashion Tasks", - "base_url": null, - "title_page": null, - "repo": "BrandonHanx/FAME-ViL", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Han_FAME-ViL_Multi-Tasking_Vision-Language_Model_for_Heterogeneous_Fashion_Tasks_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.02483", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "Generative Bias for Robust Visual Question Answering", - "base_url": null, - "title_page": null, - "repo": "chojw/genb", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Cho_Generative_Bias_for_Robust_Visual_Question_Answering_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2208.00690", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "Advancing Visual Grounding With Scene Knowledge: Benchmark and Method", - "base_url": null, - "title_page": null, - "repo": "zhjohnchan/SK-VG", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Song_Advancing_Visual_Grounding_With_Scene_Knowledge_Benchmark_and_Method_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.11558", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "DmmPiseO59o", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "Gloss Attention for Gloss-Free Sign Language Translation", - "base_url": null, - "title_page": null, - "repo": "YinAoXiong/GASLT", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Yin_Gloss_Attention_for_Gloss-Free_Sign_Language_Translation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2307.07361", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "NEoWvxkJXfU", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "You Can Ground Earlier Than See: An Effective and Efficient Pipeline for Temporal Sentence Grounding in Compressed Videos", - "base_url": null, - "title_page": null, - "repo": null, - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Fang_You_Can_Ground_Earlier_Than_See_An_Effective_and_Efficient_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.07863", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "Generalized Decoding for Pixel, Image, and Language", - "base_url": null, - "title_page": null, - "repo": "microsoft/X-Decoder", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Zou_Generalized_Decoding_for_Pixel_Image_and_Language_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2212.11270", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "wYp6vmyolqE", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "Accelerating Vision-Language Pretraining With Free Language Modeling", - "base_url": null, - "title_page": null, - "repo": "TencentARC/FLM", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Wang_Accelerating_Vision-Language_Pretraining_With_Free_Language_Modeling_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2303.14038", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "WbH_5DH_jfY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "GRES: Generalized Referring Expression Segmentation", - "base_url": null, - "title_page": null, - "repo": "henghuiding/ReLA", - "web_page": null, - "github_page": "https://henghuiding.github.io/GRES/", - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Liu_GRES_Generalized_Referring_Expression_Segmentation_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2306.00968", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "eWjAgYUU6Do", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "BUFFER: Balancing Accuracy, Efficiency, and Generalizability in Point Cloud Registration", - "base_url": null, - "title_page": null, - "repo": "The-Learning-And-Vision-Atelier-LAVA/BUFFER", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Ao_BUFFER_Balancing_Accuracy_Efficiency_and_Generalizability_in_Point_Cloud_Registration_CVPR_2023_paper.pdf", - "paper_arxiv_id": null, - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": "STmAkRWuSiY", - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - }, - { - "title": "RGB No More: Minimally-Decoded JPEG Vision Transformers", - "base_url": null, - "title_page": null, - "repo": "JeongsooP/RGB-no-more", - "web_page": null, - "github_page": null, - "colab": null, - "modelscope": null, - "gitee": null, - "zenodo": null, - "demo_page": null, - "paper_thecvf": "https://openaccess.thecvf.com/content/CVPR2023/papers/Park_RGB_No_More_Minimally-Decoded_JPEG_Vision_Transformers_CVPR_2023_paper.pdf", - "paper_arxiv_id": "2211.16421", - "paper_pdf": null, - "paper_hal_science": null, - "paper_researchgate": null, - "paper_amazon": null, - "youtube_id": null, - "drive_google": null, - "dropbox": null, - "onedrive": null, - "loom": null, - "section": "Vision, Language, and Reasoning" - } -] \ No newline at end of file