cvpr_data.json

{
    "Machine Learning": [
        {
            "paperId": "11954",
            "posterId": "1a",
            "title": "Efficient Deep Embedded Subspace Clustering",
            "authors": [
                "Jinyu Cai",
                " Jicong Fan",
                " Wenzhong Guo",
                " Shiping Wang",
                " Yunhe Zhang",
                " Zhao Zhang"
            ]
        },
        {
            "paperId": "11402",
            "posterId": "2a",
            "title": "Clipped Hyperbolic Classifiers Are Super-Hyperbolic Classifiers",
            "authors": [
                "Yunhui Guo",
                " Xudong Wang",
                " Yubei Chen",
                " Stella X. Yu"
            ]
        },
        {
            "paperId": "9445",
            "posterId": "3a",
            "title": "CO-SNE: Dimensionality Reduction and Visualization for Hyperbolic Data",
            "authors": [
                "Yunhui Guo",
                " Haoran Guo",
                " Stella X. Yu"
            ]
        },
        {
            "paperId": "8776",
            "posterId": "4a",
            "title": "Noise Is Also Useful: Negative Correlation-Steered Latent Contrastive Learning",
            "authors": [
                "Jiexi Yan",
                " Lei Luo",
                " Chenghao Xu",
                " Cheng Deng",
                " Heng Huang"
            ]
        },
        {
            "paperId": "6978",
            "posterId": "5a",
            "title": "Active Learning for Open-Set Annotation",
            "authors": [
                "Kun-Peng Ning",
                " Xun Zhao",
                " Yu Li",
                " Sheng-Jun Huang"
            ]
        },
        {
            "paperId": "9075",
            "posterId": "6a",
            "title": "Understanding and Increasing Efficiency of Frank-Wolfe Adversarial Training",
            "authors": [
                "Theodoros Tsiligkaridis",
                " Jay Roberts"
            ]
        },
        {
            "paperId": "6601",
            "posterId": "7a",
            "title": "Robust Optimization As Data Augmentation for Large-Scale Graphs",
            "authors": [
                "Kezhi Kong",
                " Guohao Li",
                " Mucong Ding",
                " Zuxuan Wu",
                " Chen Zhu",
                " Bernard Ghanem",
                " Gavin Taylor",
                " Tom Goldstein"
            ]
        },
        {
            "paperId": "6298",
            "posterId": "8a",
            "title": "A Re-Balancing Strategy for Class-Imbalanced Classification Based on Instance Difficulty",
            "authors": [
                "Sihao Yu",
                " Jiafeng Guo",
                " Ruqing Zhang",
                " Yixing Fan",
                " Zizhen Wang",
                " Xueqi Cheng"
            ]
        },
        {
            "paperId": "6106",
            "posterId": "9a",
            "title": "The Devil Is in the Margin: Margin-Based Label Smoothing for Network Calibration",
            "authors": [
                "Bingyuan Liu",
                " Ismail Ben Ayed",
                " Adrian Galdran",
                " Jose Dolz"
            ]
        },
        {
            "paperId": "6705",
            "posterId": "10a",
            "title": "Towards Better Plasticity-Stability Trade-Off in Incremental Learning: A Simple Linear Connector",
            "authors": [
                "Guoliang Lin",
                " Hanlu Chu",
                " Hanjiang Lai"
            ]
        },
        {
            "paperId": "10071",
            "posterId": "11a",
            "title": "GCR: Gradient Coreset Based Replay Buffer Selection for Continual Learning",
            "authors": [
                "Rishabh Tiwari",
                " Krishnateja Killamsetty",
                " Rishabh Iyer",
                " Pradeep Shenoy"
            ]
        },
        {
            "paperId": "7829",
            "posterId": "12a",
            "title": "Learning Bayesian Sparse Networks With Full Experience Replay for Continual Learning",
            "authors": [
                "Qingsen Yan",
                " Dong Gong",
                " Yuhang Liu",
                " Anton van den Hengel",
                " Javen Qinfeng Shi"
            ]
        },
        {
            "paperId": "5988",
            "posterId": "13a",
            "title": "A Variational Bayesian Method for Similarity Learning in Non-Rigid Image Registration",
            "authors": [
                "Daniel Grzech",
                " Mohammad Farid Azampour",
                " Ben Glocker",
                " Julia Schnabel",
                " Nassir Navab",
                " Bernhard Kainz",
                " Loïc Le Folgoc"
            ]
        },
        {
            "paperId": "2503",
            "posterId": "14a",
            "title": "Learning To Learn by Jointly Optimizing Neural Architecture and Weights",
            "authors": [
                "Yadong Ding",
                " Yu Wu",
                " Chengyue Huang",
                " Siliang Tang",
                " Yi Yang",
                " Longhui Wei",
                " Yueting Zhuang",
                " Qi Tian"
            ]
        },
        {
            "paperId": "9806",
            "posterId": "15a",
            "title": "Learning To Prompt for Continual Learning",
            "authors": [
                "Zifeng Wang",
                " Zizhao Zhang",
                " Chen-Yu Lee",
                " Han Zhang",
                " Ruoxi Sun",
                " Xiaoqi Ren",
                " Guolong Su",
                " Vincent Perot",
                " Jennifer Dy",
                " Tomas Pfister"
            ]
        },
        {
            "paperId": "2016",
            "posterId": "16a",
            "title": "Meta-Attention for ViT-Backed Continual Learning",
            "authors": [
                "Mengqi Xue",
                " Haofei Zhang",
                " Jie Song",
                " Mingli Song"
            ]
        },
        {
            "paperId": "1343",
            "posterId": "17a",
            "title": "Multi-Frame Self-Supervised Depth With Transformers",
            "authors": [
                "Vitor Guizilini",
                " Rareș Ambruș",
                " Dian Chen",
                " Sergey Zakharov",
                " Adrien Gaidon"
            ]
        },
        {
            "paperId": "10018",
            "posterId": "18a",
            "title": "Continual Learning With Lifelong Vision Transformer",
            "authors": [
                "Zhen Wang",
                " Liu Liu",
                " Yiqun Duan",
                " Yajing Kong",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "780",
            "posterId": "19a",
            "title": "Rethinking Bayesian Deep Learning Methods for Semi-Supervised Volumetric Medical Image Segmentation",
            "authors": [
                "Jianfeng Wang",
                " Thomas Lukasiewicz"
            ]
        },
        {
            "paperId": "4874",
            "posterId": "20a",
            "title": "Revisiting Random Channel Pruning for Neural Network Compression",
            "authors": [
                "Yawei Li",
                " Kamil Adamczewski",
                " Wen Li",
                " Shuhang Gu",
                " Radu Timofte",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "8330",
            "posterId": "21a",
            "title": "Deep Safe Multi-View Clustering: Reducing the Risk of Clustering Performance Degradation Caused by View Increase",
            "authors": [
                "Huayi Tang",
                " Yong Liu"
            ]
        },
        {
            "paperId": "9551",
            "posterId": "22a",
            "title": "Hypergraph-Induced Semantic Tuplet Loss for Deep Metric Learning",
            "authors": [
                "Jongin Lim",
                " Sangdoo Yun",
                " Seulki Park",
                " Jin Young Choi"
            ]
        },
        {
            "paperId": "10484",
            "posterId": "23a",
            "title": "Towards Robust and Reproducible Active Learning Using Neural Networks",
            "authors": [
                "Prateek Munjal",
                " Nasir Hayat",
                " Munawar Hayat",
                " Jamshid Sourati",
                " Shadab Khan"
            ]
        },
        {
            "paperId": "7082",
            "posterId": "24a",
            "title": "Non-Iterative Recovery From Nonlinear Observations Using Generative Models",
            "authors": [
                "Jiulong Liu",
                " Zhaoqiang Liu"
            ]
        },
        {
            "paperId": "11093",
            "posterId": "25a",
            "title": "Gaussian Process Modeling of Approximate Inference Errors for Variational Autoencoders",
            "authors": [
                "Minyoung Kim"
            ]
        },
        {
            "paperId": "4542",
            "posterId": "26a",
            "title": "Robust Combination of Distributed Gradients Under Adversarial Perturbations",
            "authors": [
                "Kwang In Kim"
            ]
        },
        {
            "paperId": "11143",
            "posterId": "27a",
            "title": "Do Learned Representations Respect Causal Relationships?",
            "authors": [
                "Lan Wang",
                " Vishnu Naresh Boddeti"
            ]
        },
        {
            "paperId": "11220",
            "posterId": "28a",
            "title": "How Much More Data Do I Need? Estimating Requirements for Downstream Tasks",
            "authors": [
                "Rafid Mahmood",
                " James Lucas",
                " David Acuna",
                " Daiqing Li",
                " Jonah Philion",
                " Jose M. Alvarez",
                " Zhiding Yu",
                " Sanja Fidler",
                " Marc T. Law"
            ]
        },
        {
            "paperId": "8156",
            "posterId": "29a",
            "title": "Pushing the Envelope of Gradient Boosting Forests via Globally-Optimized Oblique Trees",
            "authors": [
                "Magzhan Gabidolla",
                " Miguel Á. Carreira-Perpiñán"
            ]
        },
        {
            "paperId": "11131",
            "posterId": "30a",
            "title": "Contrastive Test-Time Adaptation",
            "authors": [
                "Dian Chen",
                " Dequan Wang",
                " Trevor Darrell",
                " Sayna Ebrahimi"
            ]
        },
        {
            "paperId": "448",
            "posterId": "31a",
            "title": "AutoSDF: Shape Priors for 3D Completion, Reconstruction and Generation",
            "authors": [
                "Paritosh Mittal",
                " Yen-Chi Cheng",
                " Maneesh Singh",
                " Shubham Tulsiani"
            ]
        },
        {
            "paperId": "1561",
            "posterId": "32a",
            "title": "Selective-Supervised Contrastive Learning With Noisy Labels",
            "authors": [
                "Shikun Li",
                " Xiaobo Xia",
                " Shiming Ge",
                " Tongliang Liu"
            ]
        },
        {
            "paperId": "7807",
            "posterId": "33a",
            "title": "RecDis-SNN: Rectifying Membrane Potential Distribution for Directly Training Spiking Neural Networks",
            "authors": [
                "Yufei Guo",
                " Xinyi Tong",
                " Yuanpei Chen",
                " Liwen Zhang",
                " Xiaode Liu",
                " Zhe Ma",
                " Xuhui Huang"
            ]
        },
        {
            "paperId": "3279",
            "posterId": "34a",
            "title": "Hierarchical Nearest Neighbor Graph Embedding for Efficient Dimensionality Reduction",
            "authors": [
                "Saquib Sarfraz",
                " Marios Koulakis",
                " Constantin Seibold",
                " Rainer Stiefelhagen"
            ]
        }
    ],
    "Statistical Methods": [
        {
            "paperId": "3348",
            "posterId": "35a",
            "title": "Scalable Penalized Regression for Noise Detection in Learning With Noisy Labels",
            "authors": [
                "Yikai Wang",
                " Xinwei Sun",
                " Yanwei Fu"
            ]
        },
        {
            "paperId": "7912",
            "posterId": "36a",
            "title": "Nested Hyperbolic Spaces for Dimensionality Reduction and Hyperbolic NN Design",
            "authors": [
                "Xiran Fan",
                " Chun-Hao Yang",
                " Baba C. Vemuri"
            ]
        },
        {
            "paperId": "8877",
            "posterId": "37a",
            "title": "Learning Structured Gaussians To Approximate Deep Ensembles",
            "authors": [
                "Ivor J. A. Simpson",
                " Sara Vicente",
                " Neill D. F. Campbell"
            ]
        },
        {
            "paperId": "11673",
            "posterId": "38a",
            "title": "Out-of-Distribution Generalization With Causal Invariant Transformations",
            "authors": [
                "Ruoyu Wang",
                " Mingyang Yi",
                " Zhitang Chen",
                " Shengyu Zhu"
            ]
        },
        {
            "paperId": "8393",
            "posterId": "39a",
            "title": "Split Hierarchical Variational Compression",
            "authors": [
                "Tom Ryder",
                " Chen Zhang",
                " Ning Kang",
                " Shifeng Zhang"
            ]
        },
        {
            "paperId": "9244",
            "posterId": "40a",
            "title": "Implicit Feature Decoupling With Depthwise Quantization",
            "authors": [
                "Iordanis Fostiropoulos",
                " Barry Boehm"
            ]
        },
        {
            "paperId": "282",
            "posterId": "41a",
            "title": "Understanding Uncertainty Maps in Vision With Statistical Testing",
            "authors": [
                "Jurijs Nazarovs",
                " Zhichun Huang",
                " Songwong Tasneeyapant",
                " Rudrasis Chakraborty",
                " Vikas Singh"
            ]
        }
    ],
    "Optimization Methods": [
        {
            "paperId": "785",
            "posterId": "42a",
            "title": "A Hybrid Quantum-Classical Algorithm for Robust Fitting",
            "authors": [
                "Anh-Dzung Doan",
                " Michele Sasdelli",
                " David Suter",
                " Tat-Jun Chin"
            ]
        },
        {
            "paperId": "5911",
            "posterId": "43a",
            "title": "A Scalable Combinatorial Solver for Elastic Geometrically Consistent 3D Shape Matching",
            "authors": [
                "Paul Roetzer",
                " Paul Swoboda",
                " Daniel Cremers",
                " Florian Bernard"
            ]
        },
        {
            "paperId": "6021",
            "posterId": "44a",
            "title": "FastDOG: Fast Discrete Optimization on GPU",
            "authors": [
                "Ahmed Abbas",
                " Paul Swoboda"
            ]
        },
        {
            "paperId": "9232",
            "posterId": "45a",
            "title": "Data-Free Network Compression via Parametric Non-Uniform Mixed Precision Quantization",
            "authors": [
                "Vladimir Chikin",
                " Mikhail Antiukh"
            ]
        },
        {
            "paperId": "10092",
            "posterId": "46a",
            "title": "AdaSTE: An Adaptive Straight-Through Estimator To Train Binary Neural Networks",
            "authors": [
                "Huu Le",
                " Rasmus Kjær Høier",
                " Che-Tsung Lin",
                " Christopher Zach"
            ]
        },
        {
            "paperId": "11171",
            "posterId": "47a",
            "title": "Training Quantised Neural Networks With STE Variants: The Additive Noise Annealing Algorithm",
            "authors": [
                "Matteo Spallanzani",
                " Gian Paolo Leonardi",
                " Luca Benini"
            ]
        },
        {
            "paperId": "2028",
            "posterId": "48a",
            "title": "AME: Attention and Memory Enhancement in Hyper-Parameter Optimization",
            "authors": [
                "Nuo Xu",
                " Jianlong Chang",
                " Xing Nie",
                " Chunlei Huo",
                " Shiming Xiang",
                " Chunhong Pan"
            ]
        },
        {
            "paperId": "9259",
            "posterId": "49a",
            "title": "Accelerating Neural Network Optimization Through an Automated Control Theory Lens",
            "authors": [
                "Jiahao Wang",
                " Baoyuan Wu",
                " Rui Su",
                " Mingdeng Cao",
                " Shuwei Shi",
                " Wanli Ouyang",
                " Yujiu Yang"
            ]
        },
        {
            "paperId": "11189",
            "posterId": "50a",
            "title": "Efficient Maximal Coding Rate Reduction by Variational Forms",
            "authors": [
                "Christina Baek",
                " Ziyang Wu",
                " Kwan Ho Ryan Chan",
                " Tianjiao Ding",
                " Yi Ma",
                " Benjamin D. Haeffele"
            ]
        },
        {
            "paperId": "10155",
            "posterId": "51a",
            "title": "A Unified Framework for Implicit Sinkhorn Differentiation",
            "authors": [
                "Marvin Eisenberger",
                " Aysim Toker",
                " Laura Leal-Taixé",
                " Florian Bernard",
                " Daniel Cremers"
            ]
        },
        {
            "paperId": "6845",
            "posterId": "52a",
            "title": "Computing Wasserstein-p Distance Between Images With Linear Cost",
            "authors": [
                "Yidong Chen",
                " Chen Li",
                " Zhonghua Lu"
            ]
        },
        {
            "paperId": "9064",
            "posterId": "53a",
            "title": "An Iterative Quantum Approach for Transformation Estimation From Point Sets",
            "authors": [
                "Natacha Kuete Meli",
                " Florian Mannel",
                " Jan Lellmann"
            ]
        }
    ],
    "Deep Learning Architectures & Techniques": [
        {
            "paperId": "116",
            "posterId": "121a",
            "title": "Demystifying the Neural Tangent Kernel From a Practical Perspective: Can It Be Trusted for Neural Architecture Search Without Training?",
            "authors": [
                "Jisoo Mok",
                " Byunggook Na",
                " Ji-Hoon Kim",
                " Dongyoon Han",
                " Sungroh Yoon"
            ]
        },
        {
            "paperId": "5389",
            "posterId": "122a",
            "title": "BaLeNAS: Differentiable Architecture Search via the Bayesian Learning Rule",
            "authors": [
                "Miao Zhang",
                " Shirui Pan",
                " Xiaojun Chang",
                " Steven Su",
                " Jilin Hu",
                " Gholamreza (Reza) Haffari",
                " Bin Yang"
            ]
        },
        {
            "paperId": "7704",
            "posterId": "123a",
            "title": "Arch-Graph: Acyclic Architecture Relation Predictor for Task-Transferable Neural Architecture Search",
            "authors": [
                "Minbin Huang",
                " Zhijian Huang",
                " Changlin Li",
                " Xin Chen",
                " Hang Xu",
                " Zhenguo Li",
                " Xiaodan Liang"
            ]
        },
        {
            "paperId": "4143",
            "posterId": "124a",
            "title": "Shapley-NAS: Discovering Operation Contribution for Neural Architecture Search",
            "authors": [
                "Han Xiao",
                " Ziwei Wang",
                " Zheng Zhu",
                " Jie Zhou",
                " Jiwen Lu"
            ]
        },
        {
            "paperId": "5167",
            "posterId": "125a",
            "title": "GreedyNASv2: Greedier Search With a Greedy Path Filter",
            "authors": [
                "Tao Huang",
                " Shan You",
                " Fei Wang",
                " Chen Qian",
                " Changshui Zhang",
                " Xiaogang Wang",
                " Chang Xu"
            ]
        },
        {
            "paperId": "1115",
            "posterId": "126a",
            "title": "Neural Architecture Search With Representation Mutual Information",
            "authors": [
                "Xiawu Zheng",
                " Xiang Fei",
                " Lei Zhang",
                " Chenglin Wu",
                " Fei Chao",
                " Jianzhuang Liu",
                " Wei Zeng",
                " Yonghong Tian",
                " Rongrong Ji"
            ]
        },
        {
            "paperId": "7148",
            "posterId": "127a",
            "title": "Performance-Aware Mutual Knowledge Distillation for Improving Neural Architecture Search",
            "authors": [
                "Pengtao Xie",
                " Xuefeng Du"
            ]
        },
        {
            "paperId": "8841",
            "posterId": "128a",
            "title": "Knowledge Distillation With the Reused Teacher Classifier",
            "authors": [
                "Defang Chen",
                " Jian-Ping Mei",
                " Hailin Zhang",
                " Can Wang",
                " Yan Feng",
                " Chun Chen"
            ]
        },
        {
            "paperId": "2812",
            "posterId": "129a",
            "title": "Self-Distillation From the Last Mini-Batch for Consistency Regularization",
            "authors": [
                "Yiqing Shen",
                " Liwu Xu",
                " Yuzhe Yang",
                " Yaqian Li",
                " Yandong Guo"
            ]
        },
        {
            "paperId": "142",
            "posterId": "130a",
            "title": "Decoupled Knowledge Distillation",
            "authors": [
                "Borui Zhao",
                " Quan Cui",
                " Renjie Song",
                " Yiyu Qiu",
                " Jiajun Liang"
            ]
        },
        {
            "paperId": "7053",
            "posterId": "131a",
            "title": "Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs",
            "authors": [
                "Xiaohan Ding",
                " Xiangyu Zhang",
                " Jungong Han",
                " Guiguang Ding"
            ]
        },
        {
            "paperId": "123",
            "posterId": "132a",
            "title": "A ConvNet for the 2020s",
            "authors": [
                "Zhuang Liu",
                " Hanzi Mao",
                " Chao-Yuan Wu",
                " Christoph Feichtenhofer",
                " Trevor Darrell",
                " Saining Xie"
            ]
        },
        {
            "paperId": "7254",
            "posterId": "133a",
            "title": "Beyond Fixation: Dynamic Window Visual Transformer",
            "authors": [
                "Pengzhen Ren",
                " Changlin Li",
                " Guangrun Wang",
                " Yun Xiao",
                " Qing Du",
                " Xiaodan Liang",
                " Xiaojun Chang"
            ]
        },
        {
            "paperId": "7867",
            "posterId": "134a",
            "title": "Lite Vision Transformer With Enhanced Self-Attention",
            "authors": [
                "Chenglin Yang",
                " Yilin Wang",
                " Jianming Zhang",
                " He Zhang",
                " Zijun Wei",
                " Zhe Lin",
                " Alan Yuille"
            ]
        },
        {
            "paperId": "7428",
            "posterId": "135a",
            "title": "Swin Transformer V2: Scaling Up Capacity and Resolution",
            "authors": [
                "Ze Liu",
                " Han Hu",
                " Yutong Lin",
                " Zhuliang Yao",
                " Zhenda Xie",
                " Yixuan Wei",
                " Jia Ning",
                " Yue Cao",
                " Zheng Zhang",
                " Li Dong",
                " Furu Wei",
                " Baining Guo"
            ]
        },
        {
            "paperId": "4325",
            "posterId": "136a",
            "title": "The Principle of Diversity: Training Stronger Vision Transformers Calls for Reducing All Levels of Redundancy",
            "authors": [
                "Tianlong Chen",
                " Zhenyu Zhang",
                " Yu Cheng",
                " Ahmed Awadallah",
                " Zhangyang Wang"
            ]
        },
        {
            "paperId": "9412",
            "posterId": "137a",
            "title": "MulT: An End-to-End Multitask Learning Transformer",
            "authors": [
                "Deblina Bhattacharjee",
                " Tong Zhang",
                " Sabine Süsstrunk",
                " Mathieu Salzmann"
            ]
        },
        {
            "paperId": "3664",
            "posterId": "138a",
            "title": "Towards Robust Vision Transformer",
            "authors": [
                "Xiaofeng Mao",
                " Gege Qi",
                " Yuefeng Chen",
                " Xiaodan Li",
                " Ranjie Duan",
                " Shaokai Ye",
                " Yuan He",
                " Hui Xue"
            ]
        },
        {
            "paperId": "9773",
            "posterId": "139a",
            "title": "DearKD: Data-Efficient Early Knowledge Distillation for Vision Transformers",
            "authors": [
                "Xianing Chen",
                " Qiong Cao",
                " Yujie Zhong",
                " Jing Zhang",
                " Shenghua Gao",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "2434",
            "posterId": "140a",
            "title": "MSG-Transformer: Exchanging Local Spatial Information by Manipulating Messenger Tokens",
            "authors": [
                "Jiemin Fang",
                " Lingxi Xie",
                " Xinggang Wang",
                " Xiaopeng Zhang",
                " Wenyu Liu",
                " Qi Tian"
            ]
        },
        {
            "paperId": "1032",
            "posterId": "141a",
            "title": "NomMer: Nominate Synergistic Context in Vision Transformer for Visual Recognition",
            "authors": [
                "Hao Liu",
                " Xinghua Jiang",
                " Xin Li",
                " Zhimin Bao",
                " Deqiang Jiang",
                " Bo Ren"
            ]
        },
        {
            "paperId": "2029",
            "posterId": "142a",
            "title": "TopFormer: Token Pyramid Transformer for Mobile Semantic Segmentation",
            "authors": [
                "Wenqiang Zhang",
                " Zilong Huang",
                " Guozhong Luo",
                " Tao Chen",
                " Xinggang Wang",
                " Wenyu Liu",
                " Gang Yu",
                " Chunhua Shen"
            ]
        },
        {
            "paperId": "4853",
            "posterId": "143a",
            "title": "Multi-Scale High-Resolution Vision Transformer for Semantic Segmentation",
            "authors": [
                "Jiaqi Gu",
                " Hyoukjun Kwon",
                " Dilin Wang",
                " Wei Ye",
                " Meng Li",
                " Yu-Hsin Chen",
                " Liangzhen Lai",
                " Vikas Chandra",
                " David Z. Pan"
            ]
        },
        {
            "paperId": "10350",
            "posterId": "144a",
            "title": "Scaling Vision Transformers",
            "authors": [
                "Xiaohua Zhai",
                " Alexander Kolesnikov",
                " Neil Houlsby",
                " Lucas Beyer"
            ]
        },
        {
            "paperId": "7298",
            "posterId": "145a",
            "title": "Bridged Transformer for Vision and Point Cloud 3D Object Detection",
            "authors": [
                "Yikai Wang",
                " TengQi Ye",
                " Lele Cao",
                " Wenbing Huang",
                " Fuchun Sun",
                " Fengxiang He",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "1981",
            "posterId": "146a",
            "title": "CSWin Transformer: A General Vision Transformer Backbone With Cross-Shaped Windows",
            "authors": [
                "Xiaoyi Dong",
                " Jianmin Bao",
                " Dongdong Chen",
                " Weiming Zhang",
                " Nenghai Yu",
                " Lu Yuan",
                " Dong Chen",
                " Baining Guo"
            ]
        },
        {
            "paperId": "3562",
            "posterId": "147a",
            "title": "TransMix: Attend To Mix for Vision Transformers",
            "authors": [
                "Jie-Neng Chen",
                " Shuyang Sun",
                " Ju He",
                " Philip H.S. Torr",
                " Alan Yuille",
                " Song Bai"
            ]
        },
        {
            "paperId": "2388",
            "posterId": "148a",
            "title": "MiniViT: Compressing Vision Transformers With Weight Multiplexing",
            "authors": [
                "Jinnian Zhang",
                " Houwen Peng",
                " Kan Wu",
                " Mengchen Liu",
                " Bin Xiao",
                " Jianlong Fu",
                " Lu Yuan"
            ]
        },
        {
            "paperId": "11460",
            "posterId": "149a",
            "title": "Fine-Tuning Image Transformers Using Learnable Memory",
            "authors": [
                "Mark Sandler",
                " Andrey Zhmoginov",
                " Max Vladymyrov",
                " Andrew Jackson"
            ]
        },
        {
            "paperId": "4430",
            "posterId": "150a",
            "title": "Patch Slimming for Efficient Vision Transformers",
            "authors": [
                "Yehui Tang",
                " Kai Han",
                " Yunhe Wang",
                " Chang Xu",
                " Jianyuan Guo",
                " Chao Xu",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "5093",
            "posterId": "151a",
            "title": "CMT: Convolutional Neural Networks Meet Vision Transformers",
            "authors": [
                "Jianyuan Guo",
                " Kai Han",
                " Han Wu",
                " Yehui Tang",
                " Xinghao Chen",
                " Yunhe Wang",
                " Chang Xu"
            ]
        },
        {
            "paperId": "6795",
            "posterId": "152a",
            "title": "Multimodal Token Fusion for Vision Transformers",
            "authors": [
                "Yikai Wang",
                " Xinghao Chen",
                " Lele Cao",
                " Wenbing Huang",
                " Fuchun Sun",
                " Yunhe Wang"
            ]
        }
    ],
    "Recognition: Detection, Categorization, Retrieval": [
        {
            "paperId": "2257",
            "posterId": "75b",
            "title": "Open-Vocabulary One-Stage Detection With Hierarchical Visual-Language Knowledge Distillation",
            "authors": [
                "Zongyang Ma",
                " Guan Luo",
                " Jin Gao",
                " Liang Li",
                " Yuxin Chen",
                " Shaoru Wang",
                " Congxuan Zhang",
                " Weiming Hu"
            ]
        },
        {
            "paperId": "8811",
            "posterId": "76b",
            "title": "Learning To Prompt for Open-Vocabulary Object Detection With Vision-Language Model",
            "authors": [
                "Yu Du",
                " Fangyun Wei",
                " Zihe Zhang",
                " Miaojing Shi",
                " Yue Gao",
                " Guoqi Li"
            ]
        },
        {
            "paperId": "184",
            "posterId": "77b",
            "title": "Sign Language Video Retrieval With Free-Form Textual Queries",
            "authors": [
                "Amanda Duarte",
                " Samuel Albanie",
                " Xavier Giró-i-Nieto",
                " Gül Varol"
            ]
        },
        {
            "paperId": "11661",
            "posterId": "78b",
            "title": "FashionVLP: Vision Language Transformer for Fashion Retrieval With Feedback",
            "authors": [
                "Sonam Goenka",
                " Zhaoheng Zheng",
                " Ayush Jaiswal",
                " Rakesh Chada",
                " Yue Wu",
                " Varsha Hedau",
                " Pradeep Natarajan"
            ]
        },
        {
            "paperId": "4918",
            "posterId": "79b",
            "title": "Pushing the Performance Limit of Scene Text Recognizer Without Human Annotation",
            "authors": [
                "Caiyuan Zheng",
                " Hui Li",
                " Seon-Min Rhee",
                " Seungju Han",
                " Jae-Joon Han",
                " Peng Wang"
            ]
        },
        {
            "paperId": "9957",
            "posterId": "80b",
            "title": "ESCNet: Gaze Target Detection With the Understanding of 3D Scenes",
            "authors": [
                "Jun Bao",
                " Buyu Liu",
                " Jun Yu"
            ]
        },
        {
            "paperId": "2489",
            "posterId": "81b",
            "title": "Interactive Multi-Class Tiny-Object Detection",
            "authors": [
                "Chunggi Lee",
                " Seonwook Park",
                " Heon Song",
                " Jeongun Ryu",
                " Sanghoon Kim",
                " Haejoon Kim",
                " Sérgio Pereira",
                " Donggeun Yoo"
            ]
        },
        {
            "paperId": "9614",
            "posterId": "82b",
            "title": "Weakly Supervised Rotation-Invariant Aerial Object Detection Network",
            "authors": [
                "Xiaoxu Feng",
                " Xiwen Yao",
                " Gong Cheng",
                " Junwei Han"
            ]
        },
        {
            "paperId": "8402",
            "posterId": "83b",
            "title": "Large Loss Matters in Weakly Supervised Multi-Label Classification",
            "authors": [
                "Youngwook Kim",
                " Jae Myung Kim",
                " Zeynep Akata",
                " Jungwoo Lee"
            ]
        },
        {
            "paperId": "8000",
            "posterId": "84b",
            "title": "MetaFSCIL: A Meta-Learning Approach for Few-Shot Class Incremental Learning",
            "authors": [
                "Zhixiang Chi",
                " Li Gu",
                " Huan Liu",
                " Yang Wang",
                " Yuanhao Yu",
                " Jin Tang"
            ]
        },
        {
            "paperId": "1233",
            "posterId": "85b",
            "title": "FreeSOLO: Learning To Segment Objects Without Annotations",
            "authors": [
                "Xinlong Wang",
                " Zhiding Yu",
                " Shalini De Mello",
                " Jan Kautz",
                " Anima Anandkumar",
                " Chunhua Shen",
                " Jose M. Alvarez"
            ]
        },
        {
            "paperId": "2645",
            "posterId": "86b",
            "title": "Revisiting AP Loss for Dense Object Detection: Adaptive Ranking Pair Selection",
            "authors": [
                "Dongli Xu",
                " Jinhong Deng",
                " Wen Li"
            ]
        },
        {
            "paperId": "3784",
            "posterId": "87b",
            "title": "SIOD: Single Instance Annotated per Category per Image for Object Detection",
            "authors": [
                "Hanjun Li",
                " Xingjia Pan",
                " Ke Yan",
                " Fan Tang",
                " Wei-Shi Zheng"
            ]
        },
        {
            "paperId": "4574",
            "posterId": "88b",
            "title": "Towards Robust Adaptive Object Detection Under Noisy Annotations",
            "authors": [
                "Xinyu Liu",
                " Wuyang Li",
                " Qiushi Yang",
                " Baopu Li",
                " Yixuan Yuan"
            ]
        },
        {
            "paperId": "3139",
            "posterId": "89b",
            "title": "Task-Specific Inconsistency Alignment for Domain Adaptive Object Detection",
            "authors": [
                "Liang Zhao",
                " Limin Wang"
            ]
        },
        {
            "paperId": "3751",
            "posterId": "90b",
            "title": "Salvage of Supervision in Weakly Supervised Object Detection",
            "authors": [
                "Lin Sui",
                " Chen-Lin Zhang",
                " Jianxin Wu"
            ]
        },
        {
            "paperId": "6430",
            "posterId": "91b",
            "title": "Label, Verify, Correct: A Simple Few Shot Object Detection Method",
            "authors": [
                "Prannay Kaul",
                " Weidi Xie",
                " Andrew Zisserman"
            ]
        },
        {
            "paperId": "944",
            "posterId": "92b",
            "title": "Background Activation Suppression for Weakly Supervised Object Localization",
            "authors": [
                "Pingyu Wu",
                " Wei Zhai",
                " Yang Cao"
            ]
        },
        {
            "paperId": "4063",
            "posterId": "93b",
            "title": "Bridging the Gap Between Classification and Localization for Weakly Supervised Object Localization",
            "authors": [
                "Eunji Kim",
                " Siwon Kim",
                " Jungbeom Lee",
                " Hyunwoo Kim",
                " Sungroh Yoon"
            ]
        },
        {
            "paperId": "2560",
            "posterId": "94b",
            "title": "Divide and Conquer: Compositional Experts for Generalized Novel Class Discovery",
            "authors": [
                "Muli Yang",
                " Yuehua Zhu",
                " Jiaping Yu",
                " Aming Wu",
                " Cheng Deng"
            ]
        },
        {
            "paperId": "6708",
            "posterId": "95b",
            "title": "Cloth-Changing Person Re-Identification From a Single Image With Gait Prediction and Regularization",
            "authors": [
                "Xin Jin",
                " Tianyu He",
                " Kecheng Zheng",
                " Zhiheng Yin",
                " Xu Shen",
                " Zhen Huang",
                " Ruoyu Feng",
                " Jianqiang Huang",
                " Zhibo Chen",
                " Xian-Sheng Hua"
            ]
        },
        {
            "paperId": "1508",
            "posterId": "96b",
            "title": "Lifelong Unsupervised Domain Adaptive Person Re-Identification With Coordinated Anti-Forgetting and Adaptation",
            "authors": [
                "Zhipeng Huang",
                " Zhizheng Zhang",
                " Cuiling Lan",
                " Wenjun Zeng",
                " Peng Chu",
                " Quanzeng You",
                " Jiang Wang",
                " Zicheng Liu",
                " Zheng-Jun Zha"
            ]
        },
        {
            "paperId": "4122",
            "posterId": "97b",
            "title": "Unleashing Potential of Unsupervised Pre-Training With Intra-Identity Regularization for Person Re-Identification",
            "authors": [
                "Zizheng Yang",
                " Xin Jin",
                " Kecheng Zheng",
                " Feng Zhao"
            ]
        },
        {
            "paperId": "10049",
            "posterId": "98b",
            "title": "Learning With Twin Noisy Labels for Visible-Infrared Person Re-Identification",
            "authors": [
                "Mouxing Yang",
                " Zhenyu Huang",
                " Peng Hu",
                " Taihao Li",
                " Jiancheng Lv",
                " Xi Peng"
            ]
        },
        {
            "paperId": "7097",
            "posterId": "99b",
            "title": "Towards Total Recall in Industrial Anomaly Detection",
            "authors": [
                "Karsten Roth",
                " Latha Pemula",
                " Joaquin Zepeda",
                " Bernhard Schölkopf",
                " Thomas Brox",
                " Peter Gehler"
            ]
        },
        {
            "paperId": "1207",
            "posterId": "100b",
            "title": "H2FA R-CNN: Holistic and Hierarchical Feature Alignment for Cross-Domain Weakly Supervised Object Detection",
            "authors": [
                "Yunqiu Xu",
                " Yifan Sun",
                " Zongxin Yang",
                " Jiaxu Miao",
                " Yi Yang"
            ]
        },
        {
            "paperId": "4192",
            "posterId": "101b",
            "title": "Geometric and Textural Augmentation for Domain Gap Reduction",
            "authors": [
                "Xiao-Chang Liu",
                " Yong-Liang Yang",
                " Peter Hall"
            ]
        },
        {
            "paperId": "10135",
            "posterId": "102b",
            "title": "General Incremental Learning With Domain-Aware Categorical Representations",
            "authors": [
                "Jiangwei Xie",
                " Shipeng Yan",
                " Xuming He"
            ]
        },
        {
            "paperId": "491",
            "posterId": "103b",
            "title": "DST: Dynamic Substitute Training for Data-Free Black-Box Attack",
            "authors": [
                "Wenxuan Wang",
                " Xuelin Qian",
                " Yanwei Fu",
                " Xiangyang Xue"
            ]
        },
        {
            "paperId": "8711",
            "posterId": "104b",
            "title": "ART-Point: Improving Rotation Robustness of Point Cloud Classifiers via Adversarial Rotation",
            "authors": [
                "Ruibin Wang",
                " Yibo Yang",
                " Dacheng Tao"
            ]
        }
    ],
    "Segmentation, Grouping and Shape Analysis": [
        {
            "paperId": "6126",
            "posterId": "91a",
            "title": "Dynamic Prototype Convolution Network for Few-Shot Semantic Segmentation",
            "authors": [
                "Jie Liu",
                " Yanqi Bao",
                " Guo-Sen Xie",
                " Huan Xiong",
                " Jan-Jakob Sonke",
                " Efstratios Gavves"
            ]
        },
        {
            "paperId": "2899",
            "posterId": "92a",
            "title": "Generalized Few-Shot Semantic Segmentation",
            "authors": [
                "Zhuotao Tian",
                " Xin Lai",
                " Li Jiang",
                " Shu Liu",
                " Michelle Shu",
                " Hengshuang Zhao",
                " Jiaya Jia"
            ]
        },
        {
            "paperId": "9018",
            "posterId": "93a",
            "title": "Learning Non-Target Knowledge for Few-Shot Semantic Segmentation",
            "authors": [
                "Yuanwei Liu",
                " Nian Liu",
                " Qinglong Cao",
                " Xiwen Yao",
                " Junwei Han",
                " Ling Shao"
            ]
        },
        {
            "paperId": "4783",
            "posterId": "94a",
            "title": "Decoupling Zero-Shot Semantic Segmentation",
            "authors": [
                "Jian Ding",
                " Nan Xue",
                " Gui-Song Xia",
                " Dengxin Dai"
            ]
        },
        {
            "paperId": "1590",
            "posterId": "95a",
            "title": "Class-Balanced Pixel-Level Self-Labeling for Domain Adaptive Semantic Segmentation",
            "authors": [
                "Ruihuang Li",
                " Shuai Li",
                " Chenhang He",
                " Yabin Zhang",
                " Xu Jia",
                " Lei Zhang"
            ]
        },
        {
            "paperId": "1034",
            "posterId": "96a",
            "title": "ContrastMask: Contrastive Learning To Segment Every Thing",
            "authors": [
                "Xuehui Wang",
                " Kai Zhao",
                " Ruixin Zhang",
                " Shouhong Ding",
                " Yan Wang",
                " Wei Shen"
            ]
        },
        {
            "paperId": "7789",
            "posterId": "97a",
            "title": "The Neurally-Guided Shape Parser: Grammar-Based Labeling of 3D Shape Regions With Approximate Inference",
            "authors": [
                "R. Kenny Jones",
                " Aalia Habib",
                " Rana Hanocka",
                " Daniel Ritchie"
            ]
        },
        {
            "paperId": "2539",
            "posterId": "98a",
            "title": "AutoGPart: Intermediate Supervision Search for Generalizable 3D Part Segmentation",
            "authors": [
                "Xueyi Liu",
                " Xiaomeng Xu",
                " Anyi Rao",
                " Chuang Gan",
                " Li Yi"
            ]
        },
        {
            "paperId": "1707",
            "posterId": "99a",
            "title": "APES: Articulated Part Extraction From Sprite Sheets",
            "authors": [
                "Zhan Xu",
                " Matthew Fisher",
                " Yang Zhou",
                " Deepali Aneja",
                " Rushikesh Dudhat",
                " Li Yi",
                " Evangelos Kalogerakis"
            ]
        },
        {
            "paperId": "2544",
            "posterId": "100a",
            "title": "GASP, a Generalized Framework for Agglomerative Clustering of Signed Graphs and Its Application to Instance Segmentation",
            "authors": [
                "Alberto Bailoni",
                " Constantin Pape",
                " Nathan Hütsch",
                " Steffen Wolf",
                " Thorsten Beier",
                " Anna Kreshuk",
                " Fred A. Hamprecht"
            ]
        },
        {
            "paperId": "6790",
            "posterId": "101a",
            "title": "CycleMix: A Holistic Strategy for Medical Image Segmentation From Scribble Supervision",
            "authors": [
                "Ke Zhang",
                " Xiahai Zhuang"
            ]
        },
        {
            "paperId": "5602",
            "posterId": "102a",
            "title": "Cross-Patch Dense Contrastive Learning for Semi-Supervised Segmentation of Cellular Nuclei in Histopathologic Images",
            "authors": [
                "Huisi Wu",
                " Zhaoze Wang",
                " Youyi Song",
                " Lin Yang",
                " Jing Qin"
            ]
        },
        {
            "paperId": "3446",
            "posterId": "103a",
            "title": "C-CAM: Causal CAM for Weakly Supervised Semantic Segmentation on Medical Image",
            "authors": [
                "Zhang Chen",
                " Zhiqiang Tian",
                " Jihua Zhu",
                " Ce Li",
                " Shaoyi Du"
            ]
        },
        {
            "paperId": "6268",
            "posterId": "104a",
            "title": "CRIS: CLIP-Driven Referring Image Segmentation",
            "authors": [
                "Zhaoqing Wang",
                " Yu Lu",
                " Qiang Li",
                " Xunqiang Tao",
                " Yandong Guo",
                " Mingming Gong",
                " Tongliang Liu"
            ]
        },
        {
            "paperId": "7820",
            "posterId": "105a",
            "title": "MatteFormer: Transformer-Based Image Matting via Prior-Tokens",
            "authors": [
                "GyuTae Park",
                " SungJoon Son",
                " JaeYoung Yoo",
                " SeHo Kim",
                " Nojun Kwak"
            ]
        },
        {
            "paperId": "3851",
            "posterId": "106a",
            "title": "Boosting Robustness of Image Matting With Context Assembling and Strong Data Augmentation",
            "authors": [
                "Yutong Dai",
                " Brian Price",
                " He Zhang",
                " Chunhua Shen"
            ]
        },
        {
            "paperId": "3405",
            "posterId": "107a",
            "title": "Pyramid Grafting Network for One-Stage High Resolution Saliency Detection",
            "authors": [
                "Chenxi Xie",
                " Changqun Xia",
                " Mingcan Ma",
                " Zhirui Zhao",
                " Xiaowu Chen",
                " Jia Li"
            ]
        },
        {
            "paperId": "2123",
            "posterId": "108a",
            "title": "Multi-Source Uncertainty Mining for Deep Unsupervised Saliency Detection",
            "authors": [
                "Yifan Wang",
                " Wenbo Zhang",
                " Lijun Wang",
                " Ting Liu",
                " Huchuan Lu"
            ]
        },
        {
            "paperId": "4573",
            "posterId": "109a",
            "title": "Modeling Motion With Multi-Modal Features for Text-Based Video Segmentation",
            "authors": [
                "Wangbo Zhao",
                " Kai Wang",
                " Xiangxiang Chu",
                " Fuzhao Xue",
                " Xinchao Wang",
                " Yang You"
            ]
        },
        {
            "paperId": "5002",
            "posterId": "110a",
            "title": "GAT-CADNet: Graph Attention Network for Panoptic Symbol Spotting in CAD Drawings",
            "authors": [
                "Zhaohua Zheng",
                " Jianfang Li",
                " Lingjie Zhu",
                " Honghua Li",
                " Frank Petzold",
                " Ping Tan"
            ]
        },
        {
            "paperId": "587",
            "posterId": "111a",
            "title": "Bending Graphs: Hierarchical Shape Matching Using Gated Optimal Transport",
            "authors": [
                "Mahdi Saleh",
                " Shun-Cheng Wu",
                " Luca Cosmo",
                " Nassir Navab",
                " Benjamin Busam",
                " Federico Tombari"
            ]
        },
        {
            "paperId": "3312",
            "posterId": "112a",
            "title": "CAPRI-Net: Learning Compact CAD Shapes With Adaptive Primitive Assembly",
            "authors": [
                "Fenggen Yu",
                " Zhiqin Chen",
                " Manyi Li",
                " Aditya Sanghi",
                " Hooman Shayani",
                " Ali Mahdavi-Amiri",
                " Hao Zhang"
            ]
        },
        {
            "paperId": "1743",
            "posterId": "113a",
            "title": "RIM-Net: Recursive Implicit Fields for Unsupervised Learning of Hierarchical Shape Structures",
            "authors": [
                "Chengjie Niu",
                " Manyi Li",
                " Kai Xu",
                " Hao Zhang"
            ]
        },
        {
            "paperId": "3978",
            "posterId": "114a",
            "title": "Discovering Objects That Can Move",
            "authors": [
                "Zhipeng Bao",
                " Pavel Tokmakov",
                " Allan Jabri",
                " Yu-Xiong Wang",
                " Adrien Gaidon",
                " Martial Hebert"
            ]
        },
        {
            "paperId": "2604",
            "posterId": "115a",
            "title": "PatchFormer: An Efficient Point Transformer With Patch Attention",
            "authors": [
                "Cheng Zhang",
                " Haocheng Wan",
                " Xinyi Shen",
                " Zizhao Wu"
            ]
        },
        {
            "paperId": "4099",
            "posterId": "116a",
            "title": "Panoptic-PHNet: Towards Real-Time and High-Precision LiDAR Panoptic Segmentation via Clustering Pseudo Heatmap",
            "authors": [
                "Jinke Li",
                " Xiao He",
                " Yang Wen",
                " Yuan Gao",
                " Xiaoqiang Cheng",
                " Dan Zhang"
            ]
        },
        {
            "paperId": "3933",
            "posterId": "117a",
            "title": "SemAffiNet: Semantic-Affine Transformation for Point Cloud Segmentation",
            "authors": [
                "Ziyi Wang",
                " Yongming Rao",
                " Xumin Yu",
                " Jie Zhou",
                " Jiwen Lu"
            ]
        },
        {
            "paperId": "4983",
            "posterId": "118a",
            "title": "An MIL-Derived Transformer for Weakly Supervised Point Cloud Segmentation",
            "authors": [
                "Cheng-Kun Yang",
                " Ji-Jia Wu",
                " Kai-Syun Chen",
                " Yung-Yu Chuang",
                " Yen-Yu Lin"
            ]
        },
        {
            "paperId": "7469",
            "posterId": "119a",
            "title": "Weakly Supervised Segmentation on Outdoor 4D Point Clouds With Temporal Matching and Spatial Graph Propagation",
            "authors": [
                "Hanyu Shi",
                " Jiacheng Wei",
                " Ruibo Li",
                " Fayao Liu",
                " Guosheng Lin"
            ]
        },
        {
            "paperId": "4583",
            "posterId": "120a",
            "title": "Point2Cyl: Reverse Engineering 3D Objects From Point Clouds to Extrusion Cylinders",
            "authors": [
                "Mikaela Angelina Uy",
                " Yen-Yu Chang",
                " Minhyuk Sung",
                " Purvi Goel",
                " Joseph G. Lambourne",
                " Tolga Birdal",
                " Leonidas J. Guibas"
            ]
        }
    ],
    "3D From Single Images": [
        {
            "paperId": "41",
            "posterId": "116b",
            "title": "360MonoDepth: High-Resolution 360deg Monocular Depth Estimation",
            "authors": [
                "Manuel Rey-Area",
                " Mingze Yuan",
                " Christian Richardt"
            ]
        },
        {
            "paperId": "4391",
            "posterId": "117b",
            "title": "Pre-Train, Self-Train, Distill: A Simple Recipe for Supersizing 3D Reconstruction",
            "authors": [
                "Kalyan Vasudev Alwala",
                " Abhinav Gupta",
                " Shubham Tulsiani"
            ]
        },
        {
            "paperId": "6088",
            "posterId": "118b",
            "title": "DGECN: A Depth-Guided Edge Convolutional Network for End-to-End 6D Pose Estimation",
            "authors": [
                "Tuo Cao",
                " Fei Luo",
                " Yanping Fu",
                " Wenxiao Zhang",
                " Shengjie Zheng",
                " Chunxia Xiao"
            ]
        },
        {
            "paperId": "2989",
            "posterId": "119b",
            "title": "MonoGround: Detecting Monocular 3D Objects From the Ground",
            "authors": [
                "Zequn Qin",
                " Xi Li"
            ]
        },
        {
            "paperId": "2686",
            "posterId": "120b",
            "title": "3D Shape Reconstruction From 2D Images With Disentangled Attribute Flow",
            "authors": [
                "Xin Wen",
                " Junsheng Zhou",
                " Yu-Shen Liu",
                " Hua Su",
                " Zhen Dong",
                " Zhizhong Han"
            ]
        },
        {
            "paperId": "2657",
            "posterId": "121b",
            "title": "Toward Practical Monocular Indoor Depth Estimation",
            "authors": [
                "Cho-Ying Wu",
                " Jialiang Wang",
                " Michael Hall",
                " Ulrich Neumann",
                " Shuochen Su"
            ]
        },
        {
            "paperId": "4692",
            "posterId": "122b",
            "title": "Focal Length and Object Pose Estimation via Render and Compare",
            "authors": [
                "Georgy Ponimatkin",
                " Yann Labbé",
                " Bryan Russell",
                " Mathieu Aubry",
                " Josef Sivic"
            ]
        },
        {
            "paperId": "6311",
            "posterId": "123b",
            "title": "CLIP-NeRF: Text-and-Image Driven Manipulation of Neural Radiance Fields",
            "authors": [
                "Can Wang",
                " Menglei Chai",
                " Mingming He",
                " Dongdong Chen",
                " Jing Liao"
            ]
        },
        {
            "paperId": "2116",
            "posterId": "124b",
            "title": "Registering Explicit to Implicit: Towards High-Fidelity Garment Mesh Reconstruction From Single Images",
            "authors": [
                "Heming Zhu",
                " Lingteng Qiu",
                " Yuda Qiu",
                " Xiaoguang Han"
            ]
        },
        {
            "paperId": "8082",
            "posterId": "125b",
            "title": "Layered Depth Refinement With Mask Guidance",
            "authors": [
                "Soo Ye Kim",
                " Jianming Zhang",
                " Simon Niklaus",
                " Yifei Fan",
                " Simon Chen",
                " Zhe Lin",
                " Munchurl Kim"
            ]
        },
        {
            "paperId": "1031",
            "posterId": "126b",
            "title": "HEAT: Holistic Edge Attention Transformer for Structured Reconstruction",
            "authors": [
                "Jiacheng Chen",
                " Yiming Qian",
                " Yasutaka Furukawa"
            ]
        },
        {
            "paperId": "931",
            "posterId": "127b",
            "title": "BARC: Learning To Regress 3D Dog Shape From Images by Exploiting Breed Information",
            "authors": [
                "Nadine Rüegg",
                " Silvia Zuffi",
                " Konrad Schindler",
                " Michael J. Black"
            ]
        },
        {
            "paperId": "8688",
            "posterId": "128b",
            "title": "Time3D: End-to-End Joint Monocular 3D Object Detection and Tracking for Autonomous Driving",
            "authors": [
                "Peixuan Li",
                " Jieyu Jin"
            ]
        },
        {
            "paperId": "816",
            "posterId": "129b",
            "title": "What's in Your Hands? 3D Reconstruction of Generic Objects in Hands",
            "authors": [
                "Yufei Ye",
                " Abhinav Gupta",
                " Shubham Tulsiani"
            ]
        },
        {
            "paperId": "7814",
            "posterId": "130b",
            "title": "3D Moments From Near-Duplicate Photos",
            "authors": [
                "Qianqian Wang",
                " Zhengqi Li",
                " David Salesin",
                " Noah Snavely",
                " Brian Curless",
                " Janne Kontkanen"
            ]
        },
        {
            "paperId": "5766",
            "posterId": "131b",
            "title": "Neural Window Fully-Connected CRFs for Monocular Depth Estimation",
            "authors": [
                "Weihao Yuan",
                " Xiaodong Gu",
                " Zuozhuo Dai",
                " Siyu Zhu",
                " Ping Tan"
            ]
        },
        {
            "paperId": "9095",
            "posterId": "132b",
            "title": "PUMP: Pyramidal and Uniqueness Matching Priors for Unsupervised Learning of Local Descriptors",
            "authors": [
                "Jérome Revaud",
                " Vincent Leroy",
                " Philippe Weinzaepfel",
                " Boris Chidlovskii"
            ]
        },
        {
            "paperId": "3717",
            "posterId": "133b",
            "title": "CroMo: Cross-Modal Learning for Monocular Depth Estimation",
            "authors": [
                "Yannick Verdié",
                " Jifei Song",
                " Barnabé Mas",
                " Benjamin Busam",
                " Ales̆ Leonardis",
                " Steven McDonagh"
            ]
        },
        {
            "paperId": "258",
            "posterId": "134b",
            "title": "f-SfT: Shape-From-Template With a Physics-Based Deformation Model",
            "authors": [
                "Navami Kairanda",
                " Edith Tretschk",
                " Mohamed Elgharib",
                " Christian Theobalt",
                " Vladislav Golyanik"
            ]
        },
        {
            "paperId": "923",
            "posterId": "135b",
            "title": "Human-Aware Object Placement for Visual Environment Reconstruction",
            "authors": [
                "Hongwei Yi",
                " Chun-Hao P. Huang",
                " Dimitrios Tzionas",
                " Muhammed Kocabas",
                " Mohamed Hassan",
                " Siyu Tang",
                " Justus Thies",
                " Michael J. Black"
            ]
        },
        {
            "paperId": "11298",
            "posterId": "136b",
            "title": "AutoRF: Learning 3D Object Radiance Fields From Single View Observations",
            "authors": [
                "Norman Müller",
                " Andrea Simonelli",
                " Lorenzo Porzi",
                " Samuel Rota Bulò",
                " Matthias Nießner",
                " Peter Kontschieder"
            ]
        },
        {
            "paperId": "7080",
            "posterId": "137b",
            "title": "Pix2NeRF: Unsupervised Conditional p-GAN for Single Image to Neural Radiance Fields Translation",
            "authors": [
                "Shengqu Cai",
                " Anton Obukhov",
                " Dengxin Dai",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "2163",
            "posterId": "138b",
            "title": "MonoScene: Monocular 3D Semantic Scene Completion",
            "authors": [
                "Anh-Quan Cao",
                " Raoul de Charette"
            ]
        },
        {
            "paperId": "12016",
            "posterId": "139b",
            "title": "GenDR: A Generalized Differentiable Renderer",
            "authors": [
                "Felix Petersen",
                " Bastian Goldluecke",
                " Christian Borgelt",
                " Oliver Deussen"
            ]
        },
        {
            "paperId": "4069",
            "posterId": "140b",
            "title": "MonoDTR: Monocular 3D Object Detection With Depth-Aware Transformer",
            "authors": [
                "Kuan-Chih Huang",
                " Tsung-Han Wu",
                " Hung-Ting Su",
                " Winston H. Hsu"
            ]
        },
        {
            "paperId": "7078",
            "posterId": "141b",
            "title": "ROCA: Robust CAD Model Retrieval and Alignment From a Single Image",
            "authors": [
                "Can Gümeli",
                " Angela Dai",
                " Matthias Nießner"
            ]
        }
    ],
    "Photogrammetry and Remote Sensing": [
        {
            "paperId": "971",
            "posterId": "173a",
            "title": "HyperTransformer: A Textural and Spectral Feature Fusion Transformer for Pansharpening",
            "authors": [
                "Wele Gedara Chaminda Bandara",
                " Vishal M. Patel"
            ]
        },
        {
            "paperId": "990",
            "posterId": "174a",
            "title": "Revisiting Near/Remote Sensing With Geospatial Attention",
            "authors": [
                "Scott Workman",
                " M. Usman Rafique",
                " Hunter Blanton",
                " Nathan Jacobs"
            ]
        },
        {
            "paperId": "2718",
            "posterId": "175a",
            "title": "Memory-Augmented Deep Conditional Unfolding Network for Pan-Sharpening",
            "authors": [
                "Gang Yang",
                " Man Zhou",
                " Keyu Yan",
                " Aiping Liu",
                " Xueyang Fu",
                " Fan Wang"
            ]
        },
        {
            "paperId": "3511",
            "posterId": "176a",
            "title": "Mutual Information-Driven Pan-Sharpening",
            "authors": [
                "Man Zhou",
                " Keyu Yan",
                " Jie Huang",
                " Zihe Yang",
                " Xueyang Fu",
                " Feng Zhao"
            ]
        },
        {
            "paperId": "3982",
            "posterId": "177a",
            "title": "Sparse and Complete Latent Organization for Geospatial Semantic Segmentation",
            "authors": [
                "Fengyu Yang",
                " Chenyang Ma"
            ]
        },
        {
            "paperId": "5907",
            "posterId": "178a",
            "title": "The Probabilistic Normal Epipolar Constraint for Frame-to-Frame Rotation Optimization Under Uncertain Feature Positions",
            "authors": [
                "Dominik Muhle",
                " Lukas Koestler",
                " Nikolaus Demmel",
                " Florian Bernard",
                " Daniel Cremers"
            ]
        },
        {
            "paperId": "4025",
            "posterId": "179a",
            "title": "Oriented RepPoints for Aerial Object Detection",
            "authors": [
                "Wentong Li",
                " Yijie Chen",
                " Kaixuan Hu",
                " Jianke Zhu"
            ]
        },
        {
            "paperId": "6403",
            "posterId": "180a",
            "title": "Using 3D Topological Connectivity for Ghost Particle Reduction in Flow Reconstruction",
            "authors": [
                "Christina Tsalicoglou",
                " Thomas Rösgen"
            ]
        },
        {
            "paperId": "8986",
            "posterId": "181a",
            "title": "PolyWorld: Polygonal Building Extraction With Graph Neural Networks in Satellite Images",
            "authors": [
                "Stefano Zorzi",
                " Shabab Bazrafkan",
                " Stefan Habenschuss",
                " Friedrich Fraundorfer"
            ]
        },
        {
            "paperId": "8832",
            "posterId": "182a",
            "title": "Self-Supervised Super-Resolution for Multi-Exposure Push-Frame Satellites",
            "authors": [
                "Ngoc Long Nguyen",
                " Jérémy Anger",
                " Axel Davy",
                " Pablo Arias",
                " Gabriele Facciolo"
            ]
        }
    ],
    "Low-Level Vision": [
        {
            "paperId": "163",
            "posterId": "133a",
            "title": "Bilateral Video Magnification Filter",
            "authors": [
                "Shoichiro Takeda",
                " Kenta Niwa",
                " Mariko Isogawa",
                " Shinya Shimizu",
                " Kazuki Okami",
                " Yushi Aono"
            ]
        },
        {
            "paperId": "4527",
            "posterId": "134a",
            "title": "Neural Data-Dependent Transform for Learned Image Compression",
            "authors": [
                "Dezhao Wang",
                " Wenhan Yang",
                " Yueyu Hu",
                " Jiaying Liu"
            ]
        },
        {
            "paperId": "4329",
            "posterId": "135a",
            "title": "Towards Bidirectional Arbitrary Image Rescaling: Joint Optimization and Cycle Idempotence",
            "authors": [
                "Zhihong Pan",
                " Baopu Li",
                " Dongliang He",
                " Mingde Yao",
                " Wenhao Wu",
                " Tianwei Lin",
                " Xin Li",
                " Errui Ding"
            ]
        },
        {
            "paperId": "4093",
            "posterId": "136a",
            "title": "Deep Generalized Unfolding Networks for Image Restoration",
            "authors": [
                "Chong Mou",
                " Qian Wang",
                " Jian Zhang"
            ]
        },
        {
            "paperId": "3967",
            "posterId": "137a",
            "title": "Look Back and Forth: Video Super-Resolution With Explicit Temporal Difference Modeling",
            "authors": [
                "Takashi Isobe",
                " Xu Jia",
                " Xin Tao",
                " Changlin Li",
                " Ruihuang Li",
                " Yongjie Shi",
                " Jing Mu",
                " Huchuan Lu",
                " Yu-Wing Tai"
            ]
        },
        {
            "paperId": "9885",
            "posterId": "138a",
            "title": "XYDeblur: Divide and Conquer for Single Image Deblurring",
            "authors": [
                "Seo-Won Ji",
                " Jeongmin Lee",
                " Seung-Wook Kim",
                " Jun-Pyo Hong",
                " Seung-Jin Baek",
                " Seung-Won Jung",
                " Sung-Jea Ko"
            ]
        },
        {
            "paperId": "8572",
            "posterId": "139a",
            "title": "Abandoning the Bayer-Filter To See in the Dark",
            "authors": [
                "Xingbo Dong",
                " Wanyan Xu",
                " Zhihui Miao",
                " Lan Ma",
                " Chao Zhang",
                " Jiewen Yang",
                " Zhe Jin",
                " Andrew Beng Jin Teoh",
                " Jiajun Shen"
            ]
        },
        {
            "paperId": "9293",
            "posterId": "140a",
            "title": "RSTT: Real-Time Spatial Temporal Transformer for Space-Time Video Super-Resolution",
            "authors": [
                "Zhicheng Geng",
                " Luming Liang",
                " Tianyu Ding",
                " Ilya Zharkov"
            ]
        },
        {
            "paperId": "8149",
            "posterId": "141a",
            "title": "All-in-One Image Restoration for Unknown Corruption",
            "authors": [
                "Boyun Li",
                " Xiao Liu",
                " Peng Hu",
                " Zhongqin Wu",
                " Jiancheng Lv",
                " Xi Peng"
            ]
        },
        {
            "paperId": "9697",
            "posterId": "142a",
            "title": "Modeling sRGB Camera Noise With Normalizing Flows",
            "authors": [
                "Shayan Kousha",
                " Ali Maleky",
                " Michael S. Brown",
                " Marcus A. Brubaker"
            ]
        },
        {
            "paperId": "3788",
            "posterId": "143a",
            "title": "A Differentiable Two-Stage Alignment Scheme for Burst Image Reconstruction With Large Shift",
            "authors": [
                "Shi Guo",
                " Xi Yang",
                " Jianqi Ma",
                " Gaofeng Ren",
                " Lei Zhang"
            ]
        },
        {
            "paperId": "1431",
            "posterId": "144a",
            "title": "Video Frame Interpolation Transformer",
            "authors": [
                "Zhihao Shi",
                " Xiangyu Xu",
                " Xiaohong Liu",
                " Jun Chen",
                " Ming-Hsuan Yang"
            ]
        },
        {
            "paperId": "1412",
            "posterId": "145a",
            "title": "The Devil Is in the Details: Window-Based Attention for Image Compression",
            "authors": [
                "Renjie Zou",
                " Chunfeng Song",
                " Zhaoxiang Zhang"
            ]
        },
        {
            "paperId": "1176",
            "posterId": "146a",
            "title": "Mask-Guided Spectral-Wise Transformer for Efficient Hyperspectral Image Reconstruction",
            "authors": [
                "Yuanhao Cai",
                " Jing Lin",
                " Xiaowan Hu",
                " Haoqian Wang",
                " Xin Yuan",
                " Yulun Zhang",
                " Radu Timofte",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "3387",
            "posterId": "147a",
            "title": "RestoreFormer: High-Quality Blind Face Restoration From Undegraded Key-Value Pairs",
            "authors": [
                "Zhouxia Wang",
                " Jiawei Zhang",
                " Runjian Chen",
                " Wenping Wang",
                " Ping Luo"
            ]
        },
        {
            "paperId": "3051",
            "posterId": "148a",
            "title": "AdaInt: Learning Adaptive Intervals for 3D Lookup Tables on Real-Time Image Enhancement",
            "authors": [
                "Canqian Yang",
                " Meiguang Jin",
                " Xu Jia",
                " Yi Xu",
                " Ying Chen"
            ]
        },
        {
            "paperId": "2882",
            "posterId": "149a",
            "title": "HerosNet: Hyperspectral Explicable Reconstruction and Optimal Sampling Deep Network for Snapshot Compressive Imaging",
            "authors": [
                "Xuanyu Zhang",
                " Yongbing Zhang",
                " Ruiqin Xiong",
                " Qilin Sun",
                " Jian Zhang"
            ]
        },
        {
            "paperId": "2182",
            "posterId": "150a",
            "title": "HDNet: High-Resolution Dual-Domain Learning for Spectral Compressive Imaging",
            "authors": [
                "Xiaowan Hu",
                " Yuanhao Cai",
                " Jing Lin",
                " Haoqian Wang",
                " Xin Yuan",
                " Yulun Zhang",
                " Radu Timofte",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "6342",
            "posterId": "151a",
            "title": "Learning To Zoom Inside Camera Imaging Pipeline",
            "authors": [
                "Chengzhou Tang",
                " Yuqiang Yang",
                " Bing Zeng",
                " Ping Tan",
                " Shuaicheng Liu"
            ]
        },
        {
            "paperId": "335",
            "posterId": "152a",
            "title": "Towards an End-to-End Framework for Flow-Guided Video Inpainting",
            "authors": [
                "Zhen Li",
                " Cheng-Ze Lu",
                " Jianhua Qin",
                " Chun-Le Guo",
                " Ming-Ming Cheng"
            ]
        },
        {
            "paperId": "2141",
            "posterId": "153a",
            "title": "Context-Aware Video Reconstruction for Rolling Shutter Cameras",
            "authors": [
                "Bin Fan",
                " Yuchao Dai",
                " Zhiyuan Zhang",
                " Qi Liu",
                " Mingyi He"
            ]
        },
        {
            "paperId": "5516",
            "posterId": "154a",
            "title": "CVF-SID: Cyclic Multi-Variate Function for Self-Supervised Image Denoising by Disentangling Noise From Image",
            "authors": [
                "Reyhaneh Neshatavar",
                " Mohsen Yavartanoo",
                " Sanghyun Son",
                " Kyoung Mu Lee"
            ]
        },
        {
            "paperId": "4529",
            "posterId": "155a",
            "title": "Global Matching With Overlapping Attention for Optical Flow Estimation",
            "authors": [
                "Shiyu Zhao",
                " Long Zhao",
                " Zhixing Zhang",
                " Enyu Zhou",
                " Dimitris Metaxas"
            ]
        },
        {
            "paperId": "1482",
            "posterId": "156a",
            "title": "CRAFT: Cross-Attentional Flow Transformer for Robust Optical Flow",
            "authors": [
                "Xiuchao Sui",
                " Shaohua Li",
                " Xue Geng",
                " Yan Wu",
                " Xinxing Xu",
                " Yong Liu",
                " Rick Goh",
                " Hongyuan Zhu"
            ]
        },
        {
            "paperId": "1048",
            "posterId": "157a",
            "title": "Unified Multivariate Gaussian Mixture for Efficient Neural Image Compression",
            "authors": [
                "Xiaosu Zhu",
                " Jingkuan Song",
                " Lianli Gao",
                " Feng Zheng",
                " Heng Tao Shen"
            ]
        },
        {
            "paperId": "4286",
            "posterId": "158a",
            "title": "Video Demoiréing With Relation-Based Temporal Consistency",
            "authors": [
                "Peng Dai",
                " Xin Yu",
                " Lan Ma",
                " Baoheng Zhang",
                " Jia Li",
                " Wenbo Li",
                " Jiajun Shen",
                " Xiaojuan Qi"
            ]
        },
        {
            "paperId": "6635",
            "posterId": "159a",
            "title": "Noise2NoiseFlow: Realistic Camera Noise Modeling Without Clean Images",
            "authors": [
                "Ali Maleky",
                " Shayan Kousha",
                " Michael S. Brown",
                " Marcus A. Brubaker"
            ]
        },
        {
            "paperId": "5086",
            "posterId": "160a",
            "title": "Deep Constrained Least Squares for Blind Image Super-Resolution",
            "authors": [
                "Ziwei Luo",
                " Haibin Huang",
                " Lei Yu",
                " Youwei Li",
                " Haoqiang Fan",
                " Shuaicheng Liu"
            ]
        },
        {
            "paperId": "12027",
            "posterId": "161a",
            "title": "Learning Multiple Adverse Weather Removal via Two-Stage Knowledge Learning and Multi-Contrastive Regularization: Toward a Unified Model",
            "authors": [
                "Wei-Ting Chen",
                " Zhi-Kai Huang",
                " Cheng-Che Tsai",
                " Hao-Hsiang Yang",
                " Jian-Jiun Ding",
                " Sy-Yen Kuo"
            ]
        },
        {
            "paperId": "5762",
            "posterId": "162a",
            "title": "Unsupervised Homography Estimation With Coplanarity-Aware GAN",
            "authors": [
                "Mingbo Hong",
                " Yuhang Lu",
                " Nianjin Ye",
                " Chunyu Lin",
                " Qijun Zhao",
                " Shuaicheng Liu"
            ]
        }
    ],
    "Behavior Analysis": [
        {
            "paperId": "2656",
            "posterId": "213a",
            "title": "Self-Supervised Keypoint Discovery in Behavioral Videos",
            "authors": [
                "Jennifer J. Sun",
                " Serim Ryou",
                " Roni H. Goldshmid",
                " Brandon Weissbourd",
                " John O. Dabiri",
                " David J. Anderson",
                " Ann Kennedy",
                " Yisong Yue",
                " Pietro Perona"
            ]
        },
        {
            "paperId": "874",
            "posterId": "214a",
            "title": "Learning To Align Sequential Actions in the Wild",
            "authors": [
                "Weizhe Liu",
                " Bugra Tekin",
                " Huseyin Coskun",
                " Vibhav Vineet",
                " Pascal Fua",
                " Marc Pollefeys"
            ]
        },
        {
            "paperId": "7245",
            "posterId": "215a",
            "title": "Dynamic 3D Gaze From Afar: Deep Gaze Estimation From Temporal Eye-Head-Body Coordination",
            "authors": [
                "Soma Nonaka",
                " Shohei Nobuhara",
                " Ko Nishino"
            ]
        },
        {
            "paperId": "4809",
            "posterId": "216a",
            "title": "End-to-End Human-Gaze-Target Detection With Transformers",
            "authors": [
                "Danyang Tu",
                " Xiongkuo Min",
                " Huiyu Duan",
                " Guodong Guo",
                " Guangtao Zhai",
                " Wei Shen"
            ]
        },
        {
            "paperId": "7132",
            "posterId": "217a",
            "title": "Automatic Synthesis of Diverse Weak Supervision Sources for Behavior Analysis",
            "authors": [
                "Albert Tseng",
                " Jennifer J. Sun",
                " Yisong Yue"
            ]
        },
        {
            "paperId": "9590",
            "posterId": "218a",
            "title": "MUSE-VAE: Multi-Scale VAE for Environment-Aware Long Term Trajectory Prediction",
            "authors": [
                "Mihee Lee",
                " Samuel S. Sohn",
                " Seonghyeon Moon",
                " Sejong Yoon",
                " Mubbasir Kapadia",
                " Vladimir Pavlovic"
            ]
        },
        {
            "paperId": "10192",
            "posterId": "219a",
            "title": "Graph-Based Spatial Transformer With Memory Replay for Multi-Future Pedestrian Trajectory Prediction",
            "authors": [
                "Lihuan Li",
                " Maurice Pagnucco",
                " Yang Song"
            ]
        },
        {
            "paperId": "7946",
            "posterId": "220a",
            "title": "End-to-End Trajectory Distribution Prediction Based on Occupancy Grid Maps",
            "authors": [
                "Ke Guo",
                " Wenxi Liu",
                " Jia Pan"
            ]
        },
        {
            "paperId": "754",
            "posterId": "221a",
            "title": "Learning Affordance Grounding From Exocentric Images",
            "authors": [
                "Hongchen Luo",
                " Wei Zhai",
                " Jing Zhang",
                " Yang Cao",
                " Dacheng Tao"
            ]
        }
    ],
    "Vision Applications & Systems": [
        {
            "paperId": "1915",
            "posterId": "222a",
            "title": "3D Scene Painting via Semantic Image Synthesis",
            "authors": [
                "Jaebong Jeong",
                " Janghun Jo",
                " Sunghyun Cho",
                " Jaesik Park"
            ]
        },
        {
            "paperId": "6370",
            "posterId": "223a",
            "title": "Learning Invisible Markers for Hidden Codes in Offline-to-Online Photography",
            "authors": [
                "Jun Jia",
                " Zhongpai Gao",
                " Dandan Zhu",
                " Xiongkuo Min",
                " Guangtao Zhai",
                " Xiaokang Yang"
            ]
        },
        {
            "paperId": "2264",
            "posterId": "224a",
            "title": "ETHSeg: An Amodel Instance Segmentation Network and a Real-World Dataset for X-Ray Waste Inspection",
            "authors": [
                "Lingteng Qiu",
                " Zhangyang Xiong",
                " Xuhao Wang",
                " Kenkun Liu",
                " Yihan Li",
                " Guanying Chen",
                " Xiaoguang Han",
                " Shuguang Cui"
            ]
        },
        {
            "paperId": "2112",
            "posterId": "225a",
            "title": "Doodle It Yourself: Class Incremental Learning by Drawing a Few Sketches",
            "authors": [
                "Ayan Kumar Bhunia",
                " Viswanatha Reddy Gajjala",
                " Subhadeep Koley",
                " Rohit Kundu",
                " Aneeshan Sain",
                " Tao Xiang",
                " Yi-Zhe Song"
            ]
        },
        {
            "paperId": "5892",
            "posterId": "226a",
            "title": "Image Disentanglement Autoencoder for Steganography Without Embedding",
            "authors": [
                "Xiyao Liu",
                " Ziping Ma",
                " Junxing Ma",
                " Jian Zhang",
                " Gerald Schaefer",
                " Hui Fang"
            ]
        },
        {
            "paperId": "1885",
            "posterId": "227a",
            "title": "Adaptive Hierarchical Representation Learning for Long-Tailed Object Detection",
            "authors": [
                "Banghuai Li"
            ]
        },
        {
            "paperId": "5934",
            "posterId": "228a",
            "title": "Semiconductor Defect Detection by Hybrid Classical-Quantum Deep Learning",
            "authors": [
                "Yuan-Fu Yang",
                " Min Sun"
            ]
        },
        {
            "paperId": "1616",
            "posterId": "229a",
            "title": "Density-Preserving Deep Point Cloud Compression",
            "authors": [
                "Yun He",
                " Xinlin Ren",
                " Danhang Tang",
                " Yinda Zhang",
                " Xiangyang Xue",
                " Yanwei Fu"
            ]
        },
        {
            "paperId": "9360",
            "posterId": "230a",
            "title": "Graph-Context Attention Networks for Size-Varied Deep Graph Matching",
            "authors": [
                "Zheheng Jiang",
                " Hossein Rahmani",
                " Plamen Angelov",
                " Sue Black",
                " Bryan M. Williams"
            ]
        },
        {
            "paperId": "968",
            "posterId": "231a",
            "title": "TransWeather: Transformer-Based Restoration of Images Degraded by Adverse Weather Conditions",
            "authors": [
                "Jeya Maria Jose Valanarasu",
                " Rajeev Yasarla",
                " Vishal M. Patel"
            ]
        },
        {
            "paperId": "1872",
            "posterId": "232a",
            "title": "ObjectFormer for Image Manipulation Detection and Localization",
            "authors": [
                "Junke Wang",
                " Zuxuan Wu",
                " Jingjing Chen",
                " Xintong Han",
                " Abhinav Shrivastava",
                " Ser-Nam Lim",
                " Yu-Gang Jiang"
            ]
        },
        {
            "paperId": "7760",
            "posterId": "233a",
            "title": "Sequential Voting With Relational Box Fields for Active Object Detection",
            "authors": [
                "Qichen Fu",
                " Xingyu Liu",
                " Kris Kitani"
            ]
        },
        {
            "paperId": "6580",
            "posterId": "234a",
            "title": "Efficient Classification of Very Large Images With Tiny Objects",
            "authors": [
                "Fanjie Kong",
                " Ricardo Henao"
            ]
        },
        {
            "paperId": "6468",
            "posterId": "235a",
            "title": "Partially Does It: Towards Scene-Level FG-SBIR With Partial Input",
            "authors": [
                "Pinaki Nath Chowdhury",
                " Ayan Kumar Bhunia",
                " Viswanatha Reddy Gajjala",
                " Aneeshan Sain",
                " Tao Xiang",
                " Yi-Zhe Song"
            ]
        },
        {
            "paperId": "6025",
            "posterId": "236a",
            "title": "Long-Term Visual Map Sparsification With Heterogeneous GNN",
            "authors": [
                "Ming-Fang Chang",
                " Yipu Zhao",
                " Rajvi Shah",
                " Jakob J. Engel",
                " Michael Kaess",
                " Simon Lucey"
            ]
        },
        {
            "paperId": "141",
            "posterId": "237a",
            "title": "Connecting the Complementary-View Videos: Joint Camera Identification and Subject Association",
            "authors": [
                "Ruize Han",
                " Yiyang Gan",
                " Jiacheng Li",
                " Feifan Wang",
                " Wei Feng",
                " Song Wang"
            ]
        },
        {
            "paperId": "10095",
            "posterId": "238a",
            "title": "DiffusionCLIP: Text-Guided Diffusion Models for Robust Image Manipulation",
            "authors": [
                "Gwanghyun Kim",
                " Taesung Kwon",
                " Jong Chul Ye"
            ]
        },
        {
            "paperId": "3621",
            "posterId": "239a",
            "title": "Aesthetic Text Logo Synthesis via Content-Aware Layout Inferring",
            "authors": [
                "Yizhi Wang",
                " Guo Pu",
                " Wenhan Luo",
                " Yexin Wang",
                " Pengfei Xiong",
                " Hongwen Kang",
                " Zhouhui Lian"
            ]
        },
        {
            "paperId": "1079",
            "posterId": "240a",
            "title": "Rethinking Image Cropping: Exploring Diverse Compositions From Global Views",
            "authors": [
                "Gengyun Jia",
                " Huaibo Huang",
                " Chaoyou Fu",
                " Ran He"
            ]
        },
        {
            "paperId": "1680",
            "posterId": "241a",
            "title": "Defensive Patches for Robust Recognition in the Physical World",
            "authors": [
                "Jiakai Wang",
                " Zixin Yin",
                " Pengfei Hu",
                " Aishan Liu",
                " Renshuai Tao",
                " Haotong Qin",
                " Xianglong Liu",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "8380",
            "posterId": "242a",
            "title": "Semi-Supervised Video Paragraph Grounding With Contrastive Encoder",
            "authors": [
                "Xun Jiang",
                " Xing Xu",
                " Jingran Zhang",
                " Fumin Shen",
                " Zuo Cao",
                " Heng Tao Shen"
            ]
        },
        {
            "paperId": "5336",
            "posterId": "243a",
            "title": "Large-Scale Pre-Training for Person Re-Identification With Noisy Labels",
            "authors": [
                "Dengpan Fu",
                " Dongdong Chen",
                " Hao Yang",
                " Jianmin Bao",
                " Lu Yuan",
                " Lei Zhang",
                " Houqiang Li",
                " Fang Wen",
                " Dong Chen"
            ]
        },
        {
            "paperId": "1146",
            "posterId": "244a",
            "title": "Meta Distribution Alignment for Generalizable Person Re-Identification",
            "authors": [
                "Hao Ni",
                " Jingkuan Song",
                " Xiaopeng Luo",
                " Feng Zheng",
                " Wen Li",
                " Heng Tao Shen"
            ]
        },
        {
            "paperId": "5429",
            "posterId": "245a",
            "title": "FvOR: Robust Joint Shape and Pose Optimization for Few-View Object Reconstruction",
            "authors": [
                "Zhenpei Yang",
                " Zhile Ren",
                " Miguel Angel Bautista",
                " Zaiwei Zhang",
                " Qi Shan",
                " Qixing Huang"
            ]
        },
        {
            "paperId": "2926",
            "posterId": "246a",
            "title": "It's About Time: Analog Clock Reading in the Wild",
            "authors": [
                "Charig Yang",
                " Weidi Xie",
                " Andrew Zisserman"
            ]
        },
        {
            "paperId": "9312",
            "posterId": "247a",
            "title": "Consistency Driven Sequential Transformers Attention Model for Partially Observable Scenes",
            "authors": [
                "Samrudhdhi B. Rangrej",
                " Chetan L. Srinidhi",
                " James J. Clark"
            ]
        },
        {
            "paperId": "9923",
            "posterId": "248a",
            "title": "SmartAdapt: Multi-Branch Object Detection Framework for Videos on Mobiles",
            "authors": [
                "Ran Xu",
                " Fangzhou Mu",
                " Jayoung Lee",
                " Preeti Mukherjee",
                " Somali Chaterji",
                " Saurabh Bagchi",
                " Yin Li"
            ]
        },
        {
            "paperId": "9662",
            "posterId": "249a",
            "title": "Generating 3D Bio-Printable Patches Using Wound Segmentation and Reconstruction To Treat Diabetic Foot Ulcers",
            "authors": [
                "Han Joo Chae",
                " Seunghwan Lee",
                " Hyewon Son",
                " Seungyeob Han",
                " Taebin Lim"
            ]
        },
        {
            "paperId": "9541",
            "posterId": "250a",
            "title": "Investigating the Impact of Multi-LiDAR Placement on Object Detection for Autonomous Driving",
            "authors": [
                "Hanjiang Hu",
                " Zuxin Liu",
                " Sharad Chitlangia",
                " Akhil Agnihotri",
                " Ding Zhao"
            ]
        }
    ],
    "Video Analysis & Understanding": [
        {
            "paperId": "1811",
            "posterId": "46b",
            "title": "UnweaveNet: Unweaving Activity Stories",
            "authors": [
                "Will Price",
                " Carl Vondrick",
                " Dima Damen"
            ]
        },
        {
            "paperId": "7769",
            "posterId": "47b",
            "title": "Weakly-Supervised Online Action Segmentation in Multi-View Instructional Videos",
            "authors": [
                "Reza Ghoddoosian",
                " Isht Dwivedi",
                " Nakul Agarwal",
                " Chiho Choi",
                " Behzad Dariush"
            ]
        },
        {
            "paperId": "1319",
            "posterId": "48b",
            "title": "Audio-Adaptive Activity Recognition Across Video Domains",
            "authors": [
                "Yunhua Zhang",
                " Hazel Doughty",
                " Ling Shao",
                " Cees G. M. Snoek"
            ]
        },
        {
            "paperId": "6385",
            "posterId": "49b",
            "title": "Frame-Wise Action Representations for Long Videos via Sequence Contrastive Learning",
            "authors": [
                "Minghao Chen",
                " Fangyun Wei",
                " Chong Li",
                " Deng Cai"
            ]
        },
        {
            "paperId": "9349",
            "posterId": "50b",
            "title": "Image Based Reconstruction of Liquids From 2D Surface Detections",
            "authors": [
                "Florian Richter",
                " Ryan K. Orosco",
                " Michael C. Yip"
            ]
        },
        {
            "paperId": "1579",
            "posterId": "51b",
            "title": "Learning From Untrimmed Videos: Self-Supervised Video Representation Learning With Hierarchical Consistency",
            "authors": [
                "Zhiwu Qing",
                " Shiwei Zhang",
                " Ziyuan Huang",
                " Yi Xu",
                " Xiang Wang",
                " Mingqian Tang",
                " Changxin Gao",
                " Rong Jin",
                " Nong Sang"
            ]
        },
        {
            "paperId": "6891",
            "posterId": "52b",
            "title": "How Do You Do It? Fine-Grained Action Understanding With Pseudo-Adverbs",
            "authors": [
                "Hazel Doughty",
                " Cees G. M. Snoek"
            ]
        },
        {
            "paperId": "2102",
            "posterId": "53b",
            "title": "Programmatic Concept Learning for Human Motion Description and Synthesis",
            "authors": [
                "Sumith Kulal",
                " Jiayuan Mao",
                " Alex Aiken",
                " Jiajun Wu"
            ]
        },
        {
            "paperId": "4326",
            "posterId": "54b",
            "title": "Learning To Recognize Procedural Activities With Distant Supervision",
            "authors": [
                "Xudong Lin",
                " Fabio Petroni",
                " Gedas Bertasius",
                " Marcus Rohrbach",
                " Shih-Fu Chang",
                " Lorenzo Torresani"
            ]
        },
        {
            "paperId": "6761",
            "posterId": "55b",
            "title": "Implicit Motion Handling for Video Camouflaged Object Detection",
            "authors": [
                "Xuelian Cheng",
                " Huan Xiong",
                " Deng-Ping Fan",
                " Yiran Zhong",
                " Mehrtash Harandi",
                " Tom Drummond",
                " Zongyuan Ge"
            ]
        },
        {
            "paperId": "11553",
            "posterId": "56b",
            "title": "Dynamic Scene Graph Generation via Anticipatory Pre-Training",
            "authors": [
                "Yiming Li",
                " Xiaoshan Yang",
                " Changsheng Xu"
            ]
        },
        {
            "paperId": "1845",
            "posterId": "57b",
            "title": "Learning To Refactor Action and Co-Occurrence Features for Temporal Action Localization",
            "authors": [
                "Kun Xia",
                " Le Wang",
                " Sanping Zhou",
                " Nanning Zheng",
                " Wei Tang"
            ]
        },
        {
            "paperId": "3930",
            "posterId": "58b",
            "title": "OCSampler: Compressing Videos to One Clip With Single-Step Sampling",
            "authors": [
                "Jintao Lin",
                " Haodong Duan",
                " Kai Chen",
                " Dahua Lin",
                " Limin Wang"
            ]
        },
        {
            "paperId": "5670",
            "posterId": "59b",
            "title": "A Hybrid Egocentric Activity Anticipation Framework via Memory-Augmented Recurrent and One-Shot Representation Forecasting",
            "authors": [
                "Tianshan Liu",
                " Kin-Man Lam"
            ]
        },
        {
            "paperId": "3981",
            "posterId": "60b",
            "title": "TubeFormer-DeepLab: Video Mask Transformer",
            "authors": [
                "Dahun Kim",
                " Jun Xie",
                " Huiyu Wang",
                " Siyuan Qiao",
                " Qihang Yu",
                " Hong-Seok Kim",
                " Hartwig Adam",
                " In So Kweon",
                " Liang-Chieh Chen"
            ]
        },
        {
            "paperId": "2673",
            "posterId": "61b",
            "title": "ASM-Loc: Action-Aware Segment Modeling for Weakly-Supervised Temporal Action Localization",
            "authors": [
                "Bo He",
                " Xitong Yang",
                " Le Kang",
                " Zhiyu Cheng",
                " Xin Zhou",
                " Abhinav Shrivastava"
            ]
        },
        {
            "paperId": "2928",
            "posterId": "62b",
            "title": "GASP, a Generalized Framework for Agglomerative Clustering of Signed Graphs and Its Application to Instance Segmentation",
            "authors": [
                "Zheyun Qin",
                " Xiankai Lu",
                " Xiushan Nie",
                " Yilong Yin",
                " Jianbing Shen"
            ]
        },
        {
            "paperId": "8639",
            "posterId": "63b",
            "title": "STRPM: A Spatiotemporal Residual Predictive Model for High-Resolution Video Prediction",
            "authors": [
                "Zheng Chang",
                " Xinfeng Zhang",
                " Shanshe Wang",
                " Siwei Ma",
                " Wen Gao"
            ]
        },
        {
            "paperId": "3656",
            "posterId": "64b",
            "title": "Look for the Change: Learning Object States and State-Modifying Actions From Untrimmed Web Videos",
            "authors": [
                "Tomáš Souček",
                " Jean-Baptiste Alayrac",
                " Antoine Miech",
                " Ivan Laptev",
                " Josef Sivic"
            ]
        },
        {
            "paperId": "5386",
            "posterId": "65b",
            "title": "End-to-End Compressed Video Representation Learning for Generic Event Boundary Detection",
            "authors": [
                "Congcong Li",
                " Xinyao Wang",
                " Longyin Wen",
                " Dexiang Hong",
                " Tiejian Luo",
                " Libo Zhang"
            ]
        },
        {
            "paperId": "5430",
            "posterId": "66b",
            "title": "Contextualized Spatio-Temporal Contrastive Learning With Self-Supervision",
            "authors": [
                "Liangzhe Yuan",
                " Rui Qian",
                " Yin Cui",
                " Boqing Gong",
                " Florian Schroff",
                " Ming-Hsuan Yang",
                " Hartwig Adam",
                " Ting Liu"
            ]
        },
        {
            "paperId": "2018",
            "posterId": "67b",
            "title": "Deep Anomaly Discovery From Unlabeled Videos via Normality Advantage and Self-Paced Refinement",
            "authors": [
                "Guang Yu",
                " Siqi Wang",
                " Zhiping Cai",
                " Xinwang Liu",
                " Chuanfu Xu",
                " Chengkun Wu"
            ]
        },
        {
            "paperId": "6082",
            "posterId": "68b",
            "title": "A Deeper Dive Into What Deep Spatiotemporal Networks Encode: Quantifying Static vs. Dynamic Information",
            "authors": [
                "Matthew Kowal",
                " Mennatullah Siam",
                " Md Amirul Islam",
                " Neil D. B. Bruce",
                " Richard P. Wildes",
                " Konstantinos G. Derpanis"
            ]
        },
        {
            "paperId": "8138",
            "posterId": "69b",
            "title": "Long-Short Temporal Contrastive Learning of Video Transformers",
            "authors": [
                "Jue Wang",
                " Gedas Bertasius",
                " Du Tran",
                " Lorenzo Torresani"
            ]
        },
        {
            "paperId": "4525",
            "posterId": "70b",
            "title": "Scene Consistency Representation Learning for Video Scene Segmentation",
            "authors": [
                "Haoqian Wu",
                " Keyu Chen",
                " Yanan Luo",
                " Ruizhi Qiao",
                " Bo Ren",
                " Haozhe Liu",
                " Weicheng Xie",
                " Linlin Shen"
            ]
        },
        {
            "paperId": "1024",
            "posterId": "71b",
            "title": "Unsupervised Pre-Training for Temporal Action Localization Tasks",
            "authors": [
                "Can Zhang",
                " Tianyu Yang",
                " Junwu Weng",
                " Meng Cao",
                " Jue Wang",
                " Yuexian Zou"
            ]
        },
        {
            "paperId": "7000",
            "posterId": "72b",
            "title": "Contrastive Learning for Unsupervised Video Highlight Detection",
            "authors": [
                "Taivanbat Badamdorj",
                " Mrigank Rochan",
                " Yang Wang",
                " Li Cheng"
            ]
        },
        {
            "paperId": "8133",
            "posterId": "73b",
            "title": "Deformable Video Transformer",
            "authors": [
                "Jue Wang",
                " Lorenzo Torresani"
            ]
        },
        {
            "paperId": "8415",
            "posterId": "74b",
            "title": "Recurring the Transformer for Video Action Recognition",
            "authors": [
                "Jiewen Yang",
                " Xingbo Dong",
                " Liujun Liu",
                " Chao Zhang",
                " Jiajun Shen",
                " Dahai Yu"
            ]
        }
    ],
    "Image & Video Synthesis and Generation": [
        {
            "paperId": "5438",
            "posterId": "213a",
            "title": "Text to Image Generation With Semantic-Spatial Aware GAN",
            "authors": [
                "Wentong Liao",
                " Kai Hu",
                " Michael Ying Yang",
                " Bodo Rosenhahn"
            ]
        },
        {
            "paperId": "107",
            "posterId": "214a",
            "title": "StyleT2I: Toward Compositional and High-Fidelity Text-to-Image Synthesis",
            "authors": [
                "Zhiheng Li",
                " Martin Renqiang Min",
                " Kai Li",
                " Chenliang Xu"
            ]
        },
        {
            "paperId": "5345",
            "posterId": "215a",
            "title": "Blended Diffusion for Text-Driven Editing of Natural Images",
            "authors": [
                "Omri Avrahami",
                " Dani Lischinski",
                " Ohad Fried"
            ]
        },
        {
            "paperId": "5128",
            "posterId": "216a",
            "title": "Make It Move: Controllable Image-to-Video Generation With Text Descriptions",
            "authors": [
                "Yaosi Hu",
                " Chong Luo",
                " Zhenzhong Chen"
            ]
        },
        {
            "paperId": "5317",
            "posterId": "217a",
            "title": "Predict, Prevent, and Evaluate: Disentangled Text-Driven Image Manipulation Empowered by Pre-Trained Vision-Language Model",
            "authors": [
                "Zipeng Xu",
                " Tianwei Lin",
                " Hao Tang",
                " Fu Li",
                " Dongliang He",
                " Nicu Sebe",
                " Radu Timofte",
                " Luc Van Gool",
                " Errui Ding"
            ]
        },
        {
            "paperId": "10144",
            "posterId": "218a",
            "title": "A Style-Aware Discriminator for Controllable Image Translation",
            "authors": [
                "Kunhee Kim",
                " Sanghun Park",
                " Eunyeong Jeon",
                " Taehun Kim",
                " Daijin Kim"
            ]
        },
        {
            "paperId": "8904",
            "posterId": "219a",
            "title": "Alleviating Semantics Distortion in Unsupervised Low-Level Image-to-Image Translation via Structure Consistency Constraint",
            "authors": [
                "Jiaxian Guo",
                " Jiachen Li",
                " Huan Fu",
                " Mingming Gong",
                " Kun Zhang",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "10441",
            "posterId": "220a",
            "title": "Exploring Patch-Wise Semantic Relation for Contrastive Learning in Image-to-Image Translation Tasks",
            "authors": [
                "Chanyong Jung",
                " Gihyun Kwon",
                " Jong Chul Ye"
            ]
        },
        {
            "paperId": "8356",
            "posterId": "221a",
            "title": "FlexIT: Towards Flexible Semantic Image Translation",
            "authors": [
                "Guillaume Couairon",
                " Asya Grechka",
                " Jakob Verbeek",
                " Holger Schwenk",
                " Matthieu Cord"
            ]
        },
        {
            "paperId": "4022",
            "posterId": "222a",
            "title": "Modulated Contrast for Versatile Image Synthesis",
            "authors": [
                "Fangneng Zhan",
                " Jiahui Zhang",
                " Yingchen Yu",
                " Rongliang Wu",
                " Shijian Lu"
            ]
        },
        {
            "paperId": "8146",
            "posterId": "223a",
            "title": "QS-Attn: Query-Selected Attention for Contrastive Learning in I2I Translation",
            "authors": [
                "Xueqi Hu",
                " Xinyue Zhou",
                " Qiusheng Huang",
                " Zhengyi Shi",
                " Li Sun",
                " Qingli Li"
            ]
        },
        {
            "paperId": "9818",
            "posterId": "224a",
            "title": "Self-Supervised Dense Consistency Regularization for Image-to-Image Translation",
            "authors": [
                "Minsu Ko",
                " Eunju Cha",
                " Sungjoo Suh",
                " Huijin Lee",
                " Jae-Joon Han",
                " Jinwoo Shin",
                " Bohyung Han"
            ]
        },
        {
            "paperId": "155",
            "posterId": "225a",
            "title": "Maximum Spatial Perturbation Consistency for Unpaired Image-to-Image Translation",
            "authors": [
                "Yanwu Xu",
                " Shaoan Xie",
                " Wenhao Wu",
                " Kun Zhang",
                " Mingming Gong",
                " Kayhan Batmanghelich"
            ]
        },
        {
            "paperId": "2538",
            "posterId": "226a",
            "title": "InstaFormer: Instance-Aware Image-to-Image Translation With Transformer",
            "authors": [
                "Soohyun Kim",
                " Jongbeom Baek",
                " Jihye Park",
                " Gyeongnyeon Kim",
                " Seungryong Kim"
            ]
        },
        {
            "paperId": "648",
            "posterId": "227a",
            "title": "Unsupervised Image-to-Image Translation With Generative Prior",
            "authors": [
                "Shuai Yang",
                " Liming Jiang",
                " Ziwei Liu",
                " Chen Change Loy"
            ]
        },
        {
            "paperId": "133",
            "posterId": "228a",
            "title": "StylizedNeRF: Consistent 3D Scene Stylization As Stylized NeRF via 2D-3D Mutual Learning",
            "authors": [
                "Yi-Hua Huang",
                " Yue He",
                " Yu-Jie Yuan",
                " Yu-Kun Lai",
                " Lin Gao"
            ]
        },
        {
            "paperId": "30",
            "posterId": "229a",
            "title": "NeRF-Editing: Geometry Editing of Neural Radiance Fields",
            "authors": [
                "Yu-Jie Yuan",
                " Yang-Tian Sun",
                " Yu-Kun Lai",
                " Yuewen Ma",
                " Rongfei Jia",
                " Lin Gao"
            ]
        },
        {
            "paperId": "8276",
            "posterId": "230a",
            "title": "GeoNeRF: Generalizing NeRF With Geometry Priors",
            "authors": [
                "Mohammad Mahdi Johari",
                " Yann Lepoittevin",
                " François Fleuret"
            ]
        },
        {
            "paperId": "5276",
            "posterId": "231a",
            "title": "Ray Priors Through Reprojection: Improving Neural Radiance Fields for Novel View Extrapolation",
            "authors": [
                "Jian Zhang",
                " Yuanqing Zhang",
                " Huan Fu",
                " Xiaowei Zhou",
                " Bowen Cai",
                " Jinchi Huang",
                " Rongfei Jia",
                " Binqiang Zhao",
                " Xing Tang"
            ]
        },
        {
            "paperId": "10588",
            "posterId": "232a",
            "title": "AR-NeRF: Unsupervised Learning of Depth and Defocus Effects From Natural Images With Aperture Rendering Neural Radiance Fields",
            "authors": [
                "Takuhiro Kaneko"
            ]
        },
        {
            "paperId": "5174",
            "posterId": "233a",
            "title": "HDR-NeRF: High Dynamic Range Neural Radiance Fields",
            "authors": [
                "Xin Huang",
                " Qi Zhang",
                " Ying Feng",
                " Hongdong Li",
                " Xuan Wang",
                " Qing Wang"
            ]
        },
        {
            "paperId": "3703",
            "posterId": "234a",
            "title": "NeRFReN: Neural Radiance Fields With Reflections",
            "authors": [
                "Yuan-Chen Guo",
                " Di Kang",
                " Linchao Bao",
                " Yu He",
                " Song-Hai Zhang"
            ]
        },
        {
            "paperId": "4368",
            "posterId": "235a",
            "title": "Neural Point Light Fields",
            "authors": [
                "Julian Ost",
                " Issam Laradji",
                " Alejandro Newell",
                " Yuval Bahat",
                " Felix Heide"
            ]
        },
        {
            "paperId": "697",
            "posterId": "236a",
            "title": "3D-Aware Image Synthesis via Learning Structural and Textural Representations",
            "authors": [
                "Yinghao Xu",
                " Sida Peng",
                " Ceyuan Yang",
                " Yujun Shen",
                " Bolei Zhou"
            ]
        },
        {
            "paperId": "6895",
            "posterId": "237a",
            "title": "GIRAFFE HD: A High-Resolution 3D-Aware Generative Model",
            "authors": [
                "Yang Xue",
                " Yuheng Li",
                " Krishna Kumar Singh",
                " Yong Jae Lee"
            ]
        },
        {
            "paperId": "1474",
            "posterId": "238a",
            "title": "Multi-View Consistent Generative Adversarial Networks for 3D-Aware Image Synthesis",
            "authors": [
                "Xuanmeng Zhang",
                " Zhedong Zheng",
                " Daiheng Gao",
                " Bang Zhang",
                " Pan Pan",
                " Yi Yang"
            ]
        },
        {
            "paperId": "5736",
            "posterId": "239a",
            "title": "Bi-Level Doubly Variational Learning for Energy-Based Latent Variable Models",
            "authors": [
                "Ge Kan",
                " Jinhu Lü",
                " Tian Wang",
                " Baochang Zhang",
                " Aichun Zhu",
                " Lei Huang",
                " Guodong Guo",
                " Hichem Snoussi"
            ]
        },
        {
            "paperId": "5811",
            "posterId": "240a",
            "title": "High-Resolution Image Harmonization via Collaborative Dual Transformations",
            "authors": [
                "Wenyan Cong",
                " Xinhao Tao",
                " Li Niu",
                " Jing Liang",
                " Xuesong Gao",
                " Qihao Sun",
                " Liqing Zhang"
            ]
        },
        {
            "paperId": "10156",
            "posterId": "241a",
            "title": "Brain-Supervised Image Editing",
            "authors": [
                "Keith M. Davis III",
                " Carlos de la Torre-Ortiz",
                " Tuukka Ruotsalo"
            ]
        }
    ],
    "Face & Gestures": [
        {
            "paperId": "4047",
            "posterId": "142b",
            "title": "HP-Capsule: Unsupervised Face Part Discovery by Hierarchical Parsing Capsule Network",
            "authors": [
                "Chang Yu",
                " Xiangyu Zhu",
                " Xiaomei Zhang",
                " Zidu Wang",
                " Zhaoxiang Zhang",
                " Zhen Lei"
            ]
        },
        {
            "paperId": "6529",
            "posterId": "143b",
            "title": "Killing Two Birds With One Stone: Efficient and Robust Training of Face Recognition CNNs by Partial FC",
            "authors": [
                "Xiang An",
                " Jiankang Deng",
                " Jia Guo",
                " Ziyong Feng",
                " XuHan Zhu",
                " Jing Yang",
                " Tongliang Liu"
            ]
        },
        {
            "paperId": "8566",
            "posterId": "144b",
            "title": "Sparse Local Patch Transformer for Robust Face Alignment and Landmarks Inherent Relation Learning",
            "authors": [
                "Jiahao Xia",
                " Weiwei Qu",
                " Wenjian Huang",
                " Jianguo Zhang",
                " Xi Wang",
                " Min Xu"
            ]
        },
        {
            "paperId": "5578",
            "posterId": "145b",
            "title": "Enhancing Face Recognition With Self-Supervised 3D Reconstruction",
            "authors": [
                "Mingjie He",
                " Jie Zhang",
                " Shiguang Shan",
                " Xilin Chen"
            ]
        },
        {
            "paperId": "5996",
            "posterId": "146b",
            "title": "Learning To Learn Across Diverse Data Biases in Deep Face Recognition",
            "authors": [
                "Chang Liu",
                " Xiang Yu",
                " Yi-Hsuan Tsai",
                " Masoud Faraki",
                " Ramin Moslemi",
                " Manmohan Chandraker",
                " Yun Fu"
            ]
        },
        {
            "paperId": "7320",
            "posterId": "147b",
            "title": "An Efficient Training Approach for Very Large Scale Face Recognition",
            "authors": [
                "Kai Wang",
                " Shuo Wang",
                " Panpan Zhang",
                " Zhipeng Zhou",
                " Zheng Zhu",
                " Xiaobo Wang",
                " Xiaojiang Peng",
                " Baigui Sun",
                " Hao Li",
                " Yang You"
            ]
        },
        {
            "paperId": "4045",
            "posterId": "148b",
            "title": "MogFace: Towards a Deeper Appreciation on Face Detection",
            "authors": [
                "Yang Liu",
                " Fei Wang",
                " Jiankang Deng",
                " Zhipeng Zhou",
                " Baigui Sun",
                " Hao Li"
            ]
        },
        {
            "paperId": "7382",
            "posterId": "149b",
            "title": "Exploring Frequency Adversarial Attacks for Face Forgery Detection",
            "authors": [
                "Shuai Jia",
                " Chao Ma",
                " Taiping Yao",
                " Bangjie Yin",
                " Shouhong Ding",
                " Xiaokang Yang"
            ]
        },
        {
            "paperId": "7163",
            "posterId": "150b",
            "title": "End-to-End Reconstruction-Classification Learning for Face Forgery Detection",
            "authors": [
                "Junyi Cao",
                " Chao Ma",
                " Taiping Yao",
                " Shen Chen",
                " Shouhong Ding",
                " Xiaokang Yang"
            ]
        },
        {
            "paperId": "3804",
            "posterId": "151b",
            "title": "Domain Generalization via Shuffled Style Assembly for Face Anti-Spoofing",
            "authors": [
                "Zhuo Wang",
                " Zezheng Wang",
                " Zitong Yu",
                " Weihong Deng",
                " Jiahong Li",
                " Tingting Gao",
                " Zhongyuan Wang"
            ]
        },
        {
            "paperId": "9981",
            "posterId": "152b",
            "title": "Privacy-Preserving Online AutoML for Domain-Specific Face Detection",
            "authors": [
                "Chenqian Yan",
                " Yuge Zhang",
                " Quanlu Zhang",
                " Yaming Yang",
                " Xinyang Jiang",
                " Yuqing Yang",
                " Baoyuan Wang"
            ]
        },
        {
            "paperId": "891",
            "posterId": "153b",
            "title": "Simulated Adversarial Testing of Face Recognition Models",
            "authors": [
                "Nataniel Ruiz",
                " Adam Kortylewski",
                " Weichao Qiu",
                " Cihang Xie",
                " Sarah Adel Bargal",
                " Alan Yuille",
                " Stan Sclaroff"
            ]
        },
        {
            "paperId": "5782",
            "posterId": "154b",
            "title": "Decoupled Multi-Task Learning With Cyclical Self-Regulation for Face Parsing",
            "authors": [
                "Qingping Zheng",
                " Jiankang Deng",
                " Zheng Zhu",
                " Ying Li",
                " Stefanos Zafeiriou"
            ]
        },
        {
            "paperId": "2510",
            "posterId": "155b",
            "title": "Towards Semi-Supervised Deep Facial Expression Recognition With an Adaptive Confidence Margin",
            "authors": [
                "Hangyu Li",
                " Nannan Wang",
                " Xi Yang",
                " Xiaoyu Wang",
                " Xinbo Gao"
            ]
        },
        {
            "paperId": "5638",
            "posterId": "156b",
            "title": "Towards Accurate Facial Landmark Detection via Cascaded Transformers",
            "authors": [
                "Hui Li",
                " Zidong Guo",
                " Seon-Min Rhee",
                " Seungju Han",
                " Jae-Joon Han"
            ]
        },
        {
            "paperId": "3038",
            "posterId": "157b",
            "title": "PhysFormer: Facial Video-Based Physiological Measurement With Temporal Difference Transformer",
            "authors": [
                "Zitong Yu",
                " Yuming Shen",
                " Jingang Shi",
                " Hengshuang Zhao",
                " Philip H.S. Torr",
                " Guoying Zhao"
            ]
        },
        {
            "paperId": "5557",
            "posterId": "158b",
            "title": "GazeOnce: Real-Time Multi-Person Gaze Estimation",
            "authors": [
                "Mingfang Zhang",
                " Yunfei Liu",
                " Feng Lu"
            ]
        },
        {
            "paperId": "3783",
            "posterId": "159b",
            "title": "Generalizing Gaze Estimation With Rotation Consistency",
            "authors": [
                "Yiwei Bao",
                " Yunfei Liu",
                " Haofei Wang",
                " Feng Lu"
            ]
        },
        {
            "paperId": "4512",
            "posterId": "160b",
            "title": "Face Relighting With Geometrically Consistent Shadows",
            "authors": [
                "Andrew Hou",
                " Michel Sarkis",
                " Ning Bi",
                " Yiying Tong",
                " Xiaoming Liu"
            ]
        },
        {
            "paperId": "2485",
            "posterId": "161b",
            "title": "HairMapper: Removing Hair From Portraits Using GANs",
            "authors": [
                "Yiqian Wu",
                " Yong-Liang Yang",
                " Xiaogang Jin"
            ]
        },
        {
            "paperId": "5664",
            "posterId": "162b",
            "title": "Learning To Restore 3D Face From In-the-Wild Degraded Images",
            "authors": [
                "Zhenyu Zhang",
                " Yanhao Ge",
                " Ying Tai",
                " Xiaoming Huang",
                " Chengjie Wang",
                " Hao Tang",
                " Dongjin Huang",
                " Zhifeng Xie"
            ]
        }
    ],
    "Document Analysis & Understanding": [
        {
            "paperId": "2898",
            "posterId": "190b",
            "title": "Open-Set Text Recognition via Character-Context Decoupling",
            "authors": [
                "Chang Liu",
                " Chun Yang",
                " Xu-Cheng Yin"
            ]
        },
        {
            "paperId": "3331",
            "posterId": "191b",
            "title": "Neural Collaborative Graph Machines for Table Structure Recognition",
            "authors": [
                "Hao Liu",
                " Xin Li",
                " Bing Liu",
                " Deqiang Jiang",
                " Yinsong Liu",
                " Bo Ren"
            ]
        },
        {
            "paperId": "4051",
            "posterId": "192b",
            "title": "Revisiting Document Image Dewarping by Grid Regularization",
            "authors": [
                "Xiangwei Jiang",
                " Rujiao Long",
                " Nan Xue",
                " Zhibo Yang",
                " Cong Yao",
                " Gui-Song Xia"
            ]
        },
        {
            "paperId": "4161",
            "posterId": "193b",
            "title": "Syntax-Aware Network for Handwritten Mathematical Expression Recognition",
            "authors": [
                "Ye Yuan",
                " Xiao Liu",
                " Wondimu Dikubab",
                " Hui Liu",
                " Zhilong Ji",
                " Zhongqin Wu",
                " Xiang Bai"
            ]
        },
        {
            "paperId": "4743",
            "posterId": "194b",
            "title": "Few Could Be Better Than All: Feature Sampling and Grouping for Scene Text Detection",
            "authors": [
                "Jingqun Tang",
                " Wenqing Zhang",
                " Hongye Liu",
                " MingKun Yang",
                " Bo Jiang",
                " Guanglong Hu",
                " Xiang Bai"
            ]
        },
        {
            "paperId": "5258",
            "posterId": "195b",
            "title": "Fourier Document Restoration for Robust Document Dewarping and Recognition",
            "authors": [
                "Chuhui Xue",
                " Zichen Tian",
                " Fangneng Zhan",
                " Shijian Lu",
                " Song Bai"
            ]
        },
        {
            "paperId": "6276",
            "posterId": "196b",
            "title": "XYLayoutLM: Towards Layout-Aware Multimodal Networks for Visually-Rich Document Understanding",
            "authors": [
                "Zhangxuan Gu",
                " Changhua Meng",
                " Ke Wang",
                " Jun Lan",
                " Weiqiang Wang",
                " Ming Gu",
                " Liqing Zhang"
            ]
        },
        {
            "paperId": "7348",
            "posterId": "197b",
            "title": "SwinTextSpotter: Scene Text Spotting via Better Synergy Between Text Detection and Text Recognition",
            "authors": [
                "Mingxin Huang",
                " Yuliang Liu",
                " Zhenghao Peng",
                " Chongyu Liu",
                " Dahua Lin",
                " Shenggao Zhu",
                " Nicholas Yuan",
                " Kai Ding",
                " Lianwen Jin"
            ]
        },
        {
            "paperId": "2703",
            "posterId": "198b",
            "title": "Towards Weakly-Supervised Text Spotting Using a Multi-Task Transformer",
            "authors": [
                "Yair Kittenplon",
                " Inbal Lavi",
                " Sharon Fogel",
                " Yarin Bar",
                " R. Manmatha",
                " Pietro Perona"
            ]
        },
        {
            "paperId": "3686",
            "posterId": "199b",
            "title": "TableFormer: Table Structure Understanding With Transformers",
            "authors": [
                "Ahmed Nassar",
                " Nikolaos Livathinos",
                " Maksym Lysak",
                " Peter Staar"
            ]
        },
        {
            "paperId": "8352",
            "posterId": "200b",
            "title": "Knowledge Mining With Scene Text for Fine-Grained Recognition",
            "authors": [
                "Hao Wang",
                " Junchao Liao",
                " Tianheng Cheng",
                " Zewen Gao",
                " Hao Liu",
                " Bo Ren",
                " Xiang Bai",
                " Wenyu Liu"
            ]
        },
        {
            "paperId": "11454",
            "posterId": "201b",
            "title": "PubTables-1M: Towards Comprehensive Table Extraction From Unstructured Documents",
            "authors": [
                "Brandon Smock",
                " Rohith Pesala",
                " Robin Abraham"
            ]
        }
    ],
    "Vision & Language": [
        {
            "paperId": "2043",
            "posterId": "185a",
            "title": "Towards Implicit Text-Guided 3D Shape Generation",
            "authors": [
                "Zhengzhe Liu",
                " Yi Wang",
                " Xiaojuan Qi",
                " Chi-Wing Fu"
            ]
        },
        {
            "paperId": "9380",
            "posterId": "186a",
            "title": "Towards Language-Free Training for Text-to-Image Generation",
            "authors": [
                "Yufan Zhou",
                " Ruiyi Zhang",
                " Changyou Chen",
                " Chunyuan Li",
                " Chris Tensmeyer",
                " Tong Yu",
                " Jiuxiang Gu",
                " Jinhui Xu",
                " Tong Sun"
            ]
        },
        {
            "paperId": "7612",
            "posterId": "187a",
            "title": "ZeroCap: Zero-Shot Image-to-Text Generation for Visual-Semantic Arithmetic",
            "authors": [
                "Yoad Tewel",
                " Yoav Shalev",
                " Idan Schwartz",
                " Lior Wolf"
            ]
        },
        {
            "paperId": "4952",
            "posterId": "188a",
            "title": "EMScore: Evaluating Video Captioning via Coarse-Grained and Fine-Grained Embedding Matching",
            "authors": [
                "Yaya Shi",
                " Xu Yang",
                " Haiyang Xu",
                " Chunfeng Yuan",
                " Bing Li",
                " Weiming Hu",
                " Zheng-Jun Zha"
            ]
        },
        {
            "paperId": "7374",
            "posterId": "189a",
            "title": "Hierarchical Modular Network for Video Captioning",
            "authors": [
                "Hanhua Ye",
                " Guorong Li",
                " Yuankai Qi",
                " Shuhui Wang",
                " Qingming Huang",
                " Ming-Hsuan Yang"
            ]
        },
        {
            "paperId": "3770",
            "posterId": "190a",
            "title": "SwinBERT: End-to-End Transformers With Sparse Attention for Video Captioning",
            "authors": [
                "Kevin Lin",
                " Linjie Li",
                " Chung-Ching Lin",
                " Faisal Ahmed",
                " Zhe Gan",
                " Zicheng Liu",
                " Yumao Lu",
                " Lijuan Wang"
            ]
        },
        {
            "paperId": "3222",
            "posterId": "191a",
            "title": "End-to-End Generative Pretraining for Multimodal Video Captioning",
            "authors": [
                "Paul Hongsuck Seo",
                " Arsha Nagrani",
                " Anurag Arnab",
                " Cordelia Schmid"
            ]
        },
        {
            "paperId": "4855",
            "posterId": "192a",
            "title": "Beyond a Pre-Trained Object Detector: Cross-Modal Textual and Visual Context for Image Captioning",
            "authors": [
                "Chia-Wen Kuo",
                " Zsolt Kira"
            ]
        },
        {
            "paperId": "8115",
            "posterId": "193a",
            "title": "Scaling Up Vision-Language Pre-Training for Image Captioning",
            "authors": [
                "Xiaowei Hu",
                " Zhe Gan",
                " Jianfeng Wang",
                " Zhengyuan Yang",
                " Zicheng Liu",
                " Yumao Lu",
                " Lijuan Wang"
            ]
        },
        {
            "paperId": "9270",
            "posterId": "194a",
            "title": "Comprehending and Ordering Semantics for Image Captioning",
            "authors": [
                "Yehao Li",
                " Yingwei Pan",
                " Ting Yao",
                " Tao Mei"
            ]
        },
        {
            "paperId": "11498",
            "posterId": "195a",
            "title": "NOC-REK: Novel Object Captioning With Retrieved Vocabulary From External Knowledge",
            "authors": [
                "Duc Minh Vo",
                " Hong Chen",
                " Akihiro Sugimoto",
                " Hideki Nakayama"
            ]
        },
        {
            "paperId": "814",
            "posterId": "196a",
            "title": "Injecting Semantic Concepts Into End-to-End Image Captioning",
            "authors": [
                "Zhiyuan Fang",
                " Jianfeng Wang",
                " Xiaowei Hu",
                " Lin Liang",
                " Zhe Gan",
                " Lijuan Wang",
                " Yezhou Yang",
                " Zicheng Liu"
            ]
        },
        {
            "paperId": "1613",
            "posterId": "197a",
            "title": "DIFNet: Boosting Visual Information Flow for Image Captioning",
            "authors": [
                "Mingrui Wu",
                " Xuying Zhang",
                " Xiaoshuai Sun",
                " Yiyi Zhou",
                " Chao Chen",
                " Jiaxin Gu",
                " Xing Sun",
                " Rongrong Ji"
            ]
        },
        {
            "paperId": "8224",
            "posterId": "198a",
            "title": "VisualGPT: Data-Efficient Adaptation of Pretrained Language Models for Image Captioning",
            "authors": [
                "Jun Chen",
                " Han Guo",
                " Kai Yi",
                " Boyang Li",
                " Mohamed Elhoseiny"
            ]
        },
        {
            "paperId": "7848",
            "posterId": "199a",
            "title": "Show, Deconfound and Tell: Image Captioning With Causal Inference",
            "authors": [
                "Bing Liu",
                " Dong Wang",
                " Xu Yang",
                " Yong Zhou",
                " Rui Yao",
                " Zhiwen Shao",
                " Jiaqi Zhao"
            ]
        },
        {
            "paperId": "9257",
            "posterId": "200a",
            "title": "EI-CLIP: Entity-Aware Interventional Contrastive Learning for E-Commerce Cross-Modal Retrieval",
            "authors": [
                "Haoyu Ma",
                " Handong Zhao",
                " Zhe Lin",
                " Ajinkya Kale",
                " Zhangyang Wang",
                " Tong Yu",
                " Jiuxiang Gu",
                " Sunav Choudhary",
                " Xiaohui Xie"
            ]
        },
        {
            "paperId": "11667",
            "posterId": "201a",
            "title": "CLIPstyler: Image Style Transfer With a Single Text Condition",
            "authors": [
                "Gihyun Kwon",
                " Jong Chul Ye"
            ]
        },
        {
            "paperId": "4042",
            "posterId": "202a",
            "title": "HairCLIP: Design Your Hair by Text and Reference Image",
            "authors": [
                "Tianyi Wei",
                " Dongdong Chen",
                " Wenbo Zhou",
                " Jing Liao",
                " Zhentao Tan",
                " Lu Yuan",
                " Weiming Zhang",
                " Nenghai Yu"
            ]
        },
        {
            "paperId": "1965",
            "posterId": "203a",
            "title": "DenseCLIP: Language-Guided Dense Prediction With Context-Aware Prompting",
            "authors": [
                "Yongming Rao",
                " Wenliang Zhao",
                " Guangyi Chen",
                " Yansong Tang",
                " Zheng Zhu",
                " Guan Huang",
                " Jie Zhou",
                " Jiwen Lu"
            ]
        },
        {
            "paperId": "11622",
            "posterId": "204a",
            "title": "On Guiding Visual Attention With Language Specification",
            "authors": [
                "Suzanne Petryk",
                " Lisa Dunlap",
                " Keyan Nasseri",
                " Joseph Gonzalez",
                " Trevor Darrell",
                " Anna Rohrbach"
            ]
        },
        {
            "paperId": "9610",
            "posterId": "205a",
            "title": "UTC: A Unified Transformer With Inter-Task Contrastive Learning for Visual Dialog",
            "authors": [
                "Cheng Chen",
                " Zhenshan Tan",
                " Qingrong Cheng",
                " Xin Jiang",
                " Qun Liu",
                " Yudong Zhu",
                " Xiaodong Gu"
            ]
        },
        {
            "paperId": "10953",
            "posterId": "206a",
            "title": "Text-to-Image Synthesis Based on Object-Guided Joint-Decoding Transformer",
            "authors": [
                "Fuxiang Wu",
                " Liu Liu",
                " Fusheng Hao",
                " Fengxiang He",
                " Jun Cheng"
            ]
        },
        {
            "paperId": "10338",
            "posterId": "207a",
            "title": "LiT: Zero-Shot Transfer With Locked-Image Text Tuning",
            "authors": [
                "Xiaohua Zhai",
                " Xiao Wang",
                " Basil Mustafa",
                " Andreas Steiner",
                " Daniel Keysers",
                " Alexander Kolesnikov",
                " Lucas Beyer"
            ]
        },
        {
            "paperId": "851",
            "posterId": "208a",
            "title": "GroupViT: Semantic Segmentation Emerges From Text Supervision",
            "authors": [
                "Jiarui Xu",
                " Shalini De Mello",
                " Sifei Liu",
                " Wonmin Byeon",
                " Thomas Breuel",
                " Jan Kautz",
                " Xiaolong Wang"
            ]
        },
        {
            "paperId": "1404",
            "posterId": "209a",
            "title": "ReSTR: Convolution-Free Referring Image Segmentation Using Transformers",
            "authors": [
                "Namyup Kim",
                " Dongwon Kim",
                " Cuiling Lan",
                " Wenjun Zeng",
                " Suha Kwak"
            ]
        },
        {
            "paperId": "1565",
            "posterId": "210a",
            "title": "LAVT: Language-Aware Vision Transformer for Referring Image Segmentation",
            "authors": [
                "Zhao Yang",
                " Jiaqi Wang",
                " Yansong Tang",
                " Kai Chen",
                " Hengshuang Zhao",
                " Philip H.S. Torr"
            ]
        },
        {
            "paperId": "7782",
            "posterId": "211a",
            "title": "An Empirical Study of Training End-to-End Vision-and-Language Transformers",
            "authors": [
                "Zi-Yi Dou",
                " Yichong Xu",
                " Zhe Gan",
                " Jianfeng Wang",
                " Shuohang Wang",
                " Lijuan Wang",
                " Chenguang Zhu",
                " Pengchuan Zhang",
                " Lu Yuan",
                " Nanyun Peng",
                " Zicheng Liu",
                " Michael Zeng"
            ]
        },
        {
            "paperId": "7761",
            "posterId": "212a",
            "title": "Are Multimodal Transformers Robust to Missing Modality?",
            "authors": [
                "Mengmeng Ma",
                " Jian Ren",
                " Long Zhao",
                " Davide Testuggine",
                " Xi Peng"
            ]
        }
    ],
    "3D From Multi-View & Sensors": [
        {
            "paperId": "4834",
            "posterId": "232b",
            "title": "NeurMiPs: Neural Mixture of Planar Experts for View Synthesis",
            "authors": [
                "Zhi-Hao Lin",
                " Wei-Chiu Ma",
                " Hao-Yu Hsu",
                " Yu-Chiang Frank Wang",
                " Shenlong Wang"
            ]
        },
        {
            "paperId": "4419",
            "posterId": "233b",
            "title": "FWD: Real-Time Novel View Synthesis With Forward Warping and Depth",
            "authors": [
                "Ang Cao",
                " Chris Rockwell",
                " Justin Johnson"
            ]
        },
        {
            "paperId": "441",
            "posterId": "234b",
            "title": "SOMSI: Spherical Novel View Synthesis With Soft Occlusion Multi-Sphere Images",
            "authors": [
                "Tewodros Habtegebrial",
                " Christiano Gava",
                " Marcel Rogge",
                " Didier Stricker",
                " Varun Jampani"
            ]
        },
        {
            "paperId": "11049",
            "posterId": "235b",
            "title": "Fast, Accurate and Memory-Efficient Partial Permutation Synchronization",
            "authors": [
                "Shaohan Li",
                " Yunpeng Shi",
                " Gilad Lerman"
            ]
        },
        {
            "paperId": "2015",
            "posterId": "236b",
            "title": "Learning To Find Good Models in RANSAC",
            "authors": [
                "Daniel Barath",
                " Luca Cavalli",
                " Marc Pollefeys"
            ]
        },
        {
            "paperId": "9080",
            "posterId": "237b",
            "title": "Optimizing Elimination Templates by Greedy Parameter Search",
            "authors": [
                "Evgeniy Martyushev",
                " Jana Vráblíková",
                " Tomas Pajdla"
            ]
        },
        {
            "paperId": "11523",
            "posterId": "238b",
            "title": "GPU-Based Homotopy Continuation for Minimal Problems in Computer Vision",
            "authors": [
                "Chiang-Heng Chien",
                " Hongyi Fan",
                " Ahmad Abdelfattah",
                " Elias Tsigaridas",
                " Stanimire Tomov",
                " Benjamin Kimia"
            ]
        },
        {
            "paperId": "2580",
            "posterId": "239b",
            "title": "HARA: A Hierarchical Approach for Robust Rotation Averaging",
            "authors": [
                "Seong Hun Lee",
                " Javier Civera"
            ]
        },
        {
            "paperId": "4166",
            "posterId": "240b",
            "title": "RAGO: Recurrent Graph Optimizer for Multiple Rotation Averaging",
            "authors": [
                "Heng Li",
                " Zhaopeng Cui",
                " Shuaicheng Liu",
                " Ping Tan"
            ]
        },
        {
            "paperId": "11316",
            "posterId": "241b",
            "title": "A Unified Model for Line Projections in Catadioptric Cameras With Rotationally Symmetric Mirrors",
            "authors": [
                "Pedro Miraldo",
                " José Pedro Iglesias"
            ]
        },
        {
            "paperId": "4211",
            "posterId": "242b",
            "title": "ELSR: Efficient Line Segment Reconstruction With Planes and Points Guidance",
            "authors": [
                "Dong Wei",
                " Yi Wan",
                " Yongjun Zhang",
                " Xinyi Liu",
                " Bin Zhang",
                " Xiqi Wang"
            ]
        },
        {
            "paperId": "6651",
            "posterId": "243b",
            "title": "Self-Supervised Neural Articulated Shape and Appearance Models",
            "authors": [
                "Fangyin Wei",
                " Rohan Chabra",
                " Lingni Ma",
                " Christoph Lassner",
                " Michael Zollhöfer",
                " Szymon Rusinkiewicz",
                " Chris Sweeney",
                " Richard Newcombe",
                " Mira Slavcheva"
            ]
        },
        {
            "paperId": "6645",
            "posterId": "244b",
            "title": "Virtual Elastic Objects",
            "authors": [
                "Hsiao-yu Chen",
                " Edith Tretschk",
                " Tuur Stuyck",
                " Petr Kadlecek",
                " Ladislav Kavan",
                " Etienne Vouga",
                " Christoph Lassner"
            ]
        },
        {
            "paperId": "3282",
            "posterId": "245b",
            "title": "Decoupling Makes Weakly Supervised Local Feature Better",
            "authors": [
                "Kunhong Li",
                " Longguang Wang",
                " Li Liu",
                " Qing Ran",
                " Kai Xu",
                " Yulan Guo"
            ]
        },
        {
            "paperId": "1667",
            "posterId": "246b",
            "title": "JoinABLe: Learning Bottom-Up Assembly of Parametric CAD Joints",
            "authors": [
                "Karl D.D. Willis",
                " Pradeep Kumar Jayaraman",
                " Hang Chu",
                " Yunsheng Tian",
                " Yifei Li",
                " Daniele Grandi",
                " Aditya Sanghi",
                " Linh Tran",
                " Joseph G. Lambourne",
                " Armando Solar-Lezama",
                " Wojciech Matusik"
            ]
        },
        {
            "paperId": "640",
            "posterId": "247b",
            "title": "ImplicitAtlas: Learning Deformable Shape Templates in Medical Imaging",
            "authors": [
                "Jiancheng Yang",
                " Udaranga Wickramasinghe",
                " Bingbing Ni",
                " Pascal Fua"
            ]
        },
        {
            "paperId": "9217",
            "posterId": "248b",
            "title": "DoubleField: Bridging the Neural Surface and Radiance Fields for High-Fidelity Human Reconstruction and Rendering",
            "authors": [
                "Ruizhi Shao",
                " Hongwen Zhang",
                " He Zhang",
                " Mingjia Chen",
                " Yan-Pei Cao",
                " Tao Yu",
                " Yebin Liu"
            ]
        },
        {
            "paperId": "8789",
            "posterId": "249b",
            "title": "Surface-Aligned Neural Radiance Fields for Controllable 3D Human Synthesis",
            "authors": [
                "Tianhan Xu",
                " Yasuhiro Fujita",
                " Eiichi Matsumoto"
            ]
        },
        {
            "paperId": "1269",
            "posterId": "250b",
            "title": "Structured Local Radiance Fields for Human Avatar Modeling",
            "authors": [
                "Zerong Zheng",
                " Han Huang",
                " Tao Yu",
                " Hongwen Zhang",
                " Yandong Guo",
                " Yebin Liu"
            ]
        },
        {
            "paperId": "4685",
            "posterId": "251b",
            "title": "High-Fidelity Human Avatars From a Single RGB Camera",
            "authors": [
                "Hao Zhao",
                " Jinsong Zhang",
                " Yu-Kun Lai",
                " Zerong Zheng",
                " Yingdi Xie",
                " Yebin Liu",
                " Kun Li"
            ]
        },
        {
            "paperId": "5827",
            "posterId": "252b",
            "title": "Forecasting Characteristic 3D Poses of Human Actions",
            "authors": [
                "Christian Diller",
                " Thomas Funkhouser",
                " Angela Dai"
            ]
        },
        {
            "paperId": "817",
            "posterId": "253b",
            "title": "Virtual Correspondence: Humans as a Cue for Extreme-View Geometry",
            "authors": [
                "Wei-Chiu Ma",
                " Anqi Joyce Yang",
                " Shenlong Wang",
                " Raquel Urtasun",
                " Antonio Torralba"
            ]
        },
        {
            "paperId": "869",
            "posterId": "254b",
            "title": "BEHAVE: Dataset and Method for Tracking Human Object Interactions",
            "authors": [
                "Bharat Lal Bhatnagar",
                " Xianghui Xie",
                " Ilya A. Petrov",
                " Cristian Sminchisescu",
                " Christian Theobalt",
                " Gerard Pons-Moll"
            ]
        },
        {
            "paperId": "3549",
            "posterId": "255b",
            "title": "Primitive3D: 3D Object Dataset Synthesis From Randomly Assembled Primitives",
            "authors": [
                "Xinke Li",
                " Henghui Ding",
                " Zekun Tong",
                " Yuwei Wu",
                " Yeow Meng Chee"
            ]
        },
        {
            "paperId": "8956",
            "posterId": "256b",
            "title": "RGB-Multispectral Matching: Dataset, Learning Methodology, Evaluation",
            "authors": [
                "Fabio Tosi",
                " Pierluigi Zama Ramirez",
                " Matteo Poggi",
                " Samuele Salti",
                " Stefano Mattoccia",
                " Luigi Di Stefano"
            ]
        },
        {
            "paperId": "9005",
            "posterId": "257b",
            "title": "NPBG++: Accelerating Neural Point-Based Graphics",
            "authors": [
                "Ruslan Rakhimov",
                " Andrei-Timotei Ardelean",
                " Victor Lempitsky",
                " Evgeny Burnaev"
            ]
        },
        {
            "paperId": "5409",
            "posterId": "258b",
            "title": "Depth-Guided Sparse Structure-From-Motion for Movies and TV Shows",
            "authors": [
                "Sheng Liu",
                " Xiaohan Nie",
                " Raffay Hamid"
            ]
        },
        {
            "paperId": "875",
            "posterId": "259b",
            "title": "Motion-From-Blur: 3D Shape and Motion Estimation of Motion-Blurred Objects in Videos",
            "authors": [
                "Denys Rozumnyi",
                " Martin R. Oswald",
                " Vittorio Ferrari",
                " Marc Pollefeys"
            ]
        }
    ],
    "Motion & Tracking": [
        {
            "paperId": "8292",
            "posterId": "74b",
            "title": "TransforMatcher: Match-to-Match Attention for Semantic Correspondence",
            "authors": [
                "Seungwook Kim",
                " Juhong Min",
                " Minsu Cho"
            ]
        },
        {
            "paperId": "1610",
            "posterId": "75b",
            "title": "Probabilistic Warp Consistency for Weakly-Supervised Semantic Correspondences",
            "authors": [
                "Prune Truong",
                " Martin Danelljan",
                " Fisher Yu",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "2606",
            "posterId": "76b",
            "title": "Locality-Aware Inter– and Intra-Video Reconstruction for Self-Supervised Correspondence Learning",
            "authors": [
                "Liulei Li",
                " Tianfei Zhou",
                " Wenguan Wang",
                " Lu Yang",
                " Jianwu Li",
                " Yi Yang"
            ]
        },
        {
            "paperId": "6011",
            "posterId": "77b",
            "title": "Transforming Model Prediction for Tracking",
            "authors": [
                "Christoph Mayer",
                " Martin Danelljan",
                " Goutam Bhat",
                " Matthieu Paul",
                " Danda Pani Paudel",
                " Fisher Yu",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "10078",
            "posterId": "78b",
            "title": "Ranking-Based Siamese Visual Tracking",
            "authors": [
                "Feng Tang",
                " Qiang Ling"
            ]
        },
        {
            "paperId": "3860",
            "posterId": "79b",
            "title": "Correlation-Aware Deep Tracking",
            "authors": [
                "Fei Xie",
                " Chunyu Wang",
                " Guangting Wang",
                " Yue Cao",
                " Wankou Yang",
                " Wenjun Zeng"
            ]
        },
        {
            "paperId": "3825",
            "posterId": "80b",
            "title": "Global Tracking via Ensemble of Local Trackers",
            "authors": [
                "Zikun Zhou",
                " Jianqiu Chen",
                " Wenjie Pei",
                " Kaige Mao",
                " Hongpeng Wang",
                " Zhenyu He"
            ]
        },
        {
            "paperId": "909",
            "posterId": "81b",
            "title": "Global Tracking Transformers",
            "authors": [
                "Xingyi Zhou",
                " Tianwei Yin",
                " Vladlen Koltun",
                " Philipp Krähenbühl"
            ]
        },
        {
            "paperId": "1198",
            "posterId": "82b",
            "title": "Unified Transformer Tracker for Object Tracking",
            "authors": [
                "Fan Ma",
                " Mike Zheng Shou",
                " Linchao Zhu",
                " Haoqi Fan",
                " Yilei Xu",
                " Yi Yang",
                " Zhicheng Yan"
            ]
        },
        {
            "paperId": "9651",
            "posterId": "83b",
            "title": "Transformer Tracking With Cyclic Shifting Window Attention",
            "authors": [
                "Zikai Song",
                " Junqing Yu",
                " Yi-Ping Phoebe Chen",
                " Wei Yang"
            ]
        },
        {
            "paperId": "7487",
            "posterId": "84b",
            "title": "Spiking Transformers for Event-Based Single Object Tracking",
            "authors": [
                "Jiqing Zhang",
                " Bo Dong",
                " Haiwei Zhang",
                " Jianchuan Ding",
                " Felix Heide",
                " Baocai Yin",
                " Xin Yang"
            ]
        },
        {
            "paperId": "6379",
            "posterId": "85b",
            "title": "Adiabatic Quantum Computing for Multi Object Tracking",
            "authors": [
                "Jan-Nico Zaech",
                " Alexander Liniger",
                " Martin Danelljan",
                " Dengxin Dai",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "8065",
            "posterId": "86b",
            "title": "HiVT: Hierarchical Vector Transformer for Multi-Agent Motion Prediction",
            "authors": [
                "Zikang Zhou",
                " Luyao Ye",
                " Jianping Wang",
                " Kui Wu",
                " Kejie Lu"
            ]
        },
        {
            "paperId": "2493",
            "posterId": "87b",
            "title": "Towards Discriminative Representation: Multi-View Trajectory Contrastive Learning for Online Multi-Object Tracking",
            "authors": [
                "En Yu",
                " Zhuoling Li",
                " Shoudong Han"
            ]
        },
        {
            "paperId": "9395",
            "posterId": "88b",
            "title": "TrackFormer: Multi-Object Tracking With Transformers",
            "authors": [
                "Tim Meinhardt",
                " Alexander Kirillov",
                " Laura Leal-Taixé",
                " Christoph Feichtenhofer"
            ]
        },
        {
            "paperId": "4294",
            "posterId": "89b",
            "title": "Learning of Global Objective for Network Flow in Multi-Object Tracking",
            "authors": [
                "Shuai Li",
                " Yu Kong",
                " Hamid Rezatofighi"
            ]
        },
        {
            "paperId": "5264",
            "posterId": "90b",
            "title": "LMGP: Lifted Multicut Meets Geometry Projections for Multi-Camera Multi-Object Tracking",
            "authors": [
                "Duy M. H. Nguyen",
                " Roberto Henschel",
                " Bodo Rosenhahn",
                " Daniel Sonntag",
                " Paul Swoboda"
            ]
        },
        {
            "paperId": "3128",
            "posterId": "91b",
            "title": "Multi-Object Tracking Meets Moving UAV",
            "authors": [
                "Shuai Liu",
                " Xin Li",
                " Huchuan Lu",
                " You He"
            ]
        },
        {
            "paperId": "912",
            "posterId": "92b",
            "title": "Visible-Thermal UAV Tracking: A Large-Scale Benchmark and New Baseline",
            "authors": [
                "Pengyu Zhang",
                " Jie Zhao",
                " Dong Wang",
                " Huchuan Lu",
                " Xiang Ruan"
            ]
        },
        {
            "paperId": "2683",
            "posterId": "93b",
            "title": "Unsupervised Domain Adaptation for Nighttime Aerial Tracking",
            "authors": [
                "Junjie Ye",
                " Changhong Fu",
                " Guangze Zheng",
                " Danda Pani Paudel",
                " Guang Chen"
            ]
        },
        {
            "paperId": "6998",
            "posterId": "94b",
            "title": "Learning Optical Flow With Kernel Patch Attention",
            "authors": [
                "Ao Luo",
                " Fan Yang",
                " Xin Li",
                " Shuaicheng Liu"
            ]
        },
        {
            "paperId": "5798",
            "posterId": "95b",
            "title": "Towards Understanding Adversarial Robustness of Optical Flow Networks",
            "authors": [
                "Simon Schrodi",
                " Tonmoy Saikia",
                " Thomas Brox"
            ]
        },
        {
            "paperId": "5641",
            "posterId": "96b",
            "title": "DIP: Deep Inverse Patchmatch for High-Resolution Optical Flow",
            "authors": [
                "Zihua Zheng",
                " Ni Nie",
                " Zhi Ling",
                " Pengfei Xiong",
                " Jiangyu Liu",
                " Hao Wang",
                " Jiankun Li"
            ]
        }
    ],
    "Pose Estimation & Tracking": [
        {
            "paperId": "8367",
            "posterId": "236a",
            "title": "Multi-Person Extreme Motion Prediction",
            "authors": [
                "Wen Guo",
                " Xiaoyu Bie",
                " Xavier Alameda-Pineda",
                " Francesc Moreno-Noguer"
            ]
        },
        {
            "paperId": "51",
            "posterId": "237a",
            "title": "Learning Local-Global Contextual Adaptation for Multi-Person Pose Estimation",
            "authors": [
                "Nan Xue",
                " Tianfu Wu",
                " Gui-Song Xia",
                " Liangpei Zhang"
            ]
        },
        {
            "paperId": "9962",
            "posterId": "238a",
            "title": "AdaptPose: Cross-Dataset Adaptation for 3D Human Pose Estimation by Learnable Motion Generation",
            "authors": [
                "Mohsen Gholami",
                " Bastian Wandt",
                " Helge Rhodin",
                " Rabab Ward",
                " Z. Jane Wang"
            ]
        },
        {
            "paperId": "4071",
            "posterId": "239a",
            "title": "Single-Stage Is Enough: Multi-Person Absolute 3D Pose Estimation",
            "authors": [
                "Lei Jin",
                " Chenyang Xu",
                " Xiaojuan Wang",
                " Yabo Xiao",
                " Yandong Guo",
                " Xuecheng Nie",
                " Jian Zhao"
            ]
        },
        {
            "paperId": "6971",
            "posterId": "240a",
            "title": "Distribution-Aware Single-Stage Models for Multi-Person 3D Pose Estimation",
            "authors": [
                "Zitian Wang",
                " Xuecheng Nie",
                " Xiaochao Qu",
                " Yunpeng Chen",
                " Si Liu"
            ]
        },
        {
            "paperId": "10385",
            "posterId": "241a",
            "title": "Trajectory Optimization for Physics-Based Reconstruction of 3D Human Pose From Monocular Video",
            "authors": [
                "Erik Gärtner",
                " Mykhaylo Andriluka",
                " Hongyi Xu",
                " Cristian Sminchisescu"
            ]
        },
        {
            "paperId": "6843",
            "posterId": "242a",
            "title": "Ray3D: Ray-Based 3D Human Pose Estimation for Monocular Absolute 3D Localization",
            "authors": [
                "Yu Zhan",
                " Fenghai Li",
                " Renliang Weng",
                " Wongun Choi"
            ]
        },
        {
            "paperId": "3768",
            "posterId": "243a",
            "title": "Lite Pose: Efficient Architecture Design for 2D Human Pose Estimation",
            "authors": [
                "Yihan Wang",
                " Muyang Li",
                " Han Cai",
                " Wei-Ming Chen",
                " Song Han"
            ]
        },
        {
            "paperId": "2364",
            "posterId": "244a",
            "title": "Location-Free Human Pose Estimation",
            "authors": [
                "Xixia Xu",
                " Yingguo Gao",
                " Ke Yan",
                " Xue Lin",
                " Qi Zou"
            ]
        },
        {
            "paperId": "1083",
            "posterId": "245a",
            "title": "MHFormer: Multi-Hypothesis Transformer for 3D Human Pose Estimation",
            "authors": [
                "Wenhao Li",
                " Hong Liu",
                " Hao Tang",
                " Pichao Wang",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "7104",
            "posterId": "246a",
            "title": "Estimating Egocentric 3D Human Pose in the Wild With External Weak Supervision",
            "authors": [
                "Jian Wang",
                " Lingjie Liu",
                " Weipeng Xu",
                " Kripasindhu Sarkar",
                " Diogo Luvizon",
                " Christian Theobalt"
            ]
        },
        {
            "paperId": "1897",
            "posterId": "247a",
            "title": "Physical Inertial Poser (PIP): Physics-Aware Real-Time Human Motion Tracking From Sparse Inertial Sensors",
            "authors": [
                "Xinyu Yi",
                " Yuxiao Zhou",
                " Marc Habermann",
                " Soshi Shimada",
                " Vladislav Golyanik",
                " Christian Theobalt",
                " Feng Xu"
            ]
        },
        {
            "paperId": "5115",
            "posterId": "248a",
            "title": "PoseKernelLifter: Metric Lifting of 3D Human Pose Using Sound",
            "authors": [
                "Zhijian Yang",
                " Xiaoran Fan",
                " Volkan Isler",
                " Hyun Soo Park"
            ]
        },
        {
            "paperId": "10409",
            "posterId": "249a",
            "title": "Differentiable Dynamics for Articulated 3D Human Motion Reconstruction",
            "authors": [
                "Erik Gärtner",
                " Mykhaylo Andriluka",
                " Erwin Coumans",
                " Cristian Sminchisescu"
            ]
        },
        {
            "paperId": "4352",
            "posterId": "250a",
            "title": "COAP: Compositional Articulated Occupancy of People",
            "authors": [
                "Marko Mihajlovic",
                " Shunsuke Saito",
                " Aayush Bansal",
                " Michael Zollhöfer",
                " Siyu Tang"
            ]
        },
        {
            "paperId": "6849",
            "posterId": "251a",
            "title": "Capturing Humans in Motion: Temporal-Attentive 3D Human Pose and Shape Estimation From Monocular Video",
            "authors": [
                "Wen-Li Wei",
                " Jen-Chun Lin",
                " Tyng-Luh Liu",
                " Hong-Yuan Mark Liao"
            ]
        },
        {
            "paperId": "6924",
            "posterId": "252a",
            "title": "SC2-PCR: A Second Order Spatial Compatibility for Efficient and Robust Point Cloud Registration",
            "authors": [
                "Zhi Chen",
                " Kun Sun",
                " Fan Yang",
                " Wenbing Tao"
            ]
        },
        {
            "paperId": "3094",
            "posterId": "253a",
            "title": "MixSTE: Seq2seq Mixed Spatio-Temporal Encoder for 3D Human Pose Estimation in Video",
            "authors": [
                "Jinlu Zhang",
                " Zhigang Tu",
                " Jianyu Yang",
                " Yujin Chen",
                " Junsong Yuan"
            ]
        },
        {
            "paperId": "770",
            "posterId": "254a",
            "title": "Putting People in Their Place: Monocular Regression of 3D People in Depth",
            "authors": [
                "Yu Sun",
                " Wu Liu",
                " Qian Bao",
                " Yili Fu",
                " Tao Mei",
                " Michael J. Black"
            ]
        },
        {
            "paperId": "4288",
            "posterId": "255a",
            "title": "FLAG: Flow-Based 3D Avatar Generation From Sparse Observations",
            "authors": [
                "Sadegh Aliakbarian",
                " Pashmina Cameron",
                " Federica Bogo",
                " Andrew Fitzgibbon",
                " Thomas J. Cashman"
            ]
        },
        {
            "paperId": "896",
            "posterId": "256a",
            "title": "GOAL: Generating 4D Whole-Body Motion for Hand-Object Grasping",
            "authors": [
                "Omid Taheri",
                " Vasileios Choutas",
                " Michael J. Black",
                " Dimitrios Tzionas"
            ]
        },
        {
            "paperId": "933",
            "posterId": "257a",
            "title": "Capturing and Inferring Dense Full-Body Human-Scene Contact",
            "authors": [
                "Chun-Hao P. Huang",
                " Hongwei Yi",
                " Markus Höschle",
                " Matvey Safroshkin",
                " Tsvetelina Alexiadis",
                " Senya Polikovsky",
                " Daniel Scharstein",
                " Michael J. Black"
            ]
        },
        {
            "paperId": "3301",
            "posterId": "258a",
            "title": "BodyMap: Learning Full-Body Dense Correspondence Map",
            "authors": [
                "Anastasia Ianina",
                " Nikolaos Sarafianos",
                " Yuanlu Xu",
                " Ignacio Rocco",
                " Tony Tung"
            ]
        },
        {
            "paperId": "1209",
            "posterId": "259a",
            "title": "ICON: Implicit Clothed Humans Obtained From Normals",
            "authors": [
                "Yuliang Xiu",
                " Jinlong Yang",
                " Dimitrios Tzionas",
                " Michael J. Black"
            ]
        }
    ],
    "Transfer_Low-Shot_Long-Tail Learning": [
        {
            "paperId": "7748",
            "posterId": "104b",
            "title": "Generating Representative Samples for Few-Shot Classification",
            "authors": [
                "Jingyi Xu",
                " Hieu Le"
            ]
        },
        {
            "paperId": "2919",
            "posterId": "105b",
            "title": "Matching Feature Sets for Few-Shot Image Classification",
            "authors": [
                "Arman Afrasiyabi",
                " Hugo Larochelle",
                " Jean-François Lalonde",
                " Christian Gagné"
            ]
        },
        {
            "paperId": "2525",
            "posterId": "106b",
            "title": "Improving Adversarially Robust Few-Shot Image Classification With Generalizable Representations",
            "authors": [
                "Junhao Dong",
                " Yuan Wang",
                " Jian-Huang Lai",
                " Xiaohua Xie"
            ]
        },
        {
            "paperId": "6602",
            "posterId": "107b",
            "title": "Sylph: A Hypernetwork Framework for Incremental Few-Shot Object Detection",
            "authors": [
                "Li Yin",
                " Juan M. Perez-Rua",
                " Kevin J. Liang"
            ]
        },
        {
            "paperId": "9011",
            "posterId": "108b",
            "title": "Forward Compatible Few-Shot Class-Incremental Learning",
            "authors": [
                "Da-Wei Zhou",
                " Fu-Yun Wang",
                " Han-Jia Ye",
                " Liang Ma",
                " Shiliang Pu",
                " De-Chuan Zhan"
            ]
        },
        {
            "paperId": "10780",
            "posterId": "109b",
            "title": "Constrained Few-Shot Class-Incremental Learning",
            "authors": [
                "Michael Hersche",
                " Geethan Karunaratne",
                " Giovanni Cherubini",
                " Luca Benini",
                " Abu Sebastian",
                " Abbas Rahimi"
            ]
        },
        {
            "paperId": "9441",
            "posterId": "110b",
            "title": "Pushing the Limits of Simple Pipelines for Few-Shot Learning: External Data and Fine-Tuning Make a Difference",
            "authors": [
                "Shell Xu Hu",
                " Da Li",
                " Jan Stühmer",
                " Minyoung Kim",
                " Timothy M. Hospedales"
            ]
        },
        {
            "paperId": "9456",
            "posterId": "111b",
            "title": "EASE: Unsupervised Discriminant Subspace Learning for Transductive Few-Shot Learning",
            "authors": [
                "Hao Zhu",
                " Piotr Koniusz"
            ]
        },
        {
            "paperId": "10053",
            "posterId": "112b",
            "title": "Few-Shot Learning With Noisy Labels",
            "authors": [
                "Kevin J. Liang",
                " Samrudhdhi B. Rangrej",
                " Vladan Petrovic",
                " Tal Hassner"
            ]
        },
        {
            "paperId": "7988",
            "posterId": "113b",
            "title": "Ranking Distance Calibration for Cross-Domain Few-Shot Learning",
            "authors": [
                "Pan Li",
                " Shaogang Gong",
                " Chengjie Wang",
                " Yanwei Fu"
            ]
        },
        {
            "paperId": "10614",
            "posterId": "114b",
            "title": "Revisiting Learnable Affines for Batch Norm in Few-Shot Transfer Learning",
            "authors": [
                "Moslem Yazdanpanah",
                " Aamer Abdul Rahman",
                " Muawiz Chaudhary",
                " Christian Desrosiers",
                " Mohammad Havaei",
                " Eugene Belilovsky",
                " Samira Ebrahimi Kahou"
            ]
        },
        {
            "paperId": "2507",
            "posterId": "115b",
            "title": "Attribute Surrogates Learning and Spectral Tokens Pooling in Transformers for Few-Shot Learning",
            "authors": [
                "Yangji He",
                " Weihan Liang",
                " Dongyang Zhao",
                " Hong-Yu Zhou",
                " Weifeng Ge",
                " Yizhou Yu",
                " Wenqiang Zhang"
            ]
        },
        {
            "paperId": "8242",
            "posterId": "116b",
            "title": "Learning To Memorize Feature Hallucination for One-Shot Image Generation",
            "authors": [
                "Yu Xie",
                " Yanwei Fu",
                " Ying Tai",
                " Yun Cao",
                " Junwei Zhu",
                " Chengjie Wang"
            ]
        },
        {
            "paperId": "48",
            "posterId": "117b",
            "title": "A Closer Look at Few-Shot Image Generation",
            "authors": [
                "Yunqing Zhao",
                " Henghui Ding",
                " Houjing Huang",
                " Ngai-Man Cheung"
            ]
        },
        {
            "paperId": "4470",
            "posterId": "118b",
            "title": "Motion-Modulated Temporal Fragment Alignment Network for Few-Shot Action Recognition",
            "authors": [
                "Jiamin Wu",
                " Tianzhu Zhang",
                " Zhe Zhang",
                " Feng Wu",
                " Yongdong Zhang"
            ]
        },
        {
            "paperId": "2309",
            "posterId": "119b",
            "title": "Knowledge Distillation As Efficient Pre-Training: Faster Convergence, Higher Data-Efficiency, and Better Transferability",
            "authors": [
                "Ruifei He",
                " Shuyang Sun",
                " Jihan Yang",
                " Song Bai",
                " Xiaojuan Qi"
            ]
        },
        {
            "paperId": "1534",
            "posterId": "120b",
            "title": "Transferability Estimation Using Bhattacharyya Class Separability",
            "authors": [
                "Michal Pándy",
                " Andrea Agostinelli",
                " Jasper Uijlings",
                " Vittorio Ferrari",
                " Thomas Mensink"
            ]
        },
        {
            "paperId": "9832",
            "posterId": "121b",
            "title": "Revisiting the Transferability of Supervised Pretraining: An MLP Perspective",
            "authors": [
                "Yizhou Wang",
                " Shixiang Tang",
                " Feng Zhu",
                " Lei Bai",
                " Rui Zhao",
                " Donglian Qi",
                " Wanli Ouyang"
            ]
        },
        {
            "paperId": "5990",
            "posterId": "122b",
            "title": "Task2Sim: Towards Effective Pre-Training and Transfer From Synthetic Data",
            "authors": [
                "Samarth Mishra",
                " Rameswar Panda",
                " Cheng Perng Phoo",
                " Chun-Fu (Richard) Chen",
                " Leonid Karlinsky",
                " Kate Saenko",
                " Venkatesh Saligrama",
                " Rogerio S. Feris"
            ]
        },
        {
            "paperId": "6400",
            "posterId": "123b",
            "title": "Which Model To Transfer? Finding the Needle in the Growing Haystack",
            "authors": [
                "Cedric Renggli",
                " André Susano Pinto",
                " Luka Rimanic",
                " Joan Puigcerver",
                " Carlos Riquelme",
                " Ce Zhang",
                " Mario Lučić"
            ]
        },
        {
            "paperId": "7918",
            "posterId": "124b",
            "title": "Does Robustness on ImageNet Transfer to Downstream Tasks?",
            "authors": [
                "Yutaro Yamada",
                " Mayu Otani"
            ]
        },
        {
            "paperId": "9779",
            "posterId": "125b",
            "title": "What Makes Transfer Learning Work for Medical Images: Feature Reuse & Other Factors",
            "authors": [
                "Christos Matsoukas",
                " Johan Fredin Haslum",
                " Moein Sorkhei",
                " Magnus Söderberg",
                " Kevin Smith"
            ]
        },
        {
            "paperId": "3815",
            "posterId": "126b",
            "title": "OW-DETR: Open-World Detection Transformer",
            "authors": [
                "Akshita Gupta",
                " Sanath Narayan",
                " K J Joseph",
                " Salman Khan",
                " Fahad Shahbaz Khan",
                " Mubarak Shah"
            ]
        },
        {
            "paperId": "9180",
            "posterId": "127b",
            "title": "Unseen Classes at a Later Time? No Problem",
            "authors": [
                "Hari Chandana Kuchibhotla",
                " Sumitra S Malagi",
                " Shivam Chandhok",
                " Vineeth N Balasubramanian"
            ]
        },
        {
            "paperId": "6901",
            "posterId": "128b",
            "title": "Continual Object Detection via Prototypical Task Correlation Guided Gating Mechanism",
            "authors": [
                "Binbin Yang",
                " Xinchi Deng",
                " Han Shi",
                " Changlin Li",
                " Gengwei Zhang",
                " Hang Xu",
                " Shen Zhao",
                " Liang Lin",
                " Xiaodan Liang"
            ]
        },
        {
            "paperId": "5542",
            "posterId": "129b",
            "title": "On Generalizing Beyond Domains in Cross-Domain Continual Learning",
            "authors": [
                "Christian Simon",
                " Masoud Faraki",
                " Yi-Hsuan Tsai",
                " Xiang Yu",
                " Samuel Schulter",
                " Yumin Suh",
                " Mehrtash Harandi",
                " Manmohan Chandraker"
            ]
        },
        {
            "paperId": "10123",
            "posterId": "130b",
            "title": "Online Continual Learning on a Contaminated Data Stream With Blurry Task Boundaries",
            "authors": [
                "Jihwan Bang",
                " Hyunseo Koh",
                " Seulki Park",
                " Hwanjun Song",
                " Jung-Woo Ha",
                " Jonghyun Choi"
            ]
        },
        {
            "paperId": "2527",
            "posterId": "131b",
            "title": "DyTox: Transformers for Continual Learning With DYnamic TOken eXpansion",
            "authors": [
                "Arthur Douillard",
                " Alexandre Ramé",
                " Guillaume Couairon",
                " Matthieu Cord"
            ]
        },
        {
            "paperId": "544",
            "posterId": "132b",
            "title": "Self-Sustaining Representation Expansion for Non-Exemplar Class-Incremental Learning",
            "authors": [
                "Kai Zhu",
                " Wei Zhai",
                " Yang Cao",
                " Jiebo Luo",
                " Zheng-Jun Zha"
            ]
        },
        {
            "paperId": "2321",
            "posterId": "133b",
            "title": "En-Compactness: Self-Distillation Embedding & Contrastive Generation for Generalized Zero-Shot Learning",
            "authors": [
                "Xia Kong",
                " Zuodong Gao",
                " Xiaofan Li",
                " Ming Hong",
                " Jun Liu",
                " Chengjie Wang",
                " Yuan Xie",
                " Yanyun Qu"
            ]
        },
        {
            "paperId": "5161",
            "posterId": "134b",
            "title": "VGSE: Visually-Grounded Semantic Embeddings for Zero-Shot Learning",
            "authors": [
                "Wenjia Xu",
                " Yongqin Xian",
                " Jiuniu Wang",
                " Bernt Schiele",
                " Zeynep Akata"
            ]
        },
        {
            "paperId": "5950",
            "posterId": "135b",
            "title": "Siamese Contrastive Embedding Network for Compositional Zero-Shot Learning",
            "authors": [
                "Xiangyu Li",
                " Xu Yang",
                " Kun Wei",
                " Cheng Deng",
                " Muli Yang"
            ]
        },
        {
            "paperId": "8438",
            "posterId": "136b",
            "title": "KG-SP: Knowledge Guided Simple Primitives for Open World Compositional Zero-Shot Learning",
            "authors": [
                "Shyamgopal Karthik",
                " Massimiliano Mancini",
                " Zeynep Akata"
            ]
        },
        {
            "paperId": "6727",
            "posterId": "137b",
            "title": "Non-Generative Generalized Zero-Shot Learning via Task-Correlated Disentanglement and Controllable Samples Synthesis",
            "authors": [
                "Yaogong Feng",
                " Xiaowen Huang",
                " Pengbo Yang",
                " Jian Yu",
                " Jitao Sang"
            ]
        },
        {
            "paperId": "4846",
            "posterId": "138b",
            "title": "WALT: Watch and Learn 2D Amodal Representation From Time-Lapse Imagery",
            "authors": [
                "N. Dinesh Reddy",
                " Robert Tamburo",
                " Srinivasa G. Narasimhan"
            ]
        }
    ],
    "Motion, Tracking, Registration, Vision & X, and Theory": [
        {
            "paperId": "1812",
            "posterId": "16b",
            "title": "MeMOT: Multi-Object Tracking With Memory",
            "authors": [
                "Jiarui Cai",
                " Mingze Xu",
                " Wei Li",
                " Yuanjun Xiong",
                " Wei Xia",
                " Zhuowen Tu",
                " Stefano Soatto"
            ]
        },
        {
            "paperId": "2326",
            "posterId": "17b",
            "title": "Unsupervised Learning of Accurate Siamese Tracking",
            "authors": [
                "Qiuhong Shen",
                " Lei Qiao",
                " Jinyang Guo",
                " Peixia Li",
                " Xin Li",
                " Bo Li",
                " Weitao Feng",
                " Weihao Gan",
                " Wei Wu",
                " Wanli Ouyang"
            ]
        },
        {
            "paperId": "1995",
            "posterId": "18b",
            "title": "Beyond 3D Siamese Tracking: A Motion-Centric Paradigm for 3D Single Object Tracking in Point Clouds",
            "authors": [
                "Chaoda Zheng",
                " Xu Yan",
                " Haiming Zhang",
                " Baoyuan Wang",
                " Shenghui Cheng",
                " Shuguang Cui",
                " Zhen Li"
            ]
        },
        {
            "paperId": "3616",
            "posterId": "19b",
            "title": "GMFlow: Learning Optical Flow via Global Matching",
            "authors": [
                "Haofei Xu",
                " Jing Zhang",
                " Jianfei Cai",
                " Hamid Rezatofighi",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "10012",
            "posterId": "20b",
            "title": "GridShift: A Faster Mode-Seeking Algorithm for Image Segmentation and Object Tracking",
            "authors": [
                "Abhishek Kumar",
                " Oladayo S. Ajani",
                " Swagatam Das",
                " Rammohan Mallipeddi"
            ]
        },
        {
            "paperId": "3417",
            "posterId": "21b",
            "title": "SNUG: Self-Supervised Neural Dynamic Garments",
            "authors": [
                "Igor Santesteban",
                " Miguel A. Otaduy",
                " Dan Casas"
            ]
        },
        {
            "paperId": "6431",
            "posterId": "22b",
            "title": "Weakly-Supervised Action Transition Learning for Stochastic Human Motion Prediction",
            "authors": [
                "Wei Mao",
                " Miaomiao Liu",
                " Mathieu Salzmann"
            ]
        },
        {
            "paperId": "10207",
            "posterId": "23b",
            "title": "Multi-Objective Diverse Human Motion Prediction With Knowledge Distillation",
            "authors": [
                "Hengbo Ma",
                " Jiachen Li",
                " Ramtin Hosseini",
                " Masayoshi Tomizuka",
                " Chiho Choi"
            ]
        },
        {
            "paperId": "4351",
            "posterId": "24b",
            "title": "Context-Aware Sequence Alignment Using 4D Skeletal Augmentation",
            "authors": [
                "Taein Kwon",
                " Bugra Tekin",
                " Siyu Tang",
                " Marc Pollefeys"
            ]
        },
        {
            "paperId": "10467",
            "posterId": "25b",
            "title": "Enabling Equivariance for Arbitrary Lie Groups",
            "authors": [
                "Lachlan E. MacDonald",
                " Sameera Ramasinghe",
                " Simon Lucey"
            ]
        },
        {
            "paperId": "1089",
            "posterId": "26b",
            "title": "RAMA: A Rapid Multicut Algorithm on GPU",
            "authors": [
                "Ahmed Abbas",
                " Paul Swoboda"
            ]
        },
        {
            "paperId": "103",
            "posterId": "27b",
            "title": "Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks",
            "authors": [
                "Peri Akiva",
                " Matthew Purri",
                " Matthew Leotta"
            ]
        },
        {
            "paperId": "6427",
            "posterId": "28b",
            "title": "RCP: Recurrent Closest Point for Point Cloud",
            "authors": [
                "Xiaodong Gu",
                " Chengzhou Tang",
                " Weihao Yuan",
                " Zuozhuo Dai",
                " Siyu Zhu",
                " Ping Tan"
            ]
        },
        {
            "paperId": "6607",
            "posterId": "29b",
            "title": "Audio-Visual Speech Codecs: Rethinking Audio-Visual Speech Enhancement by Re-Synthesis",
            "authors": [
                "Karren Yang",
                " Dejan Marković",
                " Steven Krenn",
                " Vasu Agrawal",
                " Alexander Richard"
            ]
        },
        {
            "paperId": "6810",
            "posterId": "30b",
            "title": "Balanced Multimodal Learning via On-the-Fly Gradient Modulation",
            "authors": [
                "Xiaokang Peng",
                " Yake Wei",
                " Andong Deng",
                " Dong Wang",
                " Di Hu"
            ]
        }
    ],
    "3D from Multiview & Sensors, Learning for Vision, Explainable Vision, and Privacy": [
        {
            "paperId": "3870",
            "posterId": "31b",
            "title": "Block-NeRF: Scalable Large Scene Neural View Synthesis",
            "authors": [
                "Matthew Tancik",
                " Vincent Casser",
                " Xinchen Yan",
                " Sabeek Pradhan",
                " Ben Mildenhall",
                " Pratul P. Srinivasan",
                " Jonathan T. Barron",
                " Henrik Kretzschmar"
            ]
        },
        {
            "paperId": "5472",
            "posterId": "32b",
            "title": "SceneSqueezer: Learning To Compress Scene for Camera Relocalization",
            "authors": [
                "Luwei Yang",
                " Rakesh Shrestha",
                " Wenbo Li",
                " Shuaicheng Liu",
                " Guofeng Zhang",
                " Zhaopeng Cui",
                " Ping Tan"
            ]
        },
        {
            "paperId": "7077",
            "posterId": "33b",
            "title": "Light Field Neural Rendering",
            "authors": [
                "Mohammed Suhail",
                " Carlos Esteves",
                " Leonid Sigal",
                " Ameesh Makadia"
            ]
        },
        {
            "paperId": "8204",
            "posterId": "34b",
            "title": "Extracting Triangular 3D Models, Materials, and Lighting From Images",
            "authors": [
                "Jacob Munkberg",
                " Jon Hasselgren",
                " Tianchang Shen",
                " Jun Gao",
                " Wenzheng Chen",
                " Alex Evans",
                " Thomas Müller",
                " Sanja Fidler"
            ]
        },
        {
            "paperId": "8722",
            "posterId": "35b",
            "title": "Super-Fibonacci Spirals: Fast, Low-Discrepancy Sampling of SO(3)",
            "authors": [
                "Marc Alexa"
            ]
        },
        {
            "paperId": "1461",
            "posterId": "36b",
            "title": "Stochastic Backpropagation: A Memory Efficient Strategy for Training Video Models",
            "authors": [
                "Feng Cheng",
                " Mingze Xu",
                " Yuanjun Xiong",
                " Hao Chen",
                " Xinyu Li",
                " Wei Li",
                " Wei Xia"
            ]
        },
        {
            "paperId": "6131",
            "posterId": "37b",
            "title": "It's All in the Teacher: Zero-Shot Quantization Brought Closer to the Teacher",
            "authors": [
                "Kanghyun Choi",
                " Hye Yoon Lee",
                " Deokki Hong",
                " Joonsang Yu",
                " Noseong Park",
                " Youngsok Kim",
                " Jinho Lee"
            ]
        },
        {
            "paperId": "6484",
            "posterId": "38b",
            "title": "NLX-GPT: A Model for Natural Language Explanations in Vision and Vision-Language Tasks",
            "authors": [
                "Fawaz Sammani",
                " Tanmoy Mukherjee",
                " Nikos Deligiannis"
            ]
        },
        {
            "paperId": "7060",
            "posterId": "39b",
            "title": "Explaining Deep Convolutional Neural Networks via Latent Visual-Semantic Filter Attention",
            "authors": [
                "Yu Yang",
                " Seungbae Kim",
                " Jungseock Joo"
            ]
        },
        {
            "paperId": "5966",
            "posterId": "40b",
            "title": "Parameter-Free Online Test-Time Adaptation",
            "authors": [
                "Malik Boudiaf",
                " Romain Mueller",
                " Ismail Ben Ayed",
                " Luca Bertinetto"
            ]
        },
        {
            "paperId": "10272",
            "posterId": "41b",
            "title": "Patch-Level Representation Learning for Self-Supervised Vision Transformers",
            "authors": [
                "Sukmin Yun",
                " Hankook Lee",
                " Jaehyung Kim",
                " Jinwoo Shin"
            ]
        },
        {
            "paperId": "11845",
            "posterId": "42b",
            "title": "Deep Spectral Methods: A Surprisingly Strong Baseline for Unsupervised Semantic Segmentation and Localization",
            "authors": [
                "Luke Melas-Kyriazi",
                " Christian Rupprecht",
                " Iro Laina",
                " Andrea Vedaldi"
            ]
        },
        {
            "paperId": "9568",
            "posterId": "43b",
            "title": "Mixed Differential Privacy in Computer Vision",
            "authors": [
                "Aditya Golatkar",
                " Alessandro Achille",
                " Yu-Xiang Wang",
                " Aaron Roth",
                " Michael Kearns",
                " Stefano Soatto"
            ]
        },
        {
            "paperId": "2663",
            "posterId": "44b",
            "title": "DPGEN: Differentially Private Generative Energy-Guided Network for Natural Image Synthesis",
            "authors": [
                "Jia-Wei Chen",
                " Chia-Mu Yu",
                " Ching-Chia Kao",
                " Tzai-Wei Pang",
                " Chun-Shien Lu"
            ]
        },
        {
            "paperId": "11405",
            "posterId": "45b",
            "title": "Local Learning Matters: Rethinking Data Heterogeneity in Federated Learning",
            "authors": [
                "Matias Mendieta",
                " Taojiannan Yang",
                " Pu Wang",
                " Minwoo Lee",
                " Zhengming Ding",
                " Chen Chen"
            ]
        }
    ],
    "Computer Vision Theory": [
        {
            "paperId": "11527",
            "posterId": "97b",
            "title": "On the Instability of Relative Pose Estimation and RANSAC's Role",
            "authors": [
                "Hongyi Fan",
                " Joe Kileel",
                " Benjamin Kimia"
            ]
        },
        {
            "paperId": "1458",
            "posterId": "98b",
            "title": "Bootstrapping ViTs: Towards Liberating Vision Transformers From Pre-Training",
            "authors": [
                "Haofei Zhang",
                " Jiarui Duan",
                " Mengqi Xue",
                " Jie Song",
                " Li Sun",
                " Mingli Song"
            ]
        },
        {
            "paperId": "2845",
            "posterId": "99b",
            "title": "Global Sensing and Measurements Reuse for Image Compressed Sensing",
            "authors": [
                "Zi-En Fan",
                " Feng Lian",
                " Jia-Ni Quan"
            ]
        },
        {
            "paperId": "7248",
            "posterId": "100b",
            "title": "Maximum Consensus by Weighted Influences of Monotone Boolean Functions",
            "authors": [
                "Erchuan Zhang",
                " David Suter",
                " Ruwan Tennakoon",
                " Tat-Jun Chin",
                " Alireza Bab-Hadiashar",
                " Giang Truong",
                " Syed Zulqarnain Gilani"
            ]
        },
        {
            "paperId": "8398",
            "posterId": "101b",
            "title": "MS2DG-Net: Progressive Correspondence Learning via Multiple Sparse Semantics Dynamic Graph",
            "authors": [
                "Luanyuan Dai",
                " Yizhang Liu",
                " Jiayi Ma",
                " Lifang Wei",
                " Taotao Lai",
                " Changcai Yang",
                " Riqing Chen"
            ]
        },
        {
            "paperId": "6292",
            "posterId": "102b",
            "title": "Styleformer: Transformer Based Generative Adversarial Networks With Style Vector",
            "authors": [
                "Jeeseung Park",
                " Younggeun Kim"
            ]
        },
        {
            "paperId": "9212",
            "posterId": "103b",
            "title": "Scanline Homographies for Rolling-Shutter Plane Absolute Pose",
            "authors": [
                "Fang Bai",
                " Agniva Sengupta",
                " Adrien Bartoli"
            ]
        }
    ],
    "Self_Semi_Meta & Unsupervised Learning": [
        {
            "paperId": "4675",
            "posterId": "164b",
            "title": "Self-Supervised Models Are Continual Learners",
            "authors": [
                "Enrico Fini",
                " Victor G. Turrisi da Costa",
                " Xavier Alameda-Pineda",
                " Elisa Ricci",
                " Karteek Alahari",
                " Julien Mairal"
            ]
        },
        {
            "paperId": "5592",
            "posterId": "165b",
            "title": "The Two Dimensions of Worst-Case Training and Their Integrated Effect for Out-of-Domain Generalization",
            "authors": [
                "Zeyi Huang",
                " Haohan Wang",
                " Dong Huang",
                " Yong Jae Lee",
                " Eric P. Xing"
            ]
        },
        {
            "paperId": "5983",
            "posterId": "166b",
            "title": "Beyond Supervised vs. Unsupervised: Representative Benchmarking and Analysis of Image Representation Learning",
            "authors": [
                "Matthew Gwilliam",
                " Abhinav Shrivastava"
            ]
        },
        {
            "paperId": "7932",
            "posterId": "167b",
            "title": "SimMIM: A Simple Framework for Masked Image Modeling",
            "authors": [
                "Zhenda Xie",
                " Zheng Zhang",
                " Yue Cao",
                " Yutong Lin",
                " Jianmin Bao",
                " Zhuliang Yao",
                " Qi Dai",
                " Han Hu"
            ]
        },
        {
            "paperId": "8651",
            "posterId": "168b",
            "title": "Semantic-Aware Auto-Encoders for Self-Supervised Representation Learning",
            "authors": [
                "Guangrun Wang",
                " Yansong Tang",
                " Liang Lin",
                " Philip H.S. Torr"
            ]
        },
        {
            "paperId": "7363",
            "posterId": "169b",
            "title": "UniCon: Combating Label Noise Through Uniform Selection and Contrastive Learning",
            "authors": [
                "Nazmul Karim",
                " Mamshad Nayeem Rizve",
                " Nazanin Rahnavard",
                " Ajmal Mian",
                " Mubarak Shah"
            ]
        },
        {
            "paperId": "6763",
            "posterId": "170b",
            "title": "Contrastive Conditional Neural Processes",
            "authors": [
                "Zesheng Ye",
                " Lina Yao"
            ]
        },
        {
            "paperId": "1945",
            "posterId": "171b",
            "title": "One-Bit Active Query With Contrastive Pairs",
            "authors": [
                "Yuhang Zhang",
                " Xiaopeng Zhang",
                " Lingxi Xie",
                " Jie Li",
                " Robert C. Qiu",
                " Hengtong Hu",
                " Qi Tian"
            ]
        },
        {
            "paperId": "496",
            "posterId": "172b",
            "title": "HCSC: Hierarchical Contrastive Selective Coding",
            "authors": [
                "Yuanfan Guo",
                " Minghao Xu",
                " Jiawen Li",
                " Bingbing Ni",
                " Xuanyu Zhu",
                " Zhenbang Sun",
                " Yi Xu"
            ]
        },
        {
            "paperId": "4560",
            "posterId": "173b",
            "title": "Motion-Aware Contrastive Video Representation Learning via Foreground-Background Merging",
            "authors": [
                "Shuangrui Ding",
                " Maomao Li",
                " Tianyu Yang",
                " Rui Qian",
                " Haohang Xu",
                " Qingyi Chen",
                " Jue Wang",
                " Hongkai Xiong"
            ]
        },
        {
            "paperId": "9291",
            "posterId": "174b",
            "title": "Hierarchical Self-Supervised Representation Learning for Movie Understanding",
            "authors": [
                "Fanyi Xiao",
                " Kaustav Kundu",
                " Joseph Tighe",
                " Davide Modolo"
            ]
        },
        {
            "paperId": "7239",
            "posterId": "175b",
            "title": "Anomaly Detection via Reverse Distillation From One-Class Embedding",
            "authors": [
                "Hanqiu Deng",
                " Xingyu Li"
            ]
        },
        {
            "paperId": "8177",
            "posterId": "176b",
            "title": "Unsupervised Representation Learning for Binary Networks by Joint Classifier Learning",
            "authors": [
                "Dahyun Kim",
                " Jonghyun Choi"
            ]
        },
        {
            "paperId": "3636",
            "posterId": "177b",
            "title": "DC-SSL: Addressing Mismatched Class Distribution in Semi-Supervised Learning",
            "authors": [
                "Zhen Zhao",
                " Luping Zhou",
                " Yue Duan",
                " Lei Wang",
                " Lei Qi",
                " Yinghuan Shi"
            ]
        },
        {
            "paperId": "5723",
            "posterId": "178b",
            "title": "Learning To Collaborate in Decentralized Learning of Personalized Models",
            "authors": [
                "Shuangtong Li",
                " Tianyi Zhou",
                " Xinmei Tian",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "8083",
            "posterId": "179b",
            "title": "Highly-Efficient Incomplete Large-Scale Multi-View Clustering With Consensus Bipartite Graph",
            "authors": [
                "Siwei Wang",
                " Xinwang Liu",
                " Li Liu",
                " Wenxuan Tu",
                " Xinzhong Zhu",
                " Jiyuan Liu",
                " Sihang Zhou",
                " En Zhu"
            ]
        },
        {
            "paperId": "1264",
            "posterId": "180b",
            "title": "DASO: Distribution-Aware Semantics-Oriented Pseudo-Label for Imbalanced Semi-Supervised Learning",
            "authors": [
                "Youngtaek Oh",
                " Dong-Jin Kim",
                " In So Kweon"
            ]
        },
        {
            "paperId": "1835",
            "posterId": "181b",
            "title": "Global Convergence of MAML and Theory-Inspired Neural Architecture Search for Few-Shot Learning",
            "authors": [
                "Haoxiang Wang",
                " Yite Wang",
                " Ruoyu Sun",
                " Bo Li"
            ]
        },
        {
            "paperId": "1139",
            "posterId": "182b",
            "title": "Semi-Supervised Object Detection via Multi-Instance Alignment With Global Class Prototypes",
            "authors": [
                "Aoxue Li",
                " Peng Yuan",
                " Zhenguo Li"
            ]
        },
        {
            "paperId": "1554",
            "posterId": "183b",
            "title": "Unbiased Teacher v2: Semi-Supervised Object Detection for Anchor-Free and Anchor-Based Detectors",
            "authors": [
                "Yen-Cheng Liu",
                " Chih-Yao Ma",
                " Zsolt Kira"
            ]
        },
        {
            "paperId": "2856",
            "posterId": "184b",
            "title": "Spectral Unsupervised Domain Adaptation for Visual Recognition",
            "authors": [
                "Jingyi Zhang",
                " Jiaxing Huang",
                " Zichen Tian",
                " Shijian Lu"
            ]
        },
        {
            "paperId": "1408",
            "posterId": "185b",
            "title": "DATA: Domain-Aware and Task-Aware Self-Supervised Learning",
            "authors": [
                "Qing Chang",
                " Junran Peng",
                " Lingxi Xie",
                " Jiajun Sun",
                " Haoran Yin",
                " Qi Tian",
                " Zhaoxiang Zhang"
            ]
        },
        {
            "paperId": "2449",
            "posterId": "186b",
            "title": "Dynamic Kernel Selection for Improved Generalization and Memory Efficiency in Meta-Learning",
            "authors": [
                "Arnav Chavan",
                " Rishabh Tiwari",
                " Udbhav Bamba",
                " Deepak K. Gupta"
            ]
        },
        {
            "paperId": "4337",
            "posterId": "187b",
            "title": "DeepDPM: Deep Clustering With an Unknown Number of Clusters",
            "authors": [
                "Meitar Ronen",
                " Shahaf E. Finder",
                " Oren Freifeld"
            ]
        },
        {
            "paperId": "7785",
            "posterId": "188b",
            "title": "PLAD: Learning To Infer Shape Programs With Pseudo-Labels and Approximate Distributions",
            "authors": [
                "R. Kenny Jones",
                " Homer Walke",
                " Daniel Ritchie"
            ]
        },
        {
            "paperId": "9990",
            "posterId": "189b",
            "title": "Robust Outlier Detection by De-Biasing VAE Likelihoods",
            "authors": [
                "Kushal Chauhan",
                " Barath Mohan U",
                " Pradeep Shenoy",
                " Manish Gupta",
                " Devarajan Sridharan"
            ]
        },
        {
            "paperId": "3489",
            "posterId": "190b",
            "title": "Image-to-Lidar Self-Supervised Distillation for Autonomous Driving Data",
            "authors": [
                "Corentin Sautier",
                " Gilles Puy",
                " Spyros Gidaris",
                " Alexandre Boulch",
                " Andrei Bursuc",
                " Renaud Marlet"
            ]
        },
        {
            "paperId": "1420",
            "posterId": "191b",
            "title": "CrossPoint: Self-Supervised Cross-Modal Contrastive Learning for 3D Point Cloud Understanding",
            "authors": [
                "Mohamed Afham",
                " Isuru Dissanayake",
                " Dinithi Dissanayake",
                " Amaya Dharmasiri",
                " Kanchana Thilakarathna",
                " Ranga Rodrigo"
            ]
        },
        {
            "paperId": "10336",
            "posterId": "192b",
            "title": "Cross-Domain Correlation Distillation for Unsupervised Domain Adaptation in Nighttime Semantic Segmentation",
            "authors": [
                "Huan Gao",
                " Jichang Guo",
                " Guoli Wang",
                " Qian Zhang"
            ]
        },
        {
            "paperId": "3423",
            "posterId": "193b",
            "title": "DAFormer: Improving Network Architectures and Training Strategies for Domain-Adaptive Semantic Segmentation",
            "authors": [
                "Lukas Hoyer",
                " Dengxin Dai",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "8154",
            "posterId": "194b",
            "title": "WildNet: Learning Domain Generalized Semantic Segmentation From the Wild",
            "authors": [
                "Suhyeon Lee",
                " Hongje Seong",
                " Seongwon Lee",
                " Euntai Kim"
            ]
        },
        {
            "paperId": "5616",
            "posterId": "195b",
            "title": "UCC: Uncertainty Guided Cross-Head Co-Training for Semi-Supervised Semantic Segmentation",
            "authors": [
                "Jiashuo Fan",
                " Bin Gao",
                " Huan Jin",
                " Lihui Jiang"
            ]
        },
        {
            "paperId": "4410",
            "posterId": "196b",
            "title": "Semi-Supervised Semantic Segmentation With Error Localization Network",
            "authors": [
                "Donghyeon Kwon",
                " Suha Kwak"
            ]
        },
        {
            "paperId": "621",
            "posterId": "197b",
            "title": "Unbiased Subclass Regularization for Semi-Supervised Semantic Segmentation",
            "authors": [
                "Dayan Guan",
                " Jiaxing Huang",
                " Aoran Xiao",
                " Shijian Lu"
            ]
        },
        {
            "paperId": "750",
            "posterId": "198b",
            "title": "Integrative Few-Shot Learning for Classification and Segmentation",
            "authors": [
                "Dahyun Kang",
                " Minsu Cho"
            ]
        },
        {
            "paperId": "4568",
            "posterId": "199b",
            "title": "GanOrCon: Are Generative Models Useful for Few-Shot Segmentation?",
            "authors": [
                "Oindrila Saha",
                " Zezhou Cheng",
                " Subhransu Maji"
            ]
        },
        {
            "paperId": "8214",
            "posterId": "200b",
            "title": "SphericGAN: Semi-Supervised Hyper-Spherical Generative Adversarial Networks for Fine-Grained Image Synthesis",
            "authors": [
                "Tianyi Chen",
                " Yunfei Zhang",
                " Xiaoyang Huo",
                " Si Wu",
                " Yong Xu",
                " Hau San Wong"
            ]
        },
        {
            "paperId": "1055",
            "posterId": "201b",
            "title": "CoordGAN: Self-Supervised Dense Correspondences Emerge From GANs",
            "authors": [
                "Jiteng Mu",
                " Shalini De Mello",
                " Zhiding Yu",
                " Nuno Vasconcelos",
                " Xiaolong Wang",
                " Jan Kautz",
                " Sifei Liu"
            ]
        }
    ],
    "Privacy and Federated Learning": [
        {
            "paperId": "93",
            "posterId": "202b",
            "title": "GradViT: Gradient Inversion of Vision Transformers",
            "authors": [
                "Ali Hatamizadeh",
                " Hongxu Yin",
                " Holger R. Roth",
                " Wenqi Li",
                " Jan Kautz",
                " Daguang Xu",
                " Pavlo Molchanov"
            ]
        },
        {
            "paperId": "9396",
            "posterId": "203b",
            "title": "Deep 3D-to-2D Watermarking: Embedding Messages in 3D Meshes and Extracting Them From 2D Renderings",
            "authors": [
                "Innfarn Yoo",
                " Huiwen Chang",
                " Xiyang Luo",
                " Ondrej Stava",
                " Ce Liu",
                " Peyman Milanfar",
                " Feng Yang"
            ]
        },
        {
            "paperId": "7502",
            "posterId": "204b",
            "title": "CD2-pFed: Cyclic Distillation-Guided Channel Decoupling for Model Personalization in Federated Learning",
            "authors": [
                "Yiqing Shen",
                " Yuyin Zhou",
                " Lequan Yu"
            ]
        },
        {
            "paperId": "6925",
            "posterId": "205b",
            "title": "APRIL: Finding the Achilles' Heel on Privacy for Vision Transformers",
            "authors": [
                "Jiahao Lu",
                " Xi Sheryl Zhang",
                " Tianli Zhao",
                " Xiangyu He",
                " Jian Cheng"
            ]
        },
        {
            "paperId": "6650",
            "posterId": "206b",
            "title": "Rethinking Architecture Design for Tackling Data Heterogeneity in Federated Learning",
            "authors": [
                "Liangqiong Qu",
                " Yuyin Zhou",
                " Paul Pu Liang",
                " Yingda Xia",
                " Feifei Wang",
                " Ehsan Adeli",
                " Li Fei-Fei",
                " Daniel Rubin"
            ]
        },
        {
            "paperId": "6121",
            "posterId": "207b",
            "title": "Robust Federated Learning With Noisy and Heterogeneous Clients",
            "authors": [
                "Xiuwen Fang",
                " Mang Ye"
            ]
        },
        {
            "paperId": "9724",
            "posterId": "208b",
            "title": "Federated Learning With Position-Aware Neurons",
            "authors": [
                "Xin-Chun Li",
                " Yi-Chu Xu",
                " Shaoming Song",
                " Bingshuai Li",
                " Yinchuan Li",
                " Yunfeng Shao",
                " De-Chuan Zhan"
            ]
        },
        {
            "paperId": "10112",
            "posterId": "209b",
            "title": "Layer-Wised Model Aggregation for Personalized Federated Learning",
            "authors": [
                "Xiaosong Ma",
                " Jie Zhang",
                " Song Guo",
                " Wenchao Xu"
            ]
        },
        {
            "paperId": "4369",
            "posterId": "210b",
            "title": "FedCor: Correlation-Based Active Client Selection Strategy for Heterogeneous Federated Learning",
            "authors": [
                "Minxue Tang",
                " Xuefei Ning",
                " Yitu Wang",
                " Jingwei Sun",
                " Yu Wang",
                " Hai Li",
                " Yiran Chen"
            ]
        },
        {
            "paperId": "2897",
            "posterId": "211b",
            "title": "FedDC: Federated Learning With Non-IID Data via Local Drift Decoupling and Correction",
            "authors": [
                "Liang Gao",
                " Huazhu Fu",
                " Li Li",
                " Yingwen Chen",
                " Ming Xu",
                " Cheng-Zhong Xu"
            ]
        },
        {
            "paperId": "1250",
            "posterId": "212b",
            "title": "Differentially Private Federated Learning With Local Regularization and Sparsification",
            "authors": [
                "Anda Cheng",
                " Peisong Wang",
                " Xi Sheryl Zhang",
                " Jian Cheng"
            ]
        },
        {
            "paperId": "1234",
            "posterId": "213b",
            "title": "Auditing Privacy Defenses in Federated Learning via Generative Gradient Leakage",
            "authors": [
                "Zhuohang Li",
                " Jiaxin Zhang",
                " Luyang Liu",
                " Jian Liu"
            ]
        },
        {
            "paperId": "5568",
            "posterId": "214b",
            "title": "Learn From Others and Be Yourself in Heterogeneous Federated Learning",
            "authors": [
                "Wenke Huang",
                " Mang Ye",
                " Bo Du"
            ]
        },
        {
            "paperId": "3953",
            "posterId": "215b",
            "title": "RSCFed: Random Sampling Consensus Federated Semi-Supervised Learning",
            "authors": [
                "Xiaoxiao Liang",
                " Yiqun Lin",
                " Huazhu Fu",
                " Lei Zhu",
                " Xiaomeng Li"
            ]
        },
        {
            "paperId": "2956",
            "posterId": "216b",
            "title": "Federated Class-Incremental Learning",
            "authors": [
                "Jiahua Dong",
                " Lixu Wang",
                " Zhen Fang",
                " Gan Sun",
                " Shichao Xu",
                " Xiao Wang",
                " Qi Zhu"
            ]
        },
        {
            "paperId": "7881",
            "posterId": "217b",
            "title": "Fine-Tuning Global Model via Data-Free Knowledge Distillation for Non-IID Federated Learning",
            "authors": [
                "Lin Zhang",
                " Li Shen",
                " Liang Ding",
                " Dacheng Tao",
                " Ling-Yu Duan"
            ]
        },
        {
            "paperId": "8257",
            "posterId": "218b",
            "title": "FedCorr: Multi-Stage Federated Learning for Label Noise Correction",
            "authors": [
                "Jingyi Xu",
                " Zihan Chen",
                " Tony Q.S. Quek",
                " Kai Fong Ernest Chong"
            ]
        },
        {
            "paperId": "6027",
            "posterId": "219b",
            "title": "ResSFL: A Resistance Transfer Framework for Defending Model Inversion Attack in Split Federated Learning",
            "authors": [
                "Jingtao Li",
                " Adnan Siraj Rakin",
                " Xing Chen",
                " Zhezhi He",
                " Deliang Fan",
                " Chaitali Chakrabarti"
            ]
        }
    ],
    "Explainable Computer Vision": [
        {
            "paperId": "1096",
            "posterId": "220b",
            "title": "Cycle-Consistent Counterfactuals by Latent Transformations",
            "authors": [
                "Saeed Khorram",
                " Li Fuxin"
            ]
        },
        {
            "paperId": "5428",
            "posterId": "221b",
            "title": "Consistent Explanations by Contrastive Learning",
            "authors": [
                "Vipin Pillai",
                " Soroush Abbasi Koohpayegani",
                " Ashley Ouligian",
                " Dennis Fong",
                " Hamed Pirsiavash"
            ]
        },
        {
            "paperId": "6357",
            "posterId": "222b",
            "title": "Towards Better Understanding Attribution Methods",
            "authors": [
                "Sukrut Rao",
                " Moritz Böhle",
                " Bernt Schiele"
            ]
        },
        {
            "paperId": "7285",
            "posterId": "223b",
            "title": "Proto2Proto: Can You Recognize the Car, the Way I Do?",
            "authors": [
                "Monish Keswani",
                " Sriranjani Ramakrishnan",
                " Nishant Reddy",
                " Vineeth N Balasubramanian"
            ]
        },
        {
            "paperId": "7606",
            "posterId": "224b",
            "title": "Do Explanations Explain? Model Knows Best",
            "authors": [
                "Ashkan Khakzar",
                " Pedram Khorsandi",
                " Rozhin Nobahari",
                " Nassir Navab"
            ]
        },
        {
            "paperId": "7668",
            "posterId": "225b",
            "title": "HINT: Hierarchical Neuron Concept Explainer",
            "authors": [
                "Andong Wang",
                " Wei-Ning Lee",
                " Xiaojuan Qi"
            ]
        },
        {
            "paperId": "7825",
            "posterId": "226b",
            "title": "Deformable ProtoPNet: An Interpretable Image Classifier Using Deformable Prototypes",
            "authors": [
                "Jon Donnelly",
                " Alina Jade Barnett",
                " Chaofan Chen"
            ]
        },
        {
            "paperId": "7404",
            "posterId": "227b",
            "title": "What Do Navigation Agents Learn About Their Environment?",
            "authors": [
                "Kshitij Dwivedi",
                " Gemma Roig",
                " Aniruddha Kembhavi",
                " Roozbeh Mottaghi"
            ]
        },
        {
            "paperId": "11789",
            "posterId": "228b",
            "title": "A Framework for Learning Ante-Hoc Explainable Models via Concepts",
            "authors": [
                "Anirban Sarkar",
                " Deepak Vijaykeerthy",
                " Anindya Sarkar",
                " Vineeth N Balasubramanian"
            ]
        },
        {
            "paperId": "778",
            "posterId": "229b",
            "title": "Exploiting Explainable Metrics for Augmented SGD",
            "authors": [
                "Mahdi S. Hosseini",
                " Mathieu Tuli",
                " Konstantinos N. Plataniotis"
            ]
        },
        {
            "paperId": "8195",
            "posterId": "230b",
            "title": "FAM: Visual Explanations for the Feature Representations From Deep Convolutional Networks",
            "authors": [
                "Yuxi Wu",
                " Changhuai Chen",
                " Jun Che",
                " Shiliang Pu"
            ]
        },
        {
            "paperId": "10710",
            "posterId": "231b",
            "title": "Interactive Disentanglement: Learning Concepts by Interacting With Their Prototype Representations",
            "authors": [
                "Wolfgang Stammer",
                " Marius Memmel",
                " Patrick Schramowski",
                " Kristian Kersting"
            ]
        },
        {
            "paperId": "6365",
            "posterId": "232b",
            "title": "B-Cos Networks: Alignment Is All We Need for Interpretability",
            "authors": [
                "Moritz Böhle",
                " Mario Fritz",
                " Bernt Schiele"
            ]
        },
        {
            "paperId": "4303",
            "posterId": "233b",
            "title": "The Flag Median and FlagIRLS",
            "authors": [
                "Nathan Mankovich",
                " Emily J. King",
                " Chris Peterson",
                " Michael Kirby"
            ]
        }
    ],
    "Transparency, Fairness, Accountability, Privacy & Ethics in Vision": [
        {
            "paperId": "112",
            "posterId": "234b",
            "title": "Learning Fair Classifiers With Partially Annotated Group Labels",
            "authors": [
                "Sangwon Jung",
                " Sanghyuk Chun",
                " Taesup Moon"
            ]
        },
        {
            "paperId": "5065",
            "posterId": "235b",
            "title": "Estimating Structural Disparities for Face Models",
            "authors": [
                "Shervin Ardeshir",
                " Cristina Segalin",
                " Nathan Kallus"
            ]
        },
        {
            "paperId": "6022",
            "posterId": "236b",
            "title": "Estimating Example Difficulty Using Variance of Gradients",
            "authors": [
                "Chirag Agarwal",
                " Daniel D'souza",
                " Sara Hooker"
            ]
        },
        {
            "paperId": "6962",
            "posterId": "237b",
            "title": "Fairness-Aware Adversarial Perturbation Towards Bias Mitigation for Deployed Deep Models",
            "authors": [
                "Zhibo Wang",
                " Xiaowei Dong",
                " Henry Xue",
                " Zhifei Zhang",
                " Weifeng Chiu",
                " Tao Wei",
                " Kui Ren"
            ]
        },
        {
            "paperId": "9906",
            "posterId": "238b",
            "title": "Fair Contrastive Learning for Facial Attribute Classification",
            "authors": [
                "Sungho Park",
                " Jewook Lee",
                " Pilhyeon Lee",
                " Sunhee Hwang",
                " Dohyung Kim",
                " Hyeran Byun"
            ]
        },
        {
            "paperId": "6582",
            "posterId": "239b",
            "title": "Leveraging Adversarial Examples To Quantify Membership Information Leakage",
            "authors": [
                "Ganesh Del Grosso",
                " Hamid Jalalzai",
                " Georg Pichler",
                " Catuscia Palamidessi",
                " Pablo Piantanida"
            ]
        },
        {
            "paperId": "10915",
            "posterId": "240b",
            "title": "Leveling Down in Computer Vision: Pareto Inefficiencies in Fair Deep Classifiers",
            "authors": [
                "Dominik Zietlow",
                " Michael Lohaus",
                " Guha Balakrishnan",
                " Matthäus Kleindessner",
                " Francesco Locatello",
                " Bernhard Schölkopf",
                " Chris Russell"
            ]
        },
        {
            "paperId": "11713",
            "posterId": "241b",
            "title": "Deep Unlearning via Randomized Conditionally Independent Hessians",
            "authors": [
                "Ronak Mehta",
                " Sourav Pal",
                " Vikas Singh",
                " Sathya N. Ravi"
            ]
        },
        {
            "paperId": "284",
            "posterId": "242b",
            "title": "Equivariance Allows Handling Multiple Nuisance Variables When Analyzing Pooled Neuroimaging Datasets",
            "authors": [
                "Vishnu Suresh Lokhande",
                " Rudrasis Chakraborty",
                " Sathya N. Ravi",
                " Vikas Singh"
            ]
        },
        {
            "paperId": "11071",
            "posterId": "243b",
            "title": "A Study on the Distribution of Social Biases in Self-Supervised Learning Visual Models",
            "authors": [
                "Kirill Sirotkin",
                " Pablo Carballeira",
                " Marcos Escudero-Viñolo"
            ]
        }
    ],
    "Vision & X": [
        {
            "paperId": "2658",
            "posterId": "244b",
            "title": "Cross-Modal Perceptionist: Can Face Geometry Be Gleaned From Voices?",
            "authors": [
                "Cho-Ying Wu",
                " Chin-Cheng Hsu",
                " Ulrich Neumann"
            ]
        },
        {
            "paperId": "649",
            "posterId": "245b",
            "title": "Learning Hierarchical Cross-Modal Association for Co-Speech Gesture Generation",
            "authors": [
                "Xian Liu",
                " Qianyi Wu",
                " Hang Zhou",
                " Yinghao Xu",
                " Rui Qian",
                " Xinyi Lin",
                " Xiaowei Zhou",
                " Wayne Wu",
                " Bo Dai",
                " Bolei Zhou"
            ]
        },
        {
            "paperId": "2266",
            "posterId": "246b",
            "title": "SEEG: Semantic Energized Co-Speech Gesture Generation",
            "authors": [
                "Yuanzhi Liang",
                " Qianyu Feng",
                " Linchao Zhu",
                " Li Hu",
                " Pan Pan",
                " Yi Yang"
            ]
        },
        {
            "paperId": "715",
            "posterId": "247b",
            "title": "Mix and Localize: Localizing Sound Sources in Mixtures",
            "authors": [
                "Xixi Hu",
                " Ziyang Chen",
                " Andrew Owens"
            ]
        },
        {
            "paperId": "2204",
            "posterId": "248b",
            "title": "Reading To Listen at the Cocktail Party: Multi-Modal Speech Separation",
            "authors": [
                "Akam Rahimi",
                " Triantafyllos Afouras",
                " Andrew Zisserman"
            ]
        },
        {
            "paperId": "7217",
            "posterId": "249b",
            "title": "IntentVizor: Towards Generic Query Guided Interactive Video Summarization",
            "authors": [
                "Guande Wu",
                " Jianzhe Lin",
                " Claudio T. Silva"
            ]
        },
        {
            "paperId": "11551",
            "posterId": "250b",
            "title": "M3L: Language-Based Video Editing via Multi-Modal Multi-Level Transformers",
            "authors": [
                "Tsu-Jui Fu",
                " Xin Eric Wang",
                " Scott T. Grafton",
                " Miguel P. Eckstein",
                " William Yang Wang"
            ]
        },
        {
            "paperId": "5355",
            "posterId": "251b",
            "title": "Finding Fallen Objects via Asynchronous Audio-Visual Integration",
            "authors": [
                "Chuang Gan",
                " Yi Gu",
                " Siyuan Zhou",
                " Jeremy Schwartz",
                " Seth Alter",
                " James Traer",
                " Dan Gutfreund",
                " Joshua B. Tenenbaum",
                " Josh H. McDermott",
                " Antonio Torralba"
            ]
        },
        {
            "paperId": "6187",
            "posterId": "252b",
            "title": "Weakly Paired Associative Learning for Sound and Image Representations via Bimodal Associative Memory",
            "authors": [
                "Sangmin Lee",
                " Hyung-Il Kim",
                " Yong Man Ro"
            ]
        },
        {
            "paperId": "6676",
            "posterId": "253b",
            "title": "Egocentric Deep Multi-Channel Audio-Visual Active Speaker Localization",
            "authors": [
                "Hao Jiang",
                " Calvin Murdock",
                " Vamsi Krishna Ithapu"
            ]
        },
        {
            "paperId": "10849",
            "posterId": "254b",
            "title": "Audio-Visual Generalised Zero-Shot Learning With Cross-Modal Attention and Language",
            "authors": [
                "Otniel-Bogdan Mercea",
                " Lukas Riesch",
                " A. Sophia Koepke",
                " Zeynep Akata"
            ]
        },
        {
            "paperId": "11001",
            "posterId": "255b",
            "title": "It's Time for Artistic Correspondence in Music and Video",
            "authors": [
                "Dídac Surís",
                " Carl Vondrick",
                " Bryan Russell",
                " Justin Salamon"
            ]
        },
        {
            "paperId": "11391",
            "posterId": "256b",
            "title": "Self-Supervised Object Detection From Audio-Visual Correspondence",
            "authors": [
                "Triantafyllos Afouras",
                " Yuki M. Asano",
                " Francois Fagan",
                " Andrea Vedaldi",
                " Florian Metze"
            ]
        },
        {
            "paperId": "8361",
            "posterId": "257b",
            "title": "More Than Words: In-the-Wild Visually-Driven Prosody for Text-to-Speech",
            "authors": [
                "Michael Hassid",
                " Michelle Tadmor Ramanovich",
                " Brendan Shillingford",
                " Miaosen Wang",
                " Ye Jia",
                " Tal Remez"
            ]
        },
        {
            "paperId": "2475",
            "posterId": "258b",
            "title": "ObjectFolder 2.0: A Multisensory Object Dataset for Sim2Real Transfer",
            "authors": [
                "Ruohan Gao",
                " Zilin Si",
                " Yen-Yu Chang",
                " Samuel Clarke",
                " Jeannette Bohg",
                " Li Fei-Fei",
                " Wenzhen Yuan",
                " Jiajun Wu"
            ]
        },
        {
            "paperId": "7892",
            "posterId": "259b",
            "title": "A Probabilistic Graphical Model Based on Neural-Symbolic Reasoning for Visual Relationship Detection",
            "authors": [
                "Dongran Yu",
                " Bo Yang",
                " Qianhao Wei",
                " Anchen Li",
                " Shirui Pan"
            ]
        }
    ],
    "Image & Video Synthesis and Generation (I)": [
        {
            "paperId": "4818",
            "posterId": "1a",
            "title": "Diffusion Autoencoders: Toward a Meaningful and Decodable Representation",
            "authors": [
                "Konpat Preechakul",
                " Nattanat Chatthee",
                " Suttisak Wizadwongsa",
                " Supasorn Suwajanakorn"
            ]
        },
        {
            "paperId": "6519",
            "posterId": "2a",
            "title": "Polymorphic-GAN: Generating Aligned Samples Across Multiple Domains With Learned Morph Maps",
            "authors": [
                "Seung Wook Kim",
                " Karsten Kreis",
                " Daiqing Li",
                " Antonio Torralba",
                " Sanja Fidler"
            ]
        },
        {
            "paperId": "11253",
            "posterId": "3a",
            "title": "Polarity Sampling: Quality and Diversity Control of Pre-Trained Generative Networks via Singular Values",
            "authors": [
                "Ahmed Imtiaz Humayun",
                " Randall Balestriero",
                " Richard Baraniuk"
            ]
        },
        {
            "paperId": "908",
            "posterId": "4a",
            "title": "Ensembling Off-the-Shelf Models for GAN Training",
            "authors": [
                "Nupur Kumari",
                " Richard Zhang",
                " Eli Shechtman",
                " Jun-Yan Zhu"
            ]
        },
        {
            "paperId": "10490",
            "posterId": "5a",
            "title": "Marginal Contrastive Correspondence for Guided Image Generation",
            "authors": [
                "Fangneng Zhan",
                " Yingchen Yu",
                " Rongliang Wu",
                " Jiahui Zhang",
                " Shijian Lu",
                " Changgong Zhang"
            ]
        },
        {
            "paperId": "3437",
            "posterId": "6a",
            "title": "GRAM: Generative Radiance Manifolds for 3D-Aware Image Generation",
            "authors": [
                "Yu Deng",
                " Jiaolong Yang",
                " Jianfeng Xiang",
                " Xin Tong"
            ]
        },
        {
            "paperId": "5452",
            "posterId": "7a",
            "title": "High-Resolution Image Synthesis With Latent Diffusion Models",
            "authors": [
                "Robin Rombach",
                " Andreas Blattmann",
                " Dominik Lorenz",
                " Patrick Esser",
                " Björn Ommer"
            ]
        },
        {
            "paperId": "3874",
            "posterId": "8a",
            "title": "Vector Quantized Diffusion Model for Text-to-Image Synthesis",
            "authors": [
                "Shuyang Gu",
                " Dong Chen",
                " Jianmin Bao",
                " Fang Wen",
                " Bo Zhang",
                " Dongdong Chen",
                " Lu Yuan",
                " Baining Guo"
            ]
        },
        {
            "paperId": "5265",
            "posterId": "9a",
            "title": "ManiTrans: Entity-Level Text-Guided Image Manipulation via Token-Wise Semantic Alignment and Generation",
            "authors": [
                "Jianan Wang",
                " Guansong Lu",
                " Hang Xu",
                " Zhenguo Li",
                " Chunjing Xu",
                " Yanwei Fu"
            ]
        },
        {
            "paperId": "790",
            "posterId": "10a",
            "title": "Dataset Distillation by Matching Training Trajectories",
            "authors": [
                "George Cazenavette",
                " Tongzhou Wang",
                " Antonio Torralba",
                " Alexei A. Efros",
                " Jun-Yan Zhu"
            ]
        },
        {
            "paperId": "6337",
            "posterId": "11a",
            "title": "Continual Predictive Learning From Videos",
            "authors": [
                "Geng Chen",
                " Wendong Zhang",
                " Han Lu",
                " Siyu Gao",
                " Yunbo Wang",
                " Mingsheng Long",
                " Xiaokang Yang"
            ]
        },
        {
            "paperId": "11474",
            "posterId": "12a",
            "title": "Motion-Adjustable Neural Implicit Video Representation",
            "authors": [
                "Long Mai",
                " Feng Liu"
            ]
        },
        {
            "paperId": "2561",
            "posterId": "13a",
            "title": "Splicing ViT Features for Semantic Appearance Transfer",
            "authors": [
                "Narek Tumanyan",
                " Omer Bar-Tal",
                " Shai Bagon",
                " Tali Dekel"
            ]
        },
        {
            "paperId": "1064",
            "posterId": "14a",
            "title": "MAT: Mask-Aware Transformer for Large Hole Image Inpainting",
            "authors": [
                "Wenbo Li",
                " Zhe Lin",
                " Kun Zhou",
                " Lu Qi",
                " Yi Wang",
                " Jiaya Jia"
            ]
        },
        {
            "paperId": "2344",
            "posterId": "15a",
            "title": "Day-to-Night Image Synthesis for Training Nighttime Neural ISPs",
            "authors": [
                "Abhijith Punnappurath",
                " Abdullah Abuolaim",
                " Abdelrahman Abdelhamed",
                " Alex Levinshtein",
                " Michael S. Brown"
            ]
        },
        {
            "paperId": "5874",
            "posterId": "16a",
            "title": "Smooth-Swap: A Simple Enhancement for Face-Swapping With Smoothness",
            "authors": [
                "Jiseob Kim",
                " Jihoon Lee",
                " Byoung-Tak Zhang"
            ]
        },
        {
            "paperId": "3576",
            "posterId": "17a",
            "title": "Few-Shot Head Swapping in the Wild",
            "authors": [
                "Changyong Shu",
                " Hemao Wu",
                " Hang Zhou",
                " Jiaming Liu",
                " Zhibin Hong",
                " Changxing Ding",
                " Junyu Han",
                " Jingtuo Liu",
                " Errui Ding",
                " Jingdong Wang"
            ]
        },
        {
            "paperId": "5059",
            "posterId": "18a",
            "title": "ClothFormer: Taming Video Virtual Try-On in All Module",
            "authors": [
                "Jianbin Jiang",
                " Tan Wang",
                " He Yan",
                " Junhui Liu"
            ]
        }
    ],
    "Human Pose Estimation & Tracking, Localization, and Object Pose Estimation": [
        {
            "paperId": "4380",
            "posterId": "37a",
            "title": "Adversarial Parametric Pose Prior",
            "authors": [
                "Andrey Davydov",
                " Anastasia Remizova",
                " Victor Constantin",
                " Sina Honari",
                " Mathieu Salzmann",
                " Pascal Fua"
            ]
        },
        {
            "paperId": "4450",
            "posterId": "38a",
            "title": "Temporal Feature Alignment and Mutual Information Maximization for Video-Based Human Pose Estimation",
            "authors": [
                "Zhenguang Liu",
                " Runyang Feng",
                " Haoming Chen",
                " Shuang Wu",
                " Yixing Gao",
                " Yunjun Gao",
                " Xiang Wang"
            ]
        },
        {
            "paperId": "4806",
            "posterId": "39a",
            "title": "PoseTriplet: Co-Evolving 3D Human Pose Estimation, Imitation, and Hallucination Under Self-Supervision",
            "authors": [
                "Kehong Gong",
                " Bingbing Li",
                " Jianfeng Zhang",
                " Tao Wang",
                " Jing Huang",
                " Michael Bi Mi",
                " Jiashi Feng",
                " Xinchao Wang"
            ]
        },
        {
            "paperId": "2492",
            "posterId": "40a",
            "title": "Generalizable Human Pose Triangulation",
            "authors": [
                "Kristijan Bartol",
                " David Bojanić",
                " Tomislav Petković",
                " Tomislav Pribanić"
            ]
        },
        {
            "paperId": "1181",
            "posterId": "41a",
            "title": "GLAMR: Global Occlusion-Aware Human Mesh Recovery With Dynamic Cameras",
            "authors": [
                "Ye Yuan",
                " Umar Iqbal",
                " Pavlo Molchanov",
                " Kris Kitani",
                " Jan Kautz"
            ]
        },
        {
            "paperId": "1468",
            "posterId": "42a",
            "title": "Bailando: 3D Dance Generation by Actor-Critic GPT With Choreographic Memory",
            "authors": [
                "Li Siyao",
                " Weijiang Yu",
                " Tianpei Gu",
                " Chunze Lin",
                " Quan Wang",
                " Chen Qian",
                " Chen Change Loy",
                " Ziwei Liu"
            ]
        },
        {
            "paperId": "4014",
            "posterId": "43a",
            "title": "Contextual Instance Decoupling for Robust Multi-Person Pose Estimation",
            "authors": [
                "Dongkai Wang",
                " Shiliang Zhang"
            ]
        },
        {
            "paperId": "2202",
            "posterId": "44a",
            "title": "End-to-End Multi-Person Pose Estimation With Transformers",
            "authors": [
                "Dahu Shi",
                " Xing Wei",
                " Liangqi Li",
                " Ye Ren",
                " Wenming Tan"
            ]
        },
        {
            "paperId": "4534",
            "posterId": "45a",
            "title": "Meta Agent Teaming Active Learning for Pose Estimation",
            "authors": [
                "Jia Gong",
                " Zhipeng Fan",
                " Qiuhong Ke",
                " Hossein Rahmani",
                " Jun Liu"
            ]
        },
        {
            "paperId": "3411",
            "posterId": "46a",
            "title": "Keypoint Transformer: Solving Joint Identification in Challenging Hands and Object Interactions for Accurate 3D Pose Estimation",
            "authors": [
                "Shreyas Hampali",
                " Sayan Deb Sarkar",
                " Mahdi Rad",
                " Vincent Lepetit"
            ]
        },
        {
            "paperId": "6194",
            "posterId": "47a",
            "title": "Not All Tokens Are Equal: Human-Centric Visual Analysis via Token Clustering Transformer",
            "authors": [
                "Wang Zeng",
                " Sheng Jin",
                " Wentao Liu",
                " Chen Qian",
                " Ping Luo",
                " Wanli Ouyang",
                " Xiaogang Wang"
            ]
        },
        {
            "paperId": "8628",
            "posterId": "48a",
            "title": "Occlusion-Robust Face Alignment Using a Viewpoint-Invariant Hierarchical Network Architecture",
            "authors": [
                "Congcong Zhu",
                " Xintong Wan",
                " Shaorong Xie",
                " Xiaoqiang Li",
                " Yinzheng Gu"
            ]
        },
        {
            "paperId": "1445",
            "posterId": "49a",
            "title": "LASER: LAtent SpacE Rendering for 2D Visual Localization",
            "authors": [
                "Zhixiang Min",
                " Naji Khosravan",
                " Zachary Bessinger",
                " Manjunath Narayana",
                " Sing Bing Kang",
                " Enrique Dunn",
                " Ivaylo Boyadzhiev"
            ]
        },
        {
            "paperId": "8152",
            "posterId": "50a",
            "title": "Learning To Detect Scene Landmarks for Camera Localization",
            "authors": [
                "Tien Do",
                " Ondrej Miksik",
                " Joseph DeGol",
                " Hyun Soo Park",
                " Sudipta N. Sinha"
            ]
        },
        {
            "paperId": "4196",
            "posterId": "51a",
            "title": "Geometric Transformer for Fast and Robust Point Cloud Registration",
            "authors": [
                "Zheng Qin",
                " Hao Yu",
                " Changjian Wang",
                " Yulan Guo",
                " Yuxing Peng",
                " Kai Xu"
            ]
        },
        {
            "paperId": "7968",
            "posterId": "52a",
            "title": "ARCS: Accurate Rotation and Correspondence Search",
            "authors": [
                "Liangzu Peng",
                " Manolis C. Tsakiris",
                " René Vidal"
            ]
        },
        {
            "paperId": "3628",
            "posterId": "53a",
            "title": "FisherMatch: Semi-Supervised Rotation Regression via Entropy-Based Filtering",
            "authors": [
                "Yingda Yin",
                " Yingcheng Cai",
                " He Wang",
                " Baoquan Chen"
            ]
        },
        {
            "paperId": "10439",
            "posterId": "54a",
            "title": "Uni6D: A Unified CNN Framework Without Projection Breakdown for 6D Pose Estimation",
            "authors": [
                "Xiaoke Jiang",
                " Donghai Li",
                " Hao Chen",
                " Ye Zheng",
                " Rui Zhao",
                " Liwei Wu"
            ]
        }
    ],
    "Efficient Learning & Inference": [
        {
            "paperId": "5660",
            "posterId": "153a",
            "title": "CAFE: Learning To Condense Dataset by Aligning Features",
            "authors": [
                "Kai Wang",
                " Bo Zhao",
                " Xiangyu Peng",
                " Zheng Zhu",
                " Shuo Yang",
                " Shuo Wang",
                " Guan Huang",
                " Hakan Bilen",
                " Xinchao Wang",
                " Yang You"
            ]
        },
        {
            "paperId": "9135",
            "posterId": "154a",
            "title": "Lite-MDETR: A Lightweight Multi-Modal Detector",
            "authors": [
                "Qian Lou",
                " Yen-Chang Hsu",
                " Burak Uzkent",
                " Ting Hua",
                " Yilin Shen",
                " Hongxia Jin"
            ]
        },
        {
            "paperId": "703",
            "posterId": "155a",
            "title": "DeeCap: Dynamic Early Exiting for Efficient Image Captioning",
            "authors": [
                "Zhengcong Fei",
                " Xu Yan",
                " Shuhui Wang",
                " Qi Tian"
            ]
        },
        {
            "paperId": "10864",
            "posterId": "156a",
            "title": "Searching the Deployable Convolution Neural Networks for GPUs",
            "authors": [
                "Linnan Wang",
                " Chenhan Yu",
                " Satish Salian",
                " Slawomir Kierat",
                " Szymon Migacz",
                " Alex Fit Florea"
            ]
        },
        {
            "paperId": "6685",
            "posterId": "157a",
            "title": "Active Learning by Feature Mixing",
            "authors": [
                "Amin Parvaneh",
                " Ehsan Abbasnejad",
                " Damien Teney",
                " Gholamreza (Reza) Haffari",
                " Anton van den Hengel",
                " Javen Qinfeng Shi"
            ]
        },
        {
            "paperId": "6585",
            "posterId": "158a",
            "title": "When To Prune? A Policy Towards Early Structural Pruning",
            "authors": [
                "Maying Shen",
                " Pavlo Molchanov",
                " Hongxu Yin",
                " Jose M. Alvarez"
            ]
        },
        {
            "paperId": "11185",
            "posterId": "159a",
            "title": "Contrastive Dual Gating: Learning Sparse Features With Contrastive Learning",
            "authors": [
                "Jian Meng",
                " Li Yang",
                " Jinwoo Shin",
                " Deliang Fan",
                " Jae-sun Seo"
            ]
        },
        {
            "paperId": "9318",
            "posterId": "160a",
            "title": "How Well Do Sparse ImageNet Models Transfer?",
            "authors": [
                "Eugenia Iofinova",
                " Alexandra Peste",
                " Mark Kurtz",
                " Dan Alistarh"
            ]
        },
        {
            "paperId": "9388",
            "posterId": "161a",
            "title": "Rep-Net: Efficient On-Device Learning via Feature Reprogramming",
            "authors": [
                "Li Yang",
                " Adnan Siraj Rakin",
                " Deliang Fan"
            ]
        },
        {
            "paperId": "4954",
            "posterId": "162a",
            "title": "CHEX: CHannel EXploration for CNN Model Compression",
            "authors": [
                "Zejiang Hou",
                " Minghai Qin",
                " Fei Sun",
                " Xiaolong Ma",
                " Kun Yuan",
                " Yi Xu",
                " Yen-Kuang Chen",
                " Rong Jin",
                " Yuan Xie",
                " Sun-Yuan Kung"
            ]
        },
        {
            "paperId": "3533",
            "posterId": "163a",
            "title": "HODEC: Towards Efficient High-Order DEcomposed Convolutional Neural Networks",
            "authors": [
                "Miao Yin",
                " Yang Sui",
                " Wanzhao Yang",
                " Xiao Zang",
                " Yu Gong",
                " Bo Yuan"
            ]
        },
        {
            "paperId": "2934",
            "posterId": "164a",
            "title": "AdaViT: Adaptive Vision Transformers for Efficient Image Recognition",
            "authors": [
                "Lingchen Meng",
                " Hengduo Li",
                " Bor-Chun Chen",
                " Shiyi Lan",
                " Zuxuan Wu",
                " Yu-Gang Jiang",
                " Ser-Nam Lim"
            ]
        },
        {
            "paperId": "1772",
            "posterId": "165a",
            "title": "Cross-Image Relational Knowledge Distillation for Semantic Segmentation",
            "authors": [
                "Chuanguang Yang",
                " Helong Zhou",
                " Zhulin An",
                " Xue Jiang",
                " Yongjun Xu",
                " Qian Zhang"
            ]
        },
        {
            "paperId": "724",
            "posterId": "166a",
            "title": "Mr.BiQ: Post-Training Non-Uniform Quantization Based on Minimizing the Reconstruction Error",
            "authors": [
                "Yongkweon Jeon",
                " Chungman Lee",
                " Eulrang Cho",
                " Yeonju Ro"
            ]
        },
        {
            "paperId": "3958",
            "posterId": "167a",
            "title": "IntraQ: Learning Synthetic Images With Intra-Class Heterogeneity for Zero-Shot Network Quantization",
            "authors": [
                "Yunshan Zhong",
                " Mingbao Lin",
                " Gongrui Nan",
                " Jianzhuang Liu",
                " Baochang Zhang",
                " Yonghong Tian",
                " Rongrong Ji"
            ]
        },
        {
            "paperId": "9796",
            "posterId": "168a",
            "title": "DECORE: Deep Compression With Reinforcement Learning",
            "authors": [
                "Manoj Alwani",
                " Yang Wang",
                " Vashisht Madhavan"
            ]
        },
        {
            "paperId": "11195",
            "posterId": "169a",
            "title": "Towards Efficient and Scalable Sharpness-Aware Minimization",
            "authors": [
                "Yong Liu",
                " Siqi Mai",
                " Xiangning Chen",
                " Cho-Jui Hsieh",
                " Yang You"
            ]
        },
        {
            "paperId": "1088",
            "posterId": "170a",
            "title": "AEGNN: Asynchronous Event-Based Graph Neural Networks",
            "authors": [
                "Simon Schaefer",
                " Daniel Gehrig",
                " Davide Scaramuzza"
            ]
        },
        {
            "paperId": "4078",
            "posterId": "171a",
            "title": "DiSparse: Disentangled Sparsification for Multitask Model Compression",
            "authors": [
                "Xinglong Sun",
                " Ali Hassani",
                " Zhangyang Wang",
                " Gao Huang",
                " Humphrey Shi"
            ]
        },
        {
            "paperId": "1836",
            "posterId": "172a",
            "title": "Multi-Modal Extreme Classification",
            "authors": [
                "Anshul Mittal",
                " Kunal Dahiya",
                " Shreya Malani",
                " Janani Ramaswamy",
                " Seba Kuruvilla",
                " Jitendra Ajmera",
                " Keng-hao Chang",
                " Sumeet Agarwal",
                " Purushottam Kar",
                " Manik Varma"
            ]
        },
        {
            "paperId": "11241",
            "posterId": "173a",
            "title": "A Sampling-Based Approach for Efficient Clustering in Large Datasets",
            "authors": [
                "Georgios Exarchakis",
                " Omar Oubari",
                " Gregor Lenz"
            ]
        },
        {
            "paperId": "11776",
            "posterId": "174a",
            "title": "Come-Closer-Diffuse-Faster: Accelerating Conditional Diffusion Models for Inverse Problems Through Stochastic Contraction",
            "authors": [
                "Hyungjin Chung",
                " Byeongsu Sim",
                " Jong Chul Ye"
            ]
        },
        {
            "paperId": "6380",
            "posterId": "175a",
            "title": "Learnable Lookup Table for Neural Network Quantization",
            "authors": [
                "Longguang Wang",
                " Xiaoyu Dong",
                " Yingqian Wang",
                " Li Liu",
                " Wei An",
                " Yulan Guo"
            ]
        },
        {
            "paperId": "8374",
            "posterId": "176a",
            "title": "Instance-Aware Dynamic Neural Network Quantization",
            "authors": [
                "Zhenhua Liu",
                " Yunhe Wang",
                " Kai Han",
                " Siwei Ma",
                " Wen Gao"
            ]
        },
        {
            "paperId": "10529",
            "posterId": "177a",
            "title": "Training High-Performance Low-Latency Spiking Neural Networks by Differentiation on Spike Representation",
            "authors": [
                "Qingyan Meng",
                " Mingqing Xiao",
                " Shen Yan",
                " Yisen Wang",
                " Zhouchen Lin",
                " Zhi-Quan Luo"
            ]
        },
        {
            "paperId": "3265",
            "posterId": "178a",
            "title": "Fire Together Wire Together: A Dynamic Pruning Approach With Self-Supervised Mask Prediction",
            "authors": [
                "Sara Elkerdawy",
                " Mostafa Elhoushi",
                " Hong Zhang",
                " Nilanjan Ray"
            ]
        },
        {
            "paperId": "5233",
            "posterId": "179a",
            "title": "Wavelet Knowledge Distillation: Towards Efficient Image-to-Image Translation",
            "authors": [
                "Linfeng Zhang",
                " Xin Chen",
                " Xiaobing Tu",
                " Pengfei Wan",
                " Ning Xu",
                " Kaisheng Ma"
            ]
        },
        {
            "paperId": "11646",
            "posterId": "180a",
            "title": "PokeBNN: A Binary Pursuit of Lightweight Accuracy",
            "authors": [
                "Yichi Zhang",
                " Zhiru Zhang",
                " Lukasz Lew"
            ]
        },
        {
            "paperId": "2031",
            "posterId": "181a",
            "title": "Automated Progressive Learning for Efficient Training of Vision Transformers",
            "authors": [
                "Changlin Li",
                " Bohan Zhuang",
                " Guangrun Wang",
                " Xiaodan Liang",
                " Xiaojun Chang",
                " Yi Yang"
            ]
        },
        {
            "paperId": "1417",
            "posterId": "182a",
            "title": "DeltaCNN: End-to-End CNN Inference of Sparse Frame Differences in Videos",
            "authors": [
                "Mathias Parger",
                " Chengcheng Tang",
                " Christopher D. Twigg",
                " Cem Keskin",
                " Robert Wang",
                " Markus Steinberger"
            ]
        },
        {
            "paperId": "9190",
            "posterId": "183a",
            "title": "Channel Balancing for Accurate Quantization of Winograd Convolutions",
            "authors": [
                "Vladimir Chikin",
                " Vladimir Kryzhanovskiy"
            ]
        },
        {
            "paperId": "9054",
            "posterId": "184a",
            "title": "ClusterGNN: Cluster-Based Coarse-To-Fine Graph Neural Network for Efficient Feature Matching",
            "authors": [
                "Yan Shi",
                " Jun-Xiong Cai",
                " Yoli Shavit",
                " Tai-Jiang Mu",
                " Wensen Feng",
                " Kai Zhang"
            ]
        },
        {
            "paperId": "8230",
            "posterId": "185a",
            "title": "Interspace Pruning: Using Adaptive Filter Representations To Improve Training of Sparse CNNs",
            "authors": [
                "Paul Wimmer",
                " Jens Mehnert",
                " Alexandru Condurache"
            ]
        },
        {
            "paperId": "4843",
            "posterId": "186a",
            "title": "AlignQ: Alignment Quantization With ADMM-Based Correlation Preservation",
            "authors": [
                "Ting-An Chen",
                " De-Nian Yang",
                " Ming-Syan Chen"
            ]
        },
        {
            "paperId": "9210",
            "posterId": "187a",
            "title": "TVConv: Efficient Translation Variant Convolution for Layout-Aware Visual Processing",
            "authors": [
                "Jierun Chen",
                " Tianlang He",
                " Weipeng Zhuo",
                " Li Ma",
                " Sangtae Ha",
                " S.-H. Gary Chan"
            ]
        },
        {
            "paperId": "185",
            "posterId": "188a",
            "title": "SplitNets: Designing Neural Architectures for Efficient Distributed Computing on Head-Mounted Systems",
            "authors": [
                "Xin Dong",
                " Barbara De Salvo",
                " Meng Li",
                " Chiao Liu",
                " Zhongnan Qu",
                " H.T. Kung",
                " Ziyun Li"
            ]
        },
        {
            "paperId": "6367",
            "posterId": "189a",
            "title": "TO-FLOW: Efficient Continuous Normalizing Flows With Temporal Optimization Adjoint With Moving Speed",
            "authors": [
                "Shian Du",
                " Yihong Luo",
                " Wei Chen",
                " Jian Xu",
                " Delu Zeng"
            ]
        }
    ],
    "Physics-Based Vision and Shape-From-X": [
        {
            "paperId": "793",
            "posterId": "190a",
            "title": "DiLiGenT102: A Photometric Stereo Benchmark Dataset With Controlled Shape and Material Variation",
            "authors": [
                "Jieji Ren",
                " Feishi Wang",
                " Jiahao Zhang",
                " Qian Zheng",
                " Mingjun Ren",
                " Boxin Shi"
            ]
        },
        {
            "paperId": "1453",
            "posterId": "191a",
            "title": "Universal Photometric Stereo Network Using Global Lighting Contexts",
            "authors": [
                "Satoshi Ikehata"
            ]
        },
        {
            "paperId": "2355",
            "posterId": "192a",
            "title": "Uncertainty-Aware Deep Multi-View Photometric Stereo",
            "authors": [
                "Berk Kaya",
                " Suryansh Kumar",
                " Carlos Oliveira",
                " Vittorio Ferrari",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "5441",
            "posterId": "193a",
            "title": "Fast Light-Weight Near-Field Photometric Stereo",
            "authors": [
                "Daniel Lichy",
                " Soumyadip Sengupta",
                " David W. Jacobs"
            ]
        },
        {
            "paperId": "4990",
            "posterId": "194a",
            "title": "Glass Segmentation Using Intensity and Spectral Polarization Cues",
            "authors": [
                "Haiyang Mei",
                " Bo Dong",
                " Wen Dong",
                " Jiaxi Yang",
                " Seung-Hwan Baek",
                " Felix Heide",
                " Pieter Peers",
                " Xiaopeng Wei",
                " Xin Yang"
            ]
        },
        {
            "paperId": "1557",
            "posterId": "195a",
            "title": "Shape From Polarization for Complex Scenes in the Wild",
            "authors": [
                "Chenyang Lei",
                " Chenyang Qi",
                " Jiaxin Xie",
                " Na Fan",
                " Vladlen Koltun",
                " Qifeng Chen"
            ]
        },
        {
            "paperId": "6107",
            "posterId": "196a",
            "title": "Deep Depth From Focus With Differential Focus Volume",
            "authors": [
                "Fengting Yang",
                " Xiaolei Huang",
                " Zihan Zhou"
            ]
        },
        {
            "paperId": "7381",
            "posterId": "197a",
            "title": "Optimal LED Spectral Multiplexing for NIR2RGB Translation",
            "authors": [
                "Lei Liu",
                " Yuze Chen",
                " Junchi Yan",
                " Yinqiang Zheng"
            ]
        },
        {
            "paperId": "8076",
            "posterId": "198a",
            "title": "Shape From Thermal Radiation: Passive Ranging Using Multi-Spectral LWIR Measurements",
            "authors": [
                "Yasuto Nagase",
                " Takahiro Kushida",
                " Kenichiro Tanaka",
                " Takuya Funatomi",
                " Yasuhiro Mukaigawa"
            ]
        },
        {
            "paperId": "8196",
            "posterId": "199a",
            "title": "NAN: Noise-Aware NeRFs for Burst-Denoising",
            "authors": [
                "Naama Pearl",
                " Tali Treibitz",
                " Simon Korman"
            ]
        },
        {
            "paperId": "3129",
            "posterId": "200a",
            "title": "Estimating Fine-Grained Noise Model via Contrastive Learning",
            "authors": [
                "Yunhao Zou",
                " Ying Fu"
            ]
        },
        {
            "paperId": "11094",
            "posterId": "201a",
            "title": "Real-Time Hyperspectral Imaging in Hardware via Trained Metasurface Encoders",
            "authors": [
                "Maksim Makarenko",
                " Arturo Burguete-Lopez",
                " Qizhou Wang",
                " Fedor Getman",
                " Silvio Giancola",
                " Bernard Ghanem",
                " Andrea Fratalocchi"
            ]
        },
        {
            "paperId": "1021",
            "posterId": "202a",
            "title": "MNSRNet: Multimodal Transformer Network for 3D Surface Super-Resolution",
            "authors": [
                "Wuyuan Xie",
                " Tengcong Huang",
                " Miaohui Wang"
            ]
        },
        {
            "paperId": "6350",
            "posterId": "203a",
            "title": "PhyIR: Physics-Based Inverse Rendering for Panoramic Indoor Images",
            "authors": [
                "Zhen Li",
                " Lingli Wang",
                " Xiang Huang",
                " Cihui Pan",
                " Jiaqi Yang"
            ]
        }
    ],
    "Visual Reasoning": [
        {
            "paperId": "10159",
            "posterId": "204a",
            "title": "Neural Shape Mating: Self-Supervised Object Assembly With Adversarial Shape Priors",
            "authors": [
                "Yun-Chun Chen",
                " Haoda Li",
                " Dylan Turpin",
                " Alec Jacobson",
                " Animesh Garg"
            ]
        },
        {
            "paperId": "1531",
            "posterId": "205a",
            "title": "Learning To Anticipate Future With Dynamic Context Removal",
            "authors": [
                "Xinyu Xu",
                " Yong-Lu Li",
                " Cewu Lu"
            ]
        },
        {
            "paperId": "11115",
            "posterId": "206a",
            "title": "Self-Supervised Spatial Reasoning on Multi-View Line Drawings",
            "authors": [
                "Siyuan Xiang",
                " Anbang Yang",
                " Yanfei Xue",
                " Yaoqing Yang",
                " Chen Feng"
            ]
        },
        {
            "paperId": "5634",
            "posterId": "207a",
            "title": "Contextual Debiasing for Visual Recognition With Causal Mechanisms",
            "authors": [
                "Ruyang Liu",
                " Hao Liu",
                " Ge Li",
                " Haodi Hou",
                " TingHao Yu",
                " Tao Yang"
            ]
        }
    ],
    "Security, Transparency, Fairness, Accountability, Privacy & Ethics in Vision": [
        {
            "paperId": "3468",
            "posterId": "1b",
            "title": "Adversarial Texture for Fooling Person Detectors in the Physical World",
            "authors": [
                "Zhanhao Hu",
                " Siyuan Huang",
                " Xiaopei Zhu",
                " Fuchun Sun",
                " Bo Zhang",
                " Xiaolin Hu"
            ]
        },
        {
            "paperId": "4109",
            "posterId": "2b",
            "title": "Infrared Invisible Clothing: Hiding From Infrared Detectors at Multiple Angles in Real World",
            "authors": [
                "Xiaopei Zhu",
                " Zhanhao Hu",
                " Siyuan Huang",
                " Jianmin Li",
                " Xiaolin Hu"
            ]
        },
        {
            "paperId": "5922",
            "posterId": "3b",
            "title": "Enhancing Classifier Conservativeness and Robustness by Polynomiality",
            "authors": [
                "Ziqi Wang",
                " Marco Loog"
            ]
        },
        {
            "paperId": "5448",
            "posterId": "4b",
            "title": "Backdoor Attacks on Self-Supervised Learning",
            "authors": [
                "Aniruddha Saha",
                " Ajinkya Tejankar",
                " Soroush Abbasi Koohpayegani",
                " Hamed Pirsiavash"
            ]
        },
        {
            "paperId": "6583",
            "posterId": "5b",
            "title": "Towards Practical Deployment-Stage Backdoor Attack on Deep Neural Networks",
            "authors": [
                "Xiangyu Qi",
                " Tinghao Xie",
                " Ruizhe Pan",
                " Jifeng Zhu",
                " Yong Yang",
                " Kai Bu"
            ]
        },
        {
            "paperId": "3994",
            "posterId": "6b",
            "title": "Few-Shot Backdoor Defense Using Shapley Estimation",
            "authors": [
                "Jiyang Guan",
                " Zhuozhuo Tu",
                " Ran He",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "10910",
            "posterId": "7b",
            "title": "Better Trigger Inversion Optimization in Backdoor Scanning",
            "authors": [
                "Guanhong Tao",
                " Guangyu Shen",
                " Yingqi Liu",
                " Shengwei An",
                " Qiuling Xu",
                " Shiqing Ma",
                " Pan Li",
                " Xiangyu Zhang"
            ]
        },
        {
            "paperId": "7051",
            "posterId": "8b",
            "title": "Bandits for Structure Perturbation-Based Black-Box Attacks To Graph Neural Networks With Theoretical Guarantees",
            "authors": [
                "Binghui Wang",
                " Youqi Li",
                " Pan Zhou"
            ]
        },
        {
            "paperId": "9002",
            "posterId": "9b",
            "title": "Improving Robustness Against Stealthy Weight Bit-Flip Attacks by Output Code Matching",
            "authors": [
                "Ozan Özdenizci",
                " Robert Legenstein"
            ]
        },
        {
            "paperId": "6908",
            "posterId": "10b",
            "title": "LAS-AT: Adversarial Training With Learnable Attack Strategy",
            "authors": [
                "Xiaojun Jia",
                " Yong Zhang",
                " Baoyuan Wu",
                " Ke Ma",
                " Jue Wang",
                " Xiaochun Cao"
            ]
        },
        {
            "paperId": "4589",
            "posterId": "11b",
            "title": "Subspace Adversarial Training",
            "authors": [
                "Tao Li",
                " Yingwen Wu",
                " Sizhe Chen",
                " Kun Fang",
                " Xiaolin Huang"
            ]
        },
        {
            "paperId": "5403",
            "posterId": "12b",
            "title": "Pyramid Adversarial Training Improves ViT Performance",
            "authors": [
                "Charles Herrmann",
                " Kyle Sargent",
                " Lu Jiang",
                " Ramin Zabih",
                " Huiwen Chang",
                " Ce Liu",
                " Dilip Krishnan",
                " Deqing Sun"
            ]
        },
        {
            "paperId": "12025",
            "posterId": "13b",
            "title": "Fingerprinting Deep Neural Networks Globally via Universal Adversarial Perturbations",
            "authors": [
                "Zirui Peng",
                " Shaofeng Li",
                " Guoxing Chen",
                " Cheng Zhang",
                " Haojin Zhu",
                " Minhui Xue"
            ]
        },
        {
            "paperId": "2245",
            "posterId": "14b",
            "title": "Robust Image Forgery Detection Over Online Social Network Shared Images",
            "authors": [
                "Haiwei Wu",
                " Jiantao Zhou",
                " Jinyu Tian",
                " Jun Liu"
            ]
        },
        {
            "paperId": "6270",
            "posterId": "15b",
            "title": "Quantifying Societal Bias Amplification in Image Captioning",
            "authors": [
                "Yusuke Hirota",
                " Yuta Nakashima",
                " Noa Garcia"
            ]
        }
    ],
    "Image & Video Synthesis and Generation (II); Video Analysis & Understanding": [
        {
            "paperId": "725",
            "posterId": "16b",
            "title": "Drop the GAN: In Defense of Patches Nearest Neighbors As Single Image Generative Models",
            "authors": [
                "Niv Granot",
                " Ben Feinstein",
                " Assaf Shocher",
                " Shai Bagon",
                " Michal Irani"
            ]
        },
        {
            "paperId": "706",
            "posterId": "17b",
            "title": "GAN-Supervised Dense Visual Alignment",
            "authors": [
                "William Peebles",
                " Jun-Yan Zhu",
                " Richard Zhang",
                " Antonio Torralba",
                " Alexei A. Efros",
                " Eli Shechtman"
            ]
        },
        {
            "paperId": "8416",
            "posterId": "18b",
            "title": "Look Closer To Supervise Better: One-Shot Font Generation via Component-Based Discriminator",
            "authors": [
                "Yuxin Kong",
                " Canjie Luo",
                " Weihong Ma",
                " Qiyuan Zhu",
                " Shenggao Zhu",
                " Nicholas Yuan",
                " Lianwen Jin"
            ]
        },
        {
            "paperId": "8925",
            "posterId": "19b",
            "title": "Text2Mesh: Text-Driven Neural Stylization for Meshes",
            "authors": [
                "Oscar Michel",
                " Roi Bar-On",
                " Richard Liu",
                " Sagie Benaim",
                " Rana Hanocka"
            ]
        },
        {
            "paperId": "6649",
            "posterId": "20b",
            "title": "StyleSDF: High-Resolution 3D-Consistent Image and Geometry Generation",
            "authors": [
                "Roy Or-El",
                " Xuan Luo",
                " Mengyi Shan",
                " Eli Shechtman",
                " Jeong Joon Park",
                " Ira Kemelmacher-Shlizerman"
            ]
        },
        {
            "paperId": "7720",
            "posterId": "21b",
            "title": "Physical Simulation Layer for Accurate 3D Modeling",
            "authors": [
                "Mariem Mezghanni",
                " Théo Bodrito",
                " Malika Boulkenafed",
                " Maks Ovsjanikov"
            ]
        },
        {
            "paperId": "717",
            "posterId": "22b",
            "title": "Fourier PlenOctrees for Dynamic Radiance Field Rendering in Real-Time",
            "authors": [
                "Liao Wang",
                " Jiakai Zhang",
                " Xinhang Liu",
                " Fuqiang Zhao",
                " Yanshun Zhang",
                " Yingliang Zhang",
                " Minye Wu",
                " Jingyi Yu",
                " Lan Xu"
            ]
        },
        {
            "paperId": "3579",
            "posterId": "23b",
            "title": "Neural Texture Extraction and Distribution for Controllable Person Image Synthesis",
            "authors": [
                "Yurui Ren",
                " Xiaoqing Fan",
                " Ge Li",
                " Shan Liu",
                " Thomas H. Li"
            ]
        },
        {
            "paperId": "6545",
            "posterId": "24b",
            "title": "I M Avatar: Implicit Morphable Head Avatars From Videos",
            "authors": [
                "Yufeng Zheng",
                " Victoria Fernández Abrevaya",
                " Marcel C. Bühler",
                " Xu Chen",
                " Michael J. Black",
                " Otmar Hilliges"
            ]
        },
        {
            "paperId": "6772",
            "posterId": "25b",
            "title": "E2V-SDE: From Asynchronous Events to Fast and Continuous Video Reconstruction via Neural Stochastic Differential Equations",
            "authors": [
                "Jongwan Kim",
                " DongJin Lee",
                " Byunggook Na",
                " Seongsik Park",
                " Sungroh Yoon"
            ]
        },
        {
            "paperId": "549",
            "posterId": "26b",
            "title": "RCL: Recurrent Continuous Localization for Temporal Action Detection",
            "authors": [
                "Qiang Wang",
                " Yanhao Zhang",
                " Yun Zheng",
                " Pan Pan"
            ]
        },
        {
            "paperId": "4317",
            "posterId": "27b",
            "title": "Self-Supervised Predictive Convolutional Attentive Block for Anomaly Detection",
            "authors": [
                "Nicolae-Cătălin Ristea",
                " Neelu Madan",
                " Radu Tudor Ionescu",
                " Kamal Nasrollahi",
                " Fahad Shahbaz Khan",
                " Thomas B. Moeslund",
                " Mubarak Shah"
            ]
        },
        {
            "paperId": "729",
            "posterId": "28b",
            "title": "MeMViT: Memory-Augmented Multiscale Vision Transformer for Efficient Long-Term Video Recognition",
            "authors": [
                "Chao-Yuan Wu",
                " Yanghao Li",
                " Karttikeya Mangalam",
                " Haoqi Fan",
                " Bo Xiong",
                " Jitendra Malik",
                " Christoph Feichtenhofer"
            ]
        },
        {
            "paperId": "9219",
            "posterId": "29b",
            "title": "TubeR: Tubelet Transformer for Video Action Detection",
            "authors": [
                "Jiaojiao Zhao",
                " Yanyi Zhang",
                " Xinyu Li",
                " Hao Chen",
                " Bing Shuai",
                " Mingze Xu",
                " Chunhui Liu",
                " Kaustav Kundu",
                " Yuanjun Xiong",
                " Davide Modolo",
                " Ivan Marsic",
                " Cees G. M. Snoek",
                " Joseph Tighe"
            ]
        },
        {
            "paperId": "8613",
            "posterId": "30b",
            "title": "MixFormer: End-to-End Tracking With Iterative Mixed Attention",
            "authors": [
                "Yutao Cui",
                " Cheng Jiang",
                " Limin Wang",
                " Gangshan Wu"
            ]
        }
    ],
    "Recognition, Learning for Vision, and Robot Vision": [
        {
            "paperId": "5905",
            "posterId": "31b",
            "title": "DN-DETR: Accelerate DETR Training by Introducing Query DeNoising",
            "authors": [
                "Feng Li",
                " Hao Zhang",
                " Shilong Liu",
                " Jian Guo",
                " Lionel M. Ni",
                " Lei Zhang"
            ]
        },
        {
            "paperId": "7010",
            "posterId": "32b",
            "title": "Proper Reuse of Image Classification Features Improves Object Detection",
            "authors": [
                "Cristina Vasconcelos",
                " Vighnesh Birodkar",
                " Vincent Dumoulin"
            ]
        },
        {
            "paperId": "8646",
            "posterId": "33b",
            "title": "Boosting 3D Object Detection by Simulating Multimodality on Point Clouds",
            "authors": [
                "Wu Zheng",
                " Mingxuan Hong",
                " Li Jiang",
                " Chi-Wing Fu"
            ]
        },
        {
            "paperId": "10578",
            "posterId": "34b",
            "title": "TransVPR: Transformer-Based Place Recognition With Multi-Level Attention Aggregation",
            "authors": [
                "Ruotong Wang",
                " Yanqing Shen",
                " Weiliang Zuo",
                " Sanping Zhou",
                " Nanning Zheng"
            ]
        },
        {
            "paperId": "9856",
            "posterId": "35b",
            "title": "Disentangling Visual Embeddings for Attributes and Objects",
            "authors": [
                "Nirat Saini",
                " Khoi Pham",
                " Abhinav Shrivastava"
            ]
        },
        {
            "paperId": "1856",
            "posterId": "36b",
            "title": "QueryDet: Cascaded Sparse Query for Accelerating High-Resolution Small Object Detection",
            "authors": [
                "Chenhongyi Yang",
                " Zehao Huang",
                " Naiyan Wang"
            ]
        },
        {
            "paperId": "5517",
            "posterId": "37b",
            "title": "Unknown-Aware Object Detection: Learning What You Don't Know From Videos in the Wild",
            "authors": [
                "Xuefeng Du",
                " Xin Wang",
                " Gabriel Gozum",
                " Yixuan Li"
            ]
        },
        {
            "paperId": "3247",
            "posterId": "38b",
            "title": "Interpretable Part-Whole Hierarchies and Conceptual-Semantic Relationships in Neural Networks",
            "authors": [
                "Nicola Garau",
                " Niccolò Bisagno",
                " Zeno Sambugaro",
                " Nicola Conci"
            ]
        },
        {
            "paperId": "5972",
            "posterId": "39b",
            "title": "Can Neural Nets Learn the Same Model Twice? Investigating Reproducibility and Double Descent From the Decision Boundary Perspective",
            "authors": [
                "Gowthami Somepalli",
                " Liam Fowl",
                " Arpit Bansal",
                " Ping Yeh-Chiang",
                " Yehuda Dar",
                " Richard Baraniuk",
                " Micah Goldblum",
                " Tom Goldstein"
            ]
        },
        {
            "paperId": "3349",
            "posterId": "40b",
            "title": "Calibrating Deep Neural Networks by Pairwise Constraints",
            "authors": [
                "Jiacheng Cheng",
                " Nuno Vasconcelos"
            ]
        },
        {
            "paperId": "7691",
            "posterId": "41b",
            "title": "Lifelong Graph Learning",
            "authors": [
                "Chen Wang",
                " Yuheng Qiu",
                " Dasong Gao",
                " Sebastian Scherer"
            ]
        },
        {
            "paperId": "11327",
            "posterId": "42b",
            "title": "OrphicX: A Causality-Inspired Latent Variable Model for Interpreting Graph Neural Networks",
            "authors": [
                "Wanyu Lin",
                " Hao Lan",
                " Hao Wang",
                " Baochun Li"
            ]
        },
        {
            "paperId": "10810",
            "posterId": "43b",
            "title": "Coarse-To-Fine Q-Attention: Efficient Learning for Visual Robotic Manipulation via Discretisation",
            "authors": [
                "Stephen James",
                " Kentaro Wada",
                " Tristan Laidlow",
                " Andrew J. Davison"
            ]
        },
        {
            "paperId": "11529",
            "posterId": "44b",
            "title": "Dual Task Learning by Leveraging Both Dense Correspondence and Mis-Correspondence for Robust Change Detection With Imperfect Matches",
            "authors": [
                "Jin-Man Park",
                " Ue-Hwan Kim",
                " Seon-Hoon Lee",
                " Jong-Hwan Kim"
            ]
        },
        {
            "paperId": "9157",
            "posterId": "45b",
            "title": "Cross-View Transformers for Real-Time Map-View Semantic Segmentation",
            "authors": [
                "Brady Zhou",
                " Philipp Krähenbühl"
            ]
        }
    ],
    "Self_Semi_Meta-, & Unsupervised Learning": [
        {
            "paperId": "8542",
            "posterId": "105b",
            "title": "Label Matching Semi-Supervised Object Detection",
            "authors": [
                "Binbin Chen",
                " Weijie Chen",
                " Shicai Yang",
                " Yunyi Xuan",
                " Jie Song",
                " Di Xie",
                " Shiliang Pu",
                " Mingli Song",
                " Yueting Zhuang"
            ]
        },
        {
            "paperId": "10433",
            "posterId": "106b",
            "title": "Multidimensional Belief Quantification for Label-Efficient Meta-Learning",
            "authors": [
                "Deep Shankar Pandey",
                " Qi Yu"
            ]
        },
        {
            "paperId": "11752",
            "posterId": "107b",
            "title": "Propagation Regularizer for Semi-Supervised Learning With Extremely Scarce Labeled Samples",
            "authors": [
                "Noo-ri Kim",
                " Jee-Hyong Lee"
            ]
        },
        {
            "paperId": "5537",
            "posterId": "108b",
            "title": "Learning To Affiliate: Mutual Centralized Learning for Few-Shot Classification",
            "authors": [
                "Yang Liu",
                " Weifeng Zhang",
                " Chao Xiang",
                " Tu Zheng",
                " Deng Cai",
                " Xiaofei He"
            ]
        },
        {
            "paperId": "9804",
            "posterId": "109b",
            "title": "Class-Aware Contrastive Semi-Supervised Learning",
            "authors": [
                "Fan Yang",
                " Kai Wu",
                " Shuyi Zhang",
                " Guannan Jiang",
                " Yong Liu",
                " Feng Zheng",
                " Wei Zhang",
                " Chengjie Wang",
                " Long Zeng"
            ]
        },
        {
            "paperId": "4181",
            "posterId": "110b",
            "title": "Exploring the Equivalence of Siamese Self-Supervised Learning via a Unified Gradient Framework",
            "authors": [
                "Chenxin Tao",
                " Honghui Wang",
                " Xizhou Zhu",
                " Jiahua Dong",
                " Shiji Song",
                " Gao Huang",
                " Jifeng Dai"
            ]
        },
        {
            "paperId": "10916",
            "posterId": "111b",
            "title": "Dual Temperature Helps Contrastive Learning Without Many Negative Samples: Towards Understanding and Simplifying MoCo",
            "authors": [
                "Chaoning Zhang",
                " Kang Zhang",
                " Trung X. Pham",
                " Axi Niu",
                " Zhinan Qiao",
                " Chang D. Yoo",
                " In So Kweon"
            ]
        },
        {
            "paperId": "2296",
            "posterId": "112b",
            "title": "Learning Where To Learn in Cross-View Self-Supervised Learning",
            "authors": [
                "Lang Huang",
                " Shan You",
                " Mingkai Zheng",
                " Fei Wang",
                " Chen Qian",
                " Toshihiko Yamasaki"
            ]
        },
        {
            "paperId": "2487",
            "posterId": "113b",
            "title": "Dist-PU: Positive-Unlabeled Learning From a Label Distribution Perspective",
            "authors": [
                "Yunrui Zhao",
                " Qianqian Xu",
                " Yangbangyan Jiang",
                " Peisong Wen",
                " Qingming Huang"
            ]
        },
        {
            "paperId": "2869",
            "posterId": "114b",
            "title": "SimMatch: Semi-Supervised Learning With Similarity Matching",
            "authors": [
                "Mingkai Zheng",
                " Shan You",
                " Lang Huang",
                " Fei Wang",
                " Chen Qian",
                " Chang Xu"
            ]
        },
        {
            "paperId": "540",
            "posterId": "115b",
            "title": "Active Teacher for Semi-Supervised Object Detection",
            "authors": [
                "Peng Mi",
                " Jianghang Lin",
                " Yiyi Zhou",
                " Yunhang Shen",
                " Gen Luo",
                " Xiaoshuai Sun",
                " Liujuan Cao",
                " Rongrong Fu",
                " Qiang Xu",
                " Rongrong Ji"
            ]
        },
        {
            "paperId": "943",
            "posterId": "116b",
            "title": "Not All Labels Are Equal: Rationalizing the Labeling Costs for Training Object Detection",
            "authors": [
                "Ismail Elezi",
                " Zhiding Yu",
                " Anima Anandkumar",
                " Laura Leal-Taixé",
                " Jose M. Alvarez"
            ]
        },
        {
            "paperId": "5807",
            "posterId": "117b",
            "title": "Self-Supervised Learning of Object Parts for Semantic Segmentation",
            "authors": [
                "Adrian Ziegler",
                " Yuki M. Asano"
            ]
        },
        {
            "paperId": "4603",
            "posterId": "118b",
            "title": "MUM: Mix Image Tiles and UnMix Feature Tiles for Semi-Supervised Object Detection",
            "authors": [
                "JongMok Kim",
                " JooYoung Jang",
                " Seunghyeon Seo",
                " Jisoo Jeong",
                " Jongkeun Na",
                " Nojun Kwak"
            ]
        },
        {
            "paperId": "6024",
            "posterId": "119b",
            "title": "Scale-Equivalent Distillation for Semi-Supervised Object Detection",
            "authors": [
                "Qiushan Guo",
                " Yao Mu",
                " Jianyu Chen",
                " Tianqi Wang",
                " Yizhou Yu",
                " Ping Luo"
            ]
        },
        {
            "paperId": "6654",
            "posterId": "120b",
            "title": "A Self-Supervised Descriptor for Image Copy Detection",
            "authors": [
                "Ed Pizzi",
                " Sreya Dutta Roy",
                " Sugosh Nagavara Ravindra",
                " Priya Goyal",
                " Matthijs Douze"
            ]
        },
        {
            "paperId": "10678",
            "posterId": "121b",
            "title": "Self-Supervised Transformers for Unsupervised Object Discovery Using Normalized Cut",
            "authors": [
                "Yangtao Wang",
                " Xi Shen",
                " Shell Xu Hu",
                " Yuan Yuan",
                " James L. Crowley",
                " Dominique Vaufreydaz"
            ]
        },
        {
            "paperId": "9521",
            "posterId": "122b",
            "title": "CAD: Co-Adapting Discriminative Features for Improved Few-Shot Classification",
            "authors": [
                "Philip Chikontwe",
                " Soopil Kim",
                " Sang Hyun Park"
            ]
        },
        {
            "paperId": "11648",
            "posterId": "123b",
            "title": "Semi-Supervised Few-Shot Learning via Multi-Factor Clustering",
            "authors": [
                "Jie Ling",
                " Lei Liao",
                " Meng Yang",
                " Jia Shuai"
            ]
        },
        {
            "paperId": "2306",
            "posterId": "124b",
            "title": "CoSSL: Co-Learning of Representation and Classifier for Imbalanced Semi-Supervised Learning",
            "authors": [
                "Yue Fan",
                " Dengxin Dai",
                " Anna Kukleva",
                " Bernt Schiele"
            ]
        },
        {
            "paperId": "2589",
            "posterId": "125b",
            "title": "Safe-Student for Safe Deep Semi-Supervised Learning With Unseen-Class Unlabeled Data",
            "authors": [
                "Rundong He",
                " Zhongyi Han",
                " Xiankai Lu",
                " Yilong Yin"
            ]
        },
        {
            "paperId": "3172",
            "posterId": "126b",
            "title": "A Simple Data Mixing Prior for Improving Self-Supervised Learning",
            "authors": [
                "Sucheng Ren",
                " Huiyu Wang",
                " Zhengqi Gao",
                " Shengfeng He",
                " Alan Yuille",
                " Yuyin Zhou",
                " Cihang Xie"
            ]
        },
        {
            "paperId": "3375",
            "posterId": "127b",
            "title": "DETReg: Unsupervised Pretraining With Region Priors for Object Detection",
            "authors": [
                "Amir Bar",
                " Xin Wang",
                " Vadim Kantorov",
                " Colorado J. Reed",
                " Roei Herzig",
                " Gal Chechik",
                " Anna Rohrbach",
                " Trevor Darrell",
                " Amir Globerson"
            ]
        },
        {
            "paperId": "4354",
            "posterId": "128b",
            "title": "Sound and Visual Representation Learning With Multiple Pretraining Tasks",
            "authors": [
                "Arun Balajee Vasudevan",
                " Dengxin Dai",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "4601",
            "posterId": "129b",
            "title": "UniVIP: A Unified Framework for Self-Supervised Visual Pre-Training",
            "authors": [
                "Zhaowen Li",
                " Yousong Zhu",
                " Fan Yang",
                " Wei Li",
                " Chaoyang Zhao",
                " Yingying Chen",
                " Zhiyang Chen",
                " Jiahao Xie",
                " Liwei Wu",
                " Rui Zhao",
                " Ming Tang",
                " Jinqiao Wang"
            ]
        },
        {
            "paperId": "1744",
            "posterId": "130b",
            "title": "Weakly Supervised Object Localization As Domain Adaption",
            "authors": [
                "Lei Zhu",
                " Qi She",
                " Qian Chen",
                " Yunfei You",
                " Boyu Wang",
                " Yanye Lu"
            ]
        },
        {
            "paperId": "7762",
            "posterId": "131b",
            "title": "Debiased Learning From Naturally Imbalanced Pseudo-Labels",
            "authors": [
                "Xudong Wang",
                " Zhirong Wu",
                " Long Lian",
                " Stella X. Yu"
            ]
        },
        {
            "paperId": "3414",
            "posterId": "132b",
            "title": "Towards Discovering the Effectiveness of Moderately Confident Samples for Semi-Supervised Learning",
            "authors": [
                "Hui Tang",
                " Kui Jia"
            ]
        },
        {
            "paperId": "1546",
            "posterId": "133b",
            "title": "Masked Feature Prediction for Self-Supervised Visual Pre-Training",
            "authors": [
                "Chen Wei",
                " Haoqi Fan",
                " Saining Xie",
                " Chao-Yuan Wu",
                " Alan Yuille",
                " Christoph Feichtenhofer"
            ]
        },
        {
            "paperId": "6171",
            "posterId": "134b",
            "title": "Contrastive Learning for Space-Time Correspondence via Self-Cycle Consistency",
            "authors": [
                "Jeany Son"
            ]
        },
        {
            "paperId": "11064",
            "posterId": "135b",
            "title": "Id-Free Person Similarity Learning",
            "authors": [
                "Bing Shuai",
                " Xinyu Li",
                " Kaustav Kundu",
                " Joseph Tighe"
            ]
        },
        {
            "paperId": "5962",
            "posterId": "136b",
            "title": "End-to-End Semi-Supervised Learning for Video Action Detection",
            "authors": [
                "Akash Kumar",
                " Yogesh Singh Rawat"
            ]
        },
        {
            "paperId": "11772",
            "posterId": "137b",
            "title": "Probabilistic Representations for Video Contrastive Learning",
            "authors": [
                "Jungin Park",
                " Jiyoung Lee",
                " Ig-Jae Kim",
                " Kwanghoon Sohn"
            ]
        },
        {
            "paperId": "5904",
            "posterId": "138b",
            "title": "Interact Before Align: Leveraging Cross-Modal Knowledge for Domain Adaptive Action Recognition",
            "authors": [
                "Lijin Yang",
                " Yifei Huang",
                " Yusuke Sugano",
                " Yoichi Sato"
            ]
        },
        {
            "paperId": "5668",
            "posterId": "139b",
            "title": "BEVT: BERT Pretraining of Video Transformers",
            "authors": [
                "Rui Wang",
                " Dongdong Chen",
                " Zuxuan Wu",
                " Yinpeng Chen",
                " Xiyang Dai",
                " Mengchen Liu",
                " Yu-Gang Jiang",
                " Luowei Zhou",
                " Lu Yuan"
            ]
        },
        {
            "paperId": "7678",
            "posterId": "140b",
            "title": "Generative Cooperative Learning for Unsupervised Video Anomaly Detection",
            "authors": [
                "M. Zaigham Zaheer",
                " Arif Mahmood",
                " M. Haris Khan",
                " Mattia Segu",
                " Fisher Yu",
                " Seung-Ik Lee"
            ]
        },
        {
            "paperId": "9976",
            "posterId": "141b",
            "title": "When Does Contrastive Visual Representation Learning Work?",
            "authors": [
                "Elijah Cole",
                " Xuan Yang",
                " Kimberly Wilber",
                " Oisin Mac Aodha",
                " Serge Belongie"
            ]
        },
        {
            "paperId": "596",
            "posterId": "142b",
            "title": "The Norm Must Go On: Dynamic Unsupervised Domain Adaptation by Normalization",
            "authors": [
                "M. Jehanzeb Mirza",
                " Jakub Micorek",
                " Horst Possegger",
                " Horst Bischof"
            ]
        },
        {
            "paperId": "5267",
            "posterId": "143b",
            "title": "What Matters for Meta-Learning Vision Regression Tasks?",
            "authors": [
                "Ning Gao",
                " Hanna Ziesche",
                " Ngo Anh Vien",
                " Michael Volpp",
                " Gerhard Neumann"
            ]
        }
    ],
    "Robot Vision": [
        {
            "paperId": "689",
            "posterId": "144b",
            "title": "IFOR: Iterative Flow Minimization for Robotic Object Rearrangement",
            "authors": [
                "Ankit Goyal",
                " Arsalan Mousavian",
                " Chris Paxton",
                " Yu-Wei Chao",
                " Brian Okorn",
                " Jia Deng",
                " Dieter Fox"
            ]
        },
        {
            "paperId": "2734",
            "posterId": "145b",
            "title": "TCTrack: Temporal Contexts for Aerial Tracking",
            "authors": [
                "Ziang Cao",
                " Ziyuan Huang",
                " Liang Pan",
                " Shiwei Zhang",
                " Ziwei Liu",
                " Changhong Fu"
            ]
        },
        {
            "paperId": "2846",
            "posterId": "146b",
            "title": "AKB-48: A Real-World Articulated Object Knowledge Base",
            "authors": [
                "Liu Liu",
                " Wenqiang Xu",
                " Haoyuan Fu",
                " Sucheng Qian",
                " Qiaojun Yu",
                " Yang Han",
                " Cewu Lu"
            ]
        },
        {
            "paperId": "4440",
            "posterId": "147b",
            "title": "3DAC: Learning Attribute Compression for Point Clouds",
            "authors": [
                "Guangchi Fang",
                " Qingyong Hu",
                " Hanyun Wang",
                " Yiling Xu",
                " Yulan Guo"
            ]
        },
        {
            "paperId": "4521",
            "posterId": "148b",
            "title": "Simple but Effective: CLIP Embeddings for Embodied AI",
            "authors": [
                "Apoorv Khandelwal",
                " Luca Weihs",
                " Roozbeh Mottaghi",
                " Aniruddha Kembhavi"
            ]
        },
        {
            "paperId": "2359",
            "posterId": "149b",
            "title": "Multi-Robot Active Mapping via Neural Bipartite Graph Matching",
            "authors": [
                "Kai Ye",
                " Siyan Dong",
                " Qingnan Fan",
                " He Wang",
                " Li Yi",
                " Fei Xia",
                " Jue Wang",
                " Baoquan Chen"
            ]
        },
        {
            "paperId": "2464",
            "posterId": "150b",
            "title": "Continuous Scene Representations for Embodied AI",
            "authors": [
                "Samir Yitzhak Gadre",
                " Kiana Ehsani",
                " Shuran Song",
                " Roozbeh Mottaghi"
            ]
        },
        {
            "paperId": "2923",
            "posterId": "151b",
            "title": "Interactron: Embodied Adaptive Object Detection",
            "authors": [
                "Klemen Kotar",
                " Roozbeh Mottaghi"
            ]
        },
        {
            "paperId": "1761",
            "posterId": "152b",
            "title": "Online Learning of Reusable Abstract Models for Object Goal Navigation",
            "authors": [
                "Tommaso Campari",
                " Leonardo Lamanna",
                " Paolo Traverso",
                " Luciano Serafini",
                " Lamberto Ballan"
            ]
        },
        {
            "paperId": "3195",
            "posterId": "153b",
            "title": "RNNPose: Recurrent 6-DoF Object Pose Refinement With Robust Correspondence Field Estimation and Pose Optimization",
            "authors": [
                "Yan Xu",
                " Kwan-Yee Lin",
                " Guofeng Zhang",
                " Xiaogang Wang",
                " Hongsheng Li"
            ]
        },
        {
            "paperId": "2684",
            "posterId": "154b",
            "title": "UDA-COPE: Unsupervised Domain Adaptation for Category-Level Object Pose Estimation",
            "authors": [
                "Taeyeop Lee",
                " Byeong-Uk Lee",
                " Inkyu Shin",
                " Jaesung Choe",
                " Ukcheol Shin",
                " In So Kweon",
                " Kuk-Jin Yoon"
            ]
        },
        {
            "paperId": "9736",
            "posterId": "155b",
            "title": "Symmetry and Uncertainty-Aware Object SLAM for 6DoF Object Pose Estimation",
            "authors": [
                "Nathaniel Merrill",
                " Yuliang Guo",
                " Xingxing Zuo",
                " Xinyu Huang",
                " Stefan Leutenegger",
                " Xi Peng",
                " Liu Ren",
                " Guoquan Huang"
            ]
        },
        {
            "paperId": "10404",
            "posterId": "156b",
            "title": "Upright-Net: Learning Upright Orientation for 3D Point Cloud",
            "authors": [
                "Xufang Pang",
                " Feng Li",
                " Ning Ding",
                " Xiaopin Zhong"
            ]
        }
    ],
    "Computer Vision for Social Good": [
        {
            "paperId": "7865",
            "posterId": "157b",
            "title": "DeepFake Disrupter: The Detector of DeepFake Is My Friend",
            "authors": [
                "Xueyu Wang",
                " Jiajun Huang",
                " Siqi Ma",
                " Surya Nepal",
                " Chang Xu"
            ]
        },
        {
            "paperId": "3350",
            "posterId": "158b",
            "title": "HybridCR: Weakly-Supervised 3D Point Cloud Semantic Segmentation via Hybrid Contrastive Regularization",
            "authors": [
                "Mengtian Li",
                " Yuan Xie",
                " Yunhang Shen",
                " Bo Ke",
                " Ruizhi Qiao",
                " Bo Ren",
                " Shaohui Lin",
                " Lizhuang Ma"
            ]
        },
        {
            "paperId": "7457",
            "posterId": "159b",
            "title": "Open-Domain, Content-Based, Multi-Modal Fact-Checking of Out-of-Context Images via Online Resources",
            "authors": [
                "Sahar Abdelnabi",
                " Rakibul Hasan",
                " Mario Fritz"
            ]
        },
        {
            "paperId": "9423",
            "posterId": "160b",
            "title": "Leveraging Real Talking Faces via Self-Supervision for Robust Forgery Detection",
            "authors": [
                "Alexandros Haliassos",
                " Rodrigo Mira",
                " Stavros Petridis",
                " Maja Pantic"
            ]
        }
    ],
    "Adversarial Attack & Defense": [
        {
            "paperId": "8193",
            "posterId": "161b",
            "title": "Transferable Sparse Adversarial Attack",
            "authors": [
                "Ziwen He",
                " Wei Wang",
                " Jing Dong",
                " Tieniu Tan"
            ]
        },
        {
            "paperId": "8898",
            "posterId": "162b",
            "title": "Segment and Complete: Defending Object Detectors Against Adversarial Patch Attacks With Robust Patch Detection",
            "authors": [
                "Jiang Liu",
                " Alexander Levine",
                " Chun Pong Lau",
                " Rama Chellappa",
                " Soheil Feizi"
            ]
        },
        {
            "paperId": "10026",
            "posterId": "163b",
            "title": "Stochastic Variance Reduced Ensemble Adversarial Attack for Boosting the Adversarial Transferability",
            "authors": [
                "Yifeng Xiong",
                " Jiadong Lin",
                " Min Zhang",
                " John E. Hopcroft",
                " Kun He"
            ]
        },
        {
            "paperId": "8063",
            "posterId": "164b",
            "title": "Improving Adversarial Transferability via Neuron Attribution-Based Attacks",
            "authors": [
                "Jianping Zhang",
                " Weibin Wu",
                " Jen-tse Huang",
                " Yizhan Huang",
                " Wenxuan Wang",
                " Yuxin Su",
                " Michael R. Lyu"
            ]
        },
        {
            "paperId": "10779",
            "posterId": "165b",
            "title": "Complex Backdoor Detection by Symmetric Feature Differencing",
            "authors": [
                "Yingqi Liu",
                " Guangyu Shen",
                " Guanhong Tao",
                " Zhenting Wang",
                " Shiqing Ma",
                " Xiangyu Zhang"
            ]
        },
        {
            "paperId": "10243",
            "posterId": "166b",
            "title": "Protecting Facial Privacy: Generating Adversarial Identity Masks via Style-Robust Makeup Transfer",
            "authors": [
                "Shengshan Hu",
                " Xiaogeng Liu",
                " Yechao Zhang",
                " Minghui Li",
                " Leo Yu Zhang",
                " Hai Jin",
                " Libing Wu"
            ]
        },
        {
            "paperId": "11148",
            "posterId": "167b",
            "title": "Zero-Query Transfer Attacks on Context-Aware Object Detectors",
            "authors": [
                "Zikui Cai",
                " Shantanu Rane",
                " Alejandro E. Brito",
                " Chengyu Song",
                " Srikanth V. Krishnamurthy",
                " Amit K. Roy-Chowdhury",
                " M. Salman Asif"
            ]
        },
        {
            "paperId": "6302",
            "posterId": "168b",
            "title": "360-Attack: Distortion-Aware Perturbations From Perspective-Views",
            "authors": [
                "Yunjian Zhang",
                " Yanwei Liu",
                " Jinxia Liu",
                " Jingbo Miao",
                " Antonios Argyriou",
                " Liming Wang",
                " Zhen Xu"
            ]
        },
        {
            "paperId": "11210",
            "posterId": "169b",
            "title": "Label-Only Model Inversion Attacks via Boundary Repulsion",
            "authors": [
                "Mostafa Kahla",
                " Si Chen",
                " Hoang Anh Just",
                " Ruoxi Jia"
            ]
        },
        {
            "paperId": "11207",
            "posterId": "170b",
            "title": "Merry Go Round: Rotate a Frame and Fool a DNN",
            "authors": [
                "Daksh Thapar",
                " Aditya Nigam",
                " Chetan Arora"
            ]
        },
        {
            "paperId": "1485",
            "posterId": "171b",
            "title": "Cross-Modal Transferable Adversarial Attacks From Images to Videos",
            "authors": [
                "Zhipeng Wei",
                " Jingjing Chen",
                " Zuxuan Wu",
                " Yu-Gang Jiang"
            ]
        },
        {
            "paperId": "10629",
            "posterId": "172b",
            "title": "BppAttack: Stealthy and Efficient Trojan Attacks Against Deep Neural Networks via Image Quantization and Contrastive Adversarial Learning",
            "authors": [
                "Zhenting Wang",
                " Juan Zhai",
                " Shiqing Ma"
            ]
        },
        {
            "paperId": "11521",
            "posterId": "173b",
            "title": "Investigating Top-k White-Box and Transferable Black-Box Attack",
            "authors": [
                "Chaoning Zhang",
                " Philipp Benz",
                " Adil Karjauv",
                " Jae Won Cho",
                " Kang Zhang",
                " In So Kweon"
            ]
        },
        {
            "paperId": "7175",
            "posterId": "174b",
            "title": "Boosting Black-Box Attack With Partially Transferred Conditional Adversarial Distribution",
            "authors": [
                "Yan Feng",
                " Baoyuan Wu",
                " Yanbo Fan",
                " Li Liu",
                " Zhifeng Li",
                " Shu-Tao Xia"
            ]
        },
        {
            "paperId": "2830",
            "posterId": "175b",
            "title": "Practical Evaluation of Adversarial Robustness via Adaptive Auto Attack",
            "authors": [
                "Ye Liu",
                " Yaya Cheng",
                " Lianli Gao",
                " Xianglong Liu",
                " Qilong Zhang",
                " Jingkuan Song"
            ]
        },
        {
            "paperId": "3325",
            "posterId": "176b",
            "title": "Towards Efficient Data Free Black-Box Adversarial Attack",
            "authors": [
                "Jie Zhang",
                " Bo Li",
                " Jianghe Xu",
                " Shuang Wu",
                " Shouhong Ding",
                " Lei Zhang",
                " Chao Wu"
            ]
        },
        {
            "paperId": "3931",
            "posterId": "177b",
            "title": "Masking Adversarial Damage: Finding Adversarial Saliency for Robust and Sparse Network",
            "authors": [
                "Byung-Kwan Lee",
                " Junho Kim",
                " Yong Man Ro"
            ]
        },
        {
            "paperId": "11451",
            "posterId": "178b",
            "title": "Certified Patch Robustness via Smoothed Vision Transformers",
            "authors": [
                "Hadi Salman",
                " Saachi Jain",
                " Eric Wong",
                " Aleksander Madry"
            ]
        },
        {
            "paperId": "5540",
            "posterId": "179b",
            "title": "Towards Practical Certifiable Patch Defense With Vision Transformer",
            "authors": [
                "Zhaoyu Chen",
                " Bo Li",
                " Jianghe Xu",
                " Shuang Wu",
                " Shouhong Ding",
                " Wenqiang Zhang"
            ]
        },
        {
            "paperId": "4282",
            "posterId": "180b",
            "title": "On Adversarial Robustness of Trajectory Prediction for Autonomous Vehicles",
            "authors": [
                "Qingzhao Zhang",
                " Shengtuo Hu",
                " Jiachen Sun",
                " Qi Alfred Chen",
                " Z. Morley Mao"
            ]
        },
        {
            "paperId": "7361",
            "posterId": "181b",
            "title": "3DeformRS: Certifying Spatial Deformations on Point Clouds",
            "authors": [
                "Gabriel Pérez S.",
                " Juan C. Pérez",
                " Motasem Alfarra",
                " Silvio Giancola",
                " Bernard Ghanem"
            ]
        },
        {
            "paperId": "4302",
            "posterId": "182b",
            "title": "Stereoscopic Universal Perturbations Across Different Architectures and Datasets",
            "authors": [
                "Zachary Berger",
                " Parth Agrawal",
                " Tian Yu Liu",
                " Stefano Soatto",
                " Alex Wong"
            ]
        },
        {
            "paperId": "4407",
            "posterId": "183b",
            "title": "Aug-NeRF: Training Stronger Neural Radiance Fields With Triple-Level Physically-Grounded Augmentations",
            "authors": [
                "Tianlong Chen",
                " Peihao Wang",
                " Zhiwen Fan",
                " Zhangyang Wang"
            ]
        },
        {
            "paperId": "10883",
            "posterId": "184b",
            "title": "Bounded Adversarial Attack on Deep Content Features",
            "authors": [
                "Qiuling Xu",
                " Guanhong Tao",
                " Xiangyu Zhang"
            ]
        },
        {
            "paperId": "9811",
            "posterId": "185b",
            "title": "DEFEAT: Deep Hidden Feature Backdoor Attacks by Imperceptible Perturbation and Latent Representation Constraints",
            "authors": [
                "Zhendong Zhao",
                " Xiaojun Chen",
                " Yuexin Xuan",
                " Ye Dong",
                " Dakui Wang",
                " Kaitai Liang"
            ]
        },
        {
            "paperId": "10212",
            "posterId": "186b",
            "title": "Two Coupled Rejection Metrics Can Tell Adversarial Examples Apart",
            "authors": [
                "Tianyu Pang",
                " Huishuai Zhang",
                " Di He",
                " Yinpeng Dong",
                " Hang Su",
                " Wei Chen",
                " Jun Zhu",
                " Tie-Yan Liu"
            ]
        },
        {
            "paperId": "10905",
            "posterId": "187b",
            "title": "Give Me Your Attention: Dot-Product Attention Considered Harmful for Adversarial Patch Robustness",
            "authors": [
                "Giulio Lovisotto",
                " Nicole Finnie",
                " Mauricio Munoz",
                " Chaithanya Kumar Mummadi",
                " Jan Hendrik Metzen"
            ]
        },
        {
            "paperId": "7360",
            "posterId": "188b",
            "title": "Improving the Transferability of Targeted Adversarial Examples Through Object-Based Diverse Input",
            "authors": [
                "Junyoung Byun",
                " Seungju Cho",
                " Myung-Joon Kwon",
                " Hee-Seon Kim",
                " Changick Kim"
            ]
        },
        {
            "paperId": "2205",
            "posterId": "189b",
            "title": "Adversarial Eigen Attack on Black-Box Models",
            "authors": [
                "Linjun Zhou",
                " Peng Cui",
                " Xingxuan Zhang",
                " Yinan Jiang",
                " Shiqiang Yang"
            ]
        },
        {
            "paperId": "7620",
            "posterId": "190b",
            "title": "Appearance and Structure Aware Robust Deep Visual Graph Matching: Attack, Defense and Beyond",
            "authors": [
                "Qibing Ren",
                " Qingquan Bao",
                " Runzhong Wang",
                " Junchi Yan"
            ]
        },
        {
            "paperId": "4422",
            "posterId": "191b",
            "title": "Enhancing Adversarial Training With Second-Order Statistics of Weights",
            "authors": [
                "Gaojie Jin",
                " Xinping Yi",
                " Wei Huang",
                " Sven Schewe",
                " Xiaowei Huang"
            ]
        },
        {
            "paperId": "9176",
            "posterId": "192b",
            "title": "Towards Data-Free Model Stealing in a Hard Label Setting",
            "authors": [
                "Sunandini Sanyal",
                " Sravanti Addepalli",
                " R. Venkatesh Babu"
            ]
        },
        {
            "paperId": "9218",
            "posterId": "193b",
            "title": "Robust Structured Declarative Classifiers for 3D Point Clouds: Defending Adversarial Attacks With Implicit Gradients",
            "authors": [
                "Kaidong Li",
                " Ziming Zhang",
                " Cuncong Zhong",
                " Guanghui Wang"
            ]
        },
        {
            "paperId": "10096",
            "posterId": "194b",
            "title": "DTA: Physical Camouflage Attacks Using Differentiable Transformation Network",
            "authors": [
                "Naufal Suryanto",
                " Yongsu Kim",
                " Hyoeun Kang",
                " Harashta Tatimma Larasati",
                " Youngyeo Yun",
                " Thi-Thu-Huong Le",
                " Hunmin Yang",
                " Se-Yoon Oh",
                " Howon Kim"
            ]
        },
        {
            "paperId": "1841",
            "posterId": "195b",
            "title": "Frequency-Driven Imperceptible Adversarial Attack on Semantic Similarity",
            "authors": [
                "Cheng Luo",
                " Qinliang Lin",
                " Weicheng Xie",
                " Bizhu Wu",
                " Jinheng Xie",
                " Linlin Shen"
            ]
        },
        {
            "paperId": "201",
            "posterId": "196b",
            "title": "Enhancing Adversarial Robustness for Deep Metric Learning",
            "authors": [
                "Mo Zhou",
                " Vishal M. Patel"
            ]
        },
        {
            "paperId": "5230",
            "posterId": "197b",
            "title": "Shape-Invariant 3D Adversarial Point Clouds",
            "authors": [
                "Qidong Huang",
                " Xiaoyi Dong",
                " Dongdong Chen",
                " Hang Zhou",
                " Weiming Zhang",
                " Nenghai Yu"
            ]
        },
        {
            "paperId": "5789",
            "posterId": "198b",
            "title": "Shadows Can Be Dangerous: Stealthy and Effective Physical-World Adversarial Attack by Natural Phenomenon",
            "authors": [
                "Yiqi Zhong",
                " Xianming Liu",
                " Deming Zhai",
                " Junjun Jiang",
                " Xiangyang Ji"
            ]
        },
        {
            "paperId": "6161",
            "posterId": "199b",
            "title": "Exploring Effective Data for Surrogate Training Towards Black-Box Attack",
            "authors": [
                "Xuxiang Sun",
                " Gong Cheng",
                " Hongda Li",
                " Lei Pei",
                " Junwei Han"
            ]
        },
        {
            "paperId": "11698",
            "posterId": "200b",
            "title": "NICGSlowDown: Evaluating the Efficiency Robustness of Neural Image Caption Generation Models",
            "authors": [
                "Simin Chen",
                " Zihe Song",
                " Mirazul Haque",
                " Cong Liu",
                " Wei Yang"
            ]
        },
        {
            "paperId": "5970",
            "posterId": "201b",
            "title": "Dual-Key Multimodal Backdoors for Visual Question Answering",
            "authors": [
                "Matthew Walmer",
                " Karan Sikka",
                " Indranil Sur",
                " Abhinav Shrivastava",
                " Susmit Jha"
            ]
        },
        {
            "paperId": "6546",
            "posterId": "202b",
            "title": "Proactive Image Manipulation Detection",
            "authors": [
                "Vishal Asnani",
                " Xi Yin",
                " Tal Hassner",
                " Sijia Liu",
                " Xiaoming Liu"
            ]
        }
    ],
    "Representation Learning": [
        {
            "paperId": "2347",
            "posterId": "46b",
            "title": "Unified Contrastive Learning in Image-Text-Label Space",
            "authors": [
                "Jianwei Yang",
                " Chunyuan Li",
                " Pengchuan Zhang",
                " Bin Xiao",
                " Ce Liu",
                " Lu Yuan",
                " Jianfeng Gao"
            ]
        },
        {
            "paperId": "9927",
            "posterId": "47b",
            "title": "AlignMixup: Improving Representations by Interpolating Aligned Features",
            "authors": [
                "Shashanka Venkataramanan",
                " Ewa Kijak",
                " Laurent Amsaleg",
                " Yannis Avrithis"
            ]
        },
        {
            "paperId": "2419",
            "posterId": "48b",
            "title": "On the Road to Online Adaptation for Semantic Image Segmentation",
            "authors": [
                "Riccardo Volpi",
                " Pau De Jorge",
                " Diane Larlus",
                " Gabriela Csurka"
            ]
        },
        {
            "paperId": "5236",
            "posterId": "49b",
            "title": "ADAS: A Direct Adaptation Strategy for Multi-Target Domain Adaptive Semantic Segmentation",
            "authors": [
                "Seunghun Lee",
                " Wonhyeok Choi",
                " Changjae Kim",
                " Minwoo Choi",
                " Sunghoon Im"
            ]
        },
        {
            "paperId": "3487",
            "posterId": "50b",
            "title": "Kernelized Few-Shot Object Detection With Efficient Integral Aggregation",
            "authors": [
                "Shan Zhang",
                " Lei Wang",
                " Naila Murray",
                " Piotr Koniusz"
            ]
        },
        {
            "paperId": "186",
            "posterId": "51b",
            "title": "Neural Mean Discrepancy for Efficient Out-of-Distribution Detection",
            "authors": [
                "Xin Dong",
                " Junfeng Guo",
                " Ang Li",
                " Wei-Te Ting",
                " Cong Liu",
                " H.T. Kung"
            ]
        },
        {
            "paperId": "8477",
            "posterId": "52b",
            "title": "A Structured Dictionary Perspective on Implicit Neural Representations",
            "authors": [
                "Gizem Yüce",
                " Guillermo Ortiz-Jiménez",
                " Beril Besbinar",
                " Pascal Frossard"
            ]
        },
        {
            "paperId": "10563",
            "posterId": "53b",
            "title": "LARGE: Latent-Based Regression Through GAN Semantics",
            "authors": [
                "Yotam Nitzan",
                " Rinon Gal",
                " Ofir Brenner",
                " Daniel Cohen-Or"
            ]
        },
        {
            "paperId": "6667",
            "posterId": "54b",
            "title": "Rethinking Controllable Variational Autoencoders",
            "authors": [
                "Huajie Shao",
                " Yifei Yang",
                " Haohong Lin",
                " Longzhong Lin",
                " Yizhuo Chen",
                " Qinmin Yang",
                " Han Zhao"
            ]
        },
        {
            "paperId": "9016",
            "posterId": "55b",
            "title": "Learning Canonical F-Correlation Projection for Compact Multiview Representation",
            "authors": [
                "Yun-Hao Yuan",
                " Jin Li",
                " Yun Li",
                " Jipeng Qiang",
                " Yi Zhu",
                " Xiaobo Shen",
                " Jianping Gou"
            ]
        },
        {
            "paperId": "6288",
            "posterId": "56b",
            "title": "Cross-Architecture Self-Supervised Video Representation Learning",
            "authors": [
                "Sheng Guo",
                " Zihua Xiong",
                " Yujie Zhong",
                " Limin Wang",
                " Xiaobo Guo",
                " Bing Han",
                " Weilin Huang"
            ]
        },
        {
            "paperId": "4418",
            "posterId": "57b",
            "title": "Improving Video Model Transfer With Dynamic Representation Learning",
            "authors": [
                "Yi Li",
                " Nuno Vasconcelos"
            ]
        },
        {
            "paperId": "5928",
            "posterId": "58b",
            "title": "Self-Supervised Image Representation Learning With Geometric Set Consistency",
            "authors": [
                "Nenglun Chen",
                " Lei Chu",
                " Hao Pan",
                " Yan Lu",
                " Wenping Wang"
            ]
        },
        {
            "paperId": "246",
            "posterId": "59b",
            "title": "HLRTF: Hierarchical Low-Rank Tensor Factorization for Inverse Problems in Multi-Dimensional Imaging",
            "authors": [
                "Yisi Luo",
                " Xi-Le Zhao",
                " Deyu Meng",
                " Tai-Xiang Jiang"
            ]
        },
        {
            "paperId": "4037",
            "posterId": "60b",
            "title": "Point-BERT: Pre-Training 3D Point Cloud Transformers With Masked Point Modeling",
            "authors": [
                "Xumin Yu",
                " Lulu Tang",
                " Yongming Rao",
                " Tiejun Huang",
                " Jie Zhou",
                " Jiwen Lu"
            ]
        },
        {
            "paperId": "7362",
            "posterId": "61b",
            "title": "DiGS: Divergence Guided Shape Implicit Neural Representation for Unoriented Point Clouds",
            "authors": [
                "Yizhak Ben-Shabat",
                " Chamin Hewa Koneputugodage",
                " Stephen Gould"
            ]
        },
        {
            "paperId": "9356",
            "posterId": "62b",
            "title": "Neural Convolutional Surfaces",
            "authors": [
                "Luca Morreale",
                " Noam Aigerman",
                " Paul Guerrero",
                " Vladimir G. Kim",
                " Niloy J. Mitra"
            ]
        },
        {
            "paperId": "10032",
            "posterId": "63b",
            "title": "Representing 3D Shapes With Probabilistic Directed Distance Fields",
            "authors": [
                "Tristan Aumentado-Armstrong",
                " Stavros Tsogkas",
                " Sven Dickinson",
                " Allan D. Jepson"
            ]
        },
        {
            "paperId": "3030",
            "posterId": "64b",
            "title": "H4D: Human 4D Modeling by Learning Neural Compositional Representation",
            "authors": [
                "Boyan Jiang",
                " Yinda Zhang",
                " Xingkui Wei",
                " Xiangyang Xue",
                " Yanwei Fu"
            ]
        },
        {
            "paperId": "518",
            "posterId": "65b",
            "title": "Learning Memory-Augmented Unidirectional Metrics for Cross-Modality Person Re-Identification",
            "authors": [
                "Jialun Liu",
                " Yifan Sun",
                " Feng Zhu",
                " Hongbin Pei",
                " Yi Yang",
                " Wenhui Li"
            ]
        },
        {
            "paperId": "1275",
            "posterId": "66b",
            "title": "Contrastive Regression for Domain Adaptation on Gaze Estimation",
            "authors": [
                "Yaoming Wang",
                " Yangzhou Jiang",
                " Jin Li",
                " Bingbing Ni",
                " Wenrui Dai",
                " Chenglin Li",
                " Hongkai Xiong",
                " Teng Li"
            ]
        },
        {
            "paperId": "9822",
            "posterId": "67b",
            "title": "Forward Compatible Training for Large-Scale Embedding Retrieval Systems",
            "authors": [
                "Vivek Ramanujan",
                " Pavan Kumar Anasosalu Vasu",
                " Ali Farhadi",
                " Oncel Tuzel",
                " Hadi Pouransari"
            ]
        },
        {
            "paperId": "4945",
            "posterId": "68b",
            "title": "Improving Subgraph Recognition With Variational Graph Information Bottleneck",
            "authors": [
                "Junchi Yu",
                " Jie Cao",
                " Ran He"
            ]
        },
        {
            "paperId": "2508",
            "posterId": "69b",
            "title": "Learning Soft Estimator of Keypoint Scale and Orientation With Probabilistic Covariant Loss",
            "authors": [
                "Pei Yan",
                " Yihua Tan",
                " Shengzhou Xiong",
                " Yuan Tai",
                " Yansheng Li"
            ]
        },
        {
            "paperId": "4145",
            "posterId": "70b",
            "title": "Few-Shot Keypoint Detection With Uncertainty Learning for Unseen Species",
            "authors": [
                "Changsheng Lu",
                " Piotr Koniusz"
            ]
        }
    ],
    "Computational Photography": [
        {
            "paperId": "4111",
            "posterId": "94b",
            "title": "Deep Stereo Image Compression via Bi-Directional Coding",
            "authors": [
                "Jianjun Lei",
                " Xiangrui Liu",
                " Bo Peng",
                " Dengchao Jin",
                " Wanqing Li",
                " Jingxiao Gu"
            ]
        },
        {
            "paperId": "8934",
            "posterId": "95b",
            "title": "RFNet: Unsupervised Network for Mutually Reinforcing Multi-Modal Image Registration and Fusion",
            "authors": [
                "Han Xu",
                " Jiayi Ma",
                " Jiteng Yuan",
                " Zhuliang Le",
                " Wei Liu"
            ]
        },
        {
            "paperId": "4213",
            "posterId": "96b",
            "title": "Semi-Supervised Wide-Angle Portraits Correction by Multi-Scale Transformer",
            "authors": [
                "Fushun Zhu",
                " Shan Zhao",
                " Peng Wang",
                " Hao Wang",
                " Hua Yan",
                " Shuaicheng Liu"
            ]
        },
        {
            "paperId": "2554",
            "posterId": "97b",
            "title": "Semi-Supervised Learning of Semantic Correspondence With Pseudo-Labels",
            "authors": [
                "Jiwon Kim",
                " Kwangrok Ryoo",
                " Junyoung Seo",
                " Gyuseong Lee",
                " Daehwan Kim",
                " Hansang Cho",
                " Seungryong Kim"
            ]
        },
        {
            "paperId": "3021",
            "posterId": "98b",
            "title": "SCS-Co: Self-Consistent Style Contrastive Learning for Image Harmonization",
            "authors": [
                "Yucheng Hang",
                " Bin Xia",
                " Wenming Yang",
                " Qingmin Liao"
            ]
        },
        {
            "paperId": "3470",
            "posterId": "99b",
            "title": "Automatic Color Image Stitching Using Quaternion Rank-1 Alignment",
            "authors": [
                "Jiaxue Li",
                " Yicong Zhou"
            ]
        },
        {
            "paperId": "6712",
            "posterId": "100b",
            "title": "SpaceEdit: Learning a Unified Editing Space for Open-Domain Image Color Editing",
            "authors": [
                "Jing Shi",
                " Ning Xu",
                " Haitian Zheng",
                " Alex Smith",
                " Jiebo Luo",
                " Chenliang Xu"
            ]
        },
        {
            "paperId": "4112",
            "posterId": "101b",
            "title": "Degree-of-Linear-Polarization-Based Color Constancy",
            "authors": [
                "Taishi Ono",
                " Yuhi Kondo",
                " Legong Sun",
                " Teppei Kurita",
                " Yusuke Moriuchi"
            ]
        },
        {
            "paperId": "2170",
            "posterId": "102b",
            "title": "Point Cloud Color Constancy",
            "authors": [
                "Xiaoyan Xing",
                " Yanlin Qian",
                " Sibo Feng",
                " Yuhan Dong",
                " Jiří Matas"
            ]
        },
        {
            "paperId": "265",
            "posterId": "103b",
            "title": "Boosting View Synthesis With Residual Transfer",
            "authors": [
                "Xuejian Rong",
                " Jia-Bin Huang",
                " Ayush Saraf",
                " Changil Kim",
                " Johannes Kopf"
            ]
        },
        {
            "paperId": "5780",
            "posterId": "104b",
            "title": "Deep Hyperspectral-Depth Reconstruction Using Single Color-Dot Projection",
            "authors": [
                "Chunyu Li",
                " Yusuke Monno",
                " Masatoshi Okutomi"
            ]
        },
        {
            "paperId": "4413",
            "posterId": "105b",
            "title": "Quantization-Aware Deep Optics for Diffractive Snapshot Hyperspectral Imaging",
            "authors": [
                "Lingen Li",
                " Lizhi Wang",
                " Weitao Song",
                " Lei Zhang",
                " Zhiwei Xiong",
                " Hua Huang"
            ]
        },
        {
            "paperId": "479",
            "posterId": "106b",
            "title": "PIE-Net: Photometric Invariant Edge Guided Network for Intrinsic Image Decomposition",
            "authors": [
                "Partha Das",
                " Sezer Karaoglu",
                " Theo Gevers"
            ]
        },
        {
            "paperId": "7596",
            "posterId": "107b",
            "title": "Multimodal Material Segmentation",
            "authors": [
                "Yupeng Liang",
                " Ryosuke Wakaki",
                " Shohei Nobuhara",
                " Ko Nishino"
            ]
        },
        {
            "paperId": "6384",
            "posterId": "108b",
            "title": "Occlusion-Aware Cost Constructor for Light Field Depth Estimation",
            "authors": [
                "Yingqian Wang",
                " Longguang Wang",
                " Zhengyu Liang",
                " Jungang Yang",
                " Wei An",
                " Yulan Guo"
            ]
        },
        {
            "paperId": "815",
            "posterId": "109b",
            "title": "Learning Neural Light Fields With Ray-Space Embedding",
            "authors": [
                "Benjamin Attal",
                " Jia-Bin Huang",
                " Michael Zollhöfer",
                " Johannes Kopf",
                " Changil Kim"
            ]
        },
        {
            "paperId": "2268",
            "posterId": "110b",
            "title": "Acquiring a Dynamic Light Field Through a Single-Shot Coded Image",
            "authors": [
                "Ryoya Mizuno",
                " Keita Takahashi",
                " Michitaka Yoshida",
                " Chihiro Tsutake",
                " Toshiaki Fujii",
                " Hajime Nagahara"
            ]
        },
        {
            "paperId": "4415",
            "posterId": "111b",
            "title": "Gravitationally Lensed Black Hole Emission Tomography",
            "authors": [
                "Aviad Levis",
                " Pratul P. Srinivasan",
                " Andrew A. Chael",
                " Ren Ng",
                " Katherine L. Bouman"
            ]
        },
        {
            "paperId": "5058",
            "posterId": "112b",
            "title": "Deep Saliency Prior for Reducing Visual Distraction",
            "authors": [
                "Kfir Aberman",
                " Junfeng He",
                " Yossi Gandelsman",
                " Inbar Mosseri",
                " David E. Jacobs",
                " Kai Kohlhoff",
                " Yael Pritch",
                " Michael Rubinstein"
            ]
        },
        {
            "paperId": "8388",
            "posterId": "113b",
            "title": "Personalized Image Aesthetics Assessment With Rich Attributes",
            "authors": [
                "Yuzhe Yang",
                " Liwu Xu",
                " Leida Li",
                " Nan Qie",
                " Yaqian Li",
                " Peng Zhang",
                " Yandong Guo"
            ]
        },
        {
            "paperId": "6382",
            "posterId": "114b",
            "title": "Artistic Style Discovery With Independent Components",
            "authors": [
                "Xin Xie",
                " Yi Li",
                " Huaibo Huang",
                " Haiyan Fu",
                " Wanwan Wang",
                " Yanqing Guo"
            ]
        }
    ],
    "Scene Analysis & Understanding": [
        {
            "paperId": "2004",
            "posterId": "80a",
            "title": "Noisy Boundaries: Lemon or Lemonade for Semi-Supervised Instance Segmentation?",
            "authors": [
                "Zhenyu Wang",
                " Yali Li",
                " Shengjin Wang"
            ]
        },
        {
            "paperId": "5105",
            "posterId": "81a",
            "title": "Partial Class Activation Attention for Semantic Segmentation",
            "authors": [
                "Sun-Ao Liu",
                " Hongtao Xie",
                " Hai Xu",
                " Yongdong Zhang",
                " Qi Tian"
            ]
        },
        {
            "paperId": "7261",
            "posterId": "82a",
            "title": "Learning Affinity From Attention: End-to-End Weakly-Supervised Semantic Segmentation With Transformers",
            "authors": [
                "Lixiang Ru",
                " Yibing Zhan",
                " Baosheng Yu",
                " Bo Du"
            ]
        },
        {
            "paperId": "4156",
            "posterId": "83a",
            "title": "Towards Noiseless Object Contours for Weakly Supervised Semantic Segmentation",
            "authors": [
                "Jing Li",
                " Junsong Fan",
                " Zhaoxiang Zhang"
            ]
        },
        {
            "paperId": "7427",
            "posterId": "84a",
            "title": "Class Similarity Weighted Knowledge Distillation for Continual Semantic Segmentation",
            "authors": [
                "Minh Hieu Phan",
                " The-Anh Ta",
                " Son Lam Phung",
                " Long Tran-Thanh",
                " Abdesselam Bouzerdoum"
            ]
        },
        {
            "paperId": "4593",
            "posterId": "85a",
            "title": "Structural and Statistical Texture Knowledge Distillation for Semantic Segmentation",
            "authors": [
                "Deyi Ji",
                " Haoran Wang",
                " Mingyuan Tao",
                " Jianqiang Huang",
                " Xian-Sheng Hua",
                " Hongtao Lu"
            ]
        },
        {
            "paperId": "1567",
            "posterId": "86a",
            "title": "L2G: A Simple Local-to-Global Knowledge Transfer Framework for Weakly Supervised Semantic Segmentation",
            "authors": [
                "Peng-Tao Jiang",
                " Yuqi Yang",
                " Qibin Hou",
                " Yunchao Wei"
            ]
        },
        {
            "paperId": "573",
            "posterId": "87a",
            "title": "Weakly Supervised Semantic Segmentation Using Out-of-Distribution Data",
            "authors": [
                "Jungbeom Lee",
                " Seong Joon Oh",
                " Sangdoo Yun",
                " Junsuk Choe",
                " Eunji Kim",
                " Sungroh Yoon"
            ]
        },
        {
            "paperId": "1307",
            "posterId": "88a",
            "title": "Tree Energy Loss: Towards Sparsely Annotated Semantic Segmentation",
            "authors": [
                "Zhiyuan Liang",
                " Tiancai Wang",
                " Xiangyu Zhang",
                " Jian Sun",
                " Jianbing Shen"
            ]
        },
        {
            "paperId": "2748",
            "posterId": "89a",
            "title": "Bending Reality: Distortion-Aware Transformers for Adapting to Panoramic Semantic Segmentation",
            "authors": [
                "Jiaming Zhang",
                " Kailun Yang",
                " Chaoxiang Ma",
                " Simon Reiß",
                " Kunyu Peng",
                " Rainer Stiefelhagen"
            ]
        },
        {
            "paperId": "4586",
            "posterId": "90a",
            "title": "MM-TTA: Multi-Modal Test-Time Adaptation for 3D Semantic Segmentation",
            "authors": [
                "Inkyu Shin",
                " Yi-Hsuan Tsai",
                " Bingbing Zhuang",
                " Samuel Schulter",
                " Buyu Liu",
                " Sparsh Garg",
                " In So Kweon",
                " Kuk-Jin Yoon"
            ]
        },
        {
            "paperId": "8233",
            "posterId": "91a",
            "title": "NightLab: A Dual-Level Architecture With Hardness Detection for Segmentation at Night",
            "authors": [
                "Xueqing Deng",
                " Peng Wang",
                " Xiaochen Lian",
                " Shawn Newsam"
            ]
        },
        {
            "paperId": "6032",
            "posterId": "92a",
            "title": "Fast Point Transformer",
            "authors": [
                "Chunghyun Park",
                " Yoonwoo Jeong",
                " Minsu Cho",
                " Jaesik Park"
            ]
        },
        {
            "paperId": "7468",
            "posterId": "93a",
            "title": "RigidFlow: Self-Supervised Scene Flow Learning on Point Clouds by Local Rigidity Prior",
            "authors": [
                "Ruibo Li",
                " Chi Zhang",
                " Guosheng Lin",
                " Zhe Wang",
                " Chunhua Shen"
            ]
        },
        {
            "paperId": "807",
            "posterId": "94a",
            "title": "ConDor: Self-Supervised Canonicalization of 3D Pose for Partial Shapes",
            "authors": [
                "Rahul Sajnani",
                " Adrien Poulenard",
                " Jivitesh Jain",
                " Radhika Dua",
                " Leonidas J. Guibas",
                " Srinath Sridhar"
            ]
        },
        {
            "paperId": "1738",
            "posterId": "95a",
            "title": "DisARM: Displacement Aware Relation Module for 3D Detection",
            "authors": [
                "Yao Duan",
                " Chenyang Zhu",
                " Yuqing Lan",
                " Renjiao Yi",
                " Xinwang Liu",
                " Kai Xu"
            ]
        },
        {
            "paperId": "2722",
            "posterId": "96a",
            "title": "Learning Object Context for Novel-View Scene Layout Generation",
            "authors": [
                "Xiaotian Qiao",
                " Gerhard P. Hancke",
                " Rynson W.H. Lau"
            ]
        },
        {
            "paperId": "2166",
            "posterId": "97a",
            "title": "Weakly but Deeply Supervised Occlusion-Reasoned Parametric Road Layouts",
            "authors": [
                "Buyu Liu",
                " Bingbing Zhuang",
                " Manmohan Chandraker"
            ]
        },
        {
            "paperId": "348",
            "posterId": "98a",
            "title": "Beyond Cross-View Image Retrieval: Highly Accurate Vehicle Localization Using Satellite Image",
            "authors": [
                "Yujiao Shi",
                " Hongdong Li"
            ]
        },
        {
            "paperId": "5927",
            "posterId": "99a",
            "title": "Raw High-Definition Radar for Multi-Task Learning",
            "authors": [
                "Julien Rebut",
                " Arthur Ouaknine",
                " Waqas Malik",
                " Patrick Pérez"
            ]
        },
        {
            "paperId": "2343",
            "posterId": "100a",
            "title": "Zero Experience Required: Plug & Play Modular Transfer Learning for Semantic Visual Navigation",
            "authors": [
                "Ziad Al-Halah",
                " Santhosh Kumar Ramakrishnan",
                " Kristen Grauman"
            ]
        },
        {
            "paperId": "7169",
            "posterId": "101a",
            "title": "UKPGAN: A General Self-Supervised Keypoint Detector",
            "authors": [
                "Yang You",
                " Wenhai Liu",
                " Yanjie Ze",
                " Yong-Lu Li",
                " Weiming Wang",
                " Cewu Lu"
            ]
        },
        {
            "paperId": "5057",
            "posterId": "102a",
            "title": "Cannot See the Forest for the Trees: Aggregating Multiple Viewpoints To Better Classify Objects in Videos",
            "authors": [
                "Sukjun Hwang",
                " Miran Heo",
                " Seoung Wug Oh",
                " Seon Joo Kim"
            ]
        }
    ],
    "Navigation & Autonomous Driving": [
        {
            "paperId": "104",
            "posterId": "103a",
            "title": "Rethinking Efficient Lane Detection via Curve Modeling",
            "authors": [
                "Zhengyang Feng",
                " Shaohua Guo",
                " Xin Tan",
                " Ke Xu",
                " Min Wang",
                " Lizhuang Ma"
            ]
        },
        {
            "paperId": "5623",
            "posterId": "104a",
            "title": "Exploiting Temporal Relations on Radar Perception for Autonomous Driving",
            "authors": [
                "Peizhao Li",
                " Pu Wang",
                " Karl Berntorp",
                " Hongfu Liu"
            ]
        },
        {
            "paperId": "1321",
            "posterId": "105a",
            "title": "Towards Robust and Adaptive Motion Forecasting: A Causal Representation Perspective",
            "authors": [
                "Yuejiang Liu",
                " Riccardo Cadei",
                " Jonas Schweizer",
                " Sherwin Bahmani",
                " Alexandre Alahi"
            ]
        },
        {
            "paperId": "3631",
            "posterId": "106a",
            "title": "BE-STI: Spatial-Temporal Integrated Network for Class-Agnostic Motion Prediction With Bidirectional Enhancement",
            "authors": [
                "Yunlong Wang",
                " Hongyu Pan",
                " Jun Zhu",
                " Yu-Huan Wu",
                " Xin Zhan",
                " Kun Jiang",
                " Diange Yang"
            ]
        },
        {
            "paperId": "9886",
            "posterId": "107a",
            "title": "ScePT: Scene-Consistent, Policy-Based Trajectory Predictions for Planning",
            "authors": [
                "Yuxiao Chen",
                " Boris Ivanovic",
                " Marco Pavone"
            ]
        },
        {
            "paperId": "607",
            "posterId": "108a",
            "title": "Stochastic Trajectory Prediction via Motion Indeterminacy Diffusion",
            "authors": [
                "Tianpei Gu",
                " Guangyi Chen",
                " Junlong Li",
                " Chunze Lin",
                " Yongming Rao",
                " Jie Zhou",
                " Jiwen Lu"
            ]
        },
        {
            "paperId": "1397",
            "posterId": "109a",
            "title": "Vehicle Trajectory Prediction Works, but Not Everywhere",
            "authors": [
                "Mohammadhossein Bahari",
                " Saeed Saadatnejad",
                " Ahmad Rahimi",
                " Mohammad Shaverdikondori",
                " Amir Hossein Shahidzadeh",
                " Seyed-Mohsen Moosavi-Dezfooli",
                " Alexandre Alahi"
            ]
        },
        {
            "paperId": "9659",
            "posterId": "110a",
            "title": "LTP: Lane-Based Trajectory Prediction for Autonomous Driving",
            "authors": [
                "Jingke Wang",
                " Tengju Ye",
                " Ziqing Gu",
                " Junbo Chen"
            ]
        },
        {
            "paperId": "2468",
            "posterId": "111a",
            "title": "ONCE-3DLanes: Building Monocular 3D Lane Detection",
            "authors": [
                "Fan Yan",
                " Ming Nie",
                " Xinyue Cai",
                " Jianhua Han",
                " Hang Xu",
                " Zhen Yang",
                " Chaoqiang Ye",
                " Yanwei Fu",
                " Michael Bi Mi",
                " Li Zhang"
            ]
        },
        {
            "paperId": "10899",
            "posterId": "112a",
            "title": "Towards Driving-Oriented Metric for Lane Detection Models",
            "authors": [
                "Takami Sato",
                " Qi Alfred Chen"
            ]
        },
        {
            "paperId": "6918",
            "posterId": "113a",
            "title": "Eigenlanes: Data-Driven Lane Descriptors for Structurally Diverse Lanes",
            "authors": [
                "Dongkwon Jin",
                " Wonhui Park",
                " Seong-Gyun Jeong",
                " Heeyeon Kwon",
                " Chang-Su Kim"
            ]
        },
        {
            "paperId": "5120",
            "posterId": "114a",
            "title": "LIFT: Learning 4D LiDAR Image Fusion Transformer for 3D Object Detection",
            "authors": [
                "Yihan Zeng",
                " Da Zhang",
                " Chunwei Wang",
                " Zhenwei Miao",
                " Ting Liu",
                " Xin Zhan",
                " Dayang Hao",
                " Chao Ma"
            ]
        },
        {
            "paperId": "1664",
            "posterId": "115a",
            "title": "DeepFusion: Lidar-Camera Deep Fusion for Multi-Modal 3D Object Detection",
            "authors": [
                "Yingwei Li",
                " Adams Wei Yu",
                " Tianjian Meng",
                " Ben Caine",
                " Jiquan Ngiam",
                " Daiyi Peng",
                " Junyang Shen",
                " Yifeng Lu",
                " Denny Zhou",
                " Quoc V. Le",
                " Alan Yuille",
                " Mingxing Tan"
            ]
        },
        {
            "paperId": "9131",
            "posterId": "116a",
            "title": "A Versatile Multi-View Framework for LiDAR-Based 3D Object Detection With Guidance From Panoptic Segmentation",
            "authors": [
                "Hamidreza Fazlali",
                " Yixuan Xu",
                " Yuan Ren",
                " Bingbing Liu"
            ]
        },
        {
            "paperId": "7091",
            "posterId": "117a",
            "title": "Forecasting From LiDAR via Future Object Detection",
            "authors": [
                "Neehar Peri",
                " Jonathon Luiten",
                " Mengtian Li",
                " Aljoša Ošep",
                " Laura Leal-Taixé",
                " Deva Ramanan"
            ]
        },
        {
            "paperId": "5998",
            "posterId": "118a",
            "title": "RIDDLE: Lidar Data Compression With Range Image Deep Delta Encoding",
            "authors": [
                "Xuanyu Zhou",
                " Charles R. Qi",
                " Yin Zhou",
                " Dragomir Anguelov"
            ]
        },
        {
            "paperId": "3364",
            "posterId": "119a",
            "title": "Learning From All Vehicles",
            "authors": [
                "Dian Chen",
                " Philipp Krähenbühl"
            ]
        },
        {
            "paperId": "10331",
            "posterId": "120a",
            "title": "Is Mapping Necessary for Realistic PointGoal Navigation?",
            "authors": [
                "Ruslan Partsey",
                " Erik Wijmans",
                " Naoki Yokoyama",
                " Oles Dobosevych",
                " Dhruv Batra",
                " Oleksandr Maksymets"
            ]
        },
        {
            "paperId": "9772",
            "posterId": "121a",
            "title": "Symmetry-Aware Neural Architecture for Embodied Visual Exploration",
            "authors": [
                "Shuang Liu",
                " Takayuki Okatani"
            ]
        },
        {
            "paperId": "6482",
            "posterId": "122a",
            "title": "Coopernaut: End-to-End Driving With Cooperative Perception for Networked Vehicles",
            "authors": [
                "Jiaxun Cui",
                " Hang Qiu",
                " Dian Chen",
                " Peter Stone",
                " Yuke Zhu"
            ]
        },
        {
            "paperId": "10621",
            "posterId": "123a",
            "title": "Topology Preserving Local Road Network Estimation From Single Onboard Camera Image",
            "authors": [
                "Yigit Baran Can",
                " Alexander Liniger",
                " Danda Pani Paudel",
                " Luc Van Gool"
            ]
        },
        {
            "paperId": "6744",
            "posterId": "124a",
            "title": "Coupling Vision and Proprioception for Navigation of Legged Robots",
            "authors": [
                "Zipeng Fu",
                " Ashish Kumar",
                " Ananye Agarwal",
                " Haozhi Qi",
                " Jitendra Malik",
                " Deepak Pathak"
            ]
        },
        {
            "paperId": "10063",
            "posterId": "125a",
            "title": "Pyramid Architecture for Multi-Scale Processing in Point Cloud Segmentation",
            "authors": [
                "Dong Nie",
                " Rui Lan",
                " Ling Wang",
                " Xiaofeng Ren"
            ]
        },
        {
            "paperId": "9391",
            "posterId": "126a",
            "title": "3D-VField: Adversarial Augmentation of Point Clouds for Domain Generalization in 3D Object Detection",
            "authors": [
                "Alexander Lehner",
                " Stefano Gasperini",
                " Alvaro Marcos-Ramiro",
                " Michael Schmidt",
                " Mohammad-Ali Nikouei Mahani",
                " Nassir Navab",
                " Benjamin Busam",
                " Federico Tombari"
            ]
        },
        {
            "paperId": "4385",
            "posterId": "127a",
            "title": "Generating Useful Accident-Prone Driving Scenarios via a Learned Traffic Prior",
            "authors": [
                "Davis Rempe",
                " Jonah Philion",
                " Leonidas J. Guibas",
                " Sanja Fidler",
                " Or Litany"
            ]
        },
        {
            "paperId": "2537",
            "posterId": "128a",
            "title": "SelfD: Self-Learning Large-Scale Driving Policies From the Web",
            "authors": [
                "Jimuyang Zhang",
                " Ruizhao Zhu",
                " Eshed Ohn-Bar"
            ]
        },
        {
            "paperId": "5244",
            "posterId": "129a",
            "title": "Towards Real-World Navigation With Deep Differentiable Planners",
            "authors": [
                "Shu Ishida",
                " João F. Henriques"
            ]
        },
        {
            "paperId": "10481",
            "posterId": "130a",
            "title": "Privacy Preserving Partial Localization",
            "authors": [
                "Marcel Geppert",
                " Viktor Larsson",
                " Johannes L. Schönberger",
                " Marc Pollefeys"
            ]
        },
        {
            "paperId": "6490",
            "posterId": "131a",
            "title": "Efficient Large-Scale Localization by Global Instance Recognition",
            "authors": [
                "Fei Xue",
                " Ignas Budvytis",
                " Daniel Olmeda Reino",
                " Roberto Cipolla"
            ]
        },
        {
            "paperId": "5459",
            "posterId": "132a",
            "title": "CrossLoc: Scalable Aerial Localization Assisted by Multimodal Synthetic Data",
            "authors": [
                "Qi Yan",
                " Jianhao Zheng",
                " Simon Reding",
                " Shanci Li",
                " Iordan Doytchinov"
            ]
        }
    ],
    "Vision & Graphics": [
        {
            "paperId": "84",
            "posterId": "242a",
            "title": "De-Rendering 3D Objects in the Wild",
            "authors": [
                "Felix Wimbauer",
                " Shangzhe Wu",
                " Christian Rupprecht"
            ]
        },
        {
            "paperId": "4234",
            "posterId": "243a",
            "title": "Neural Fields As Learnable Kernels for 3D Reconstruction",
            "authors": [
                "Francis Williams",
                " Zan Gojcic",
                " Sameh Khamis",
                " Denis Zorin",
                " Joan Bruna",
                " Sanja Fidler",
                " Or Litany"
            ]
        },
        {
            "paperId": "3715",
            "posterId": "244a",
            "title": "HyperStyle: StyleGAN Inversion With HyperNetworks for Real Image Editing",
            "authors": [
                "Yuval Alaluf",
                " Omer Tov",
                " Ron Mokady",
                " Rinon Gal",
                " Amit Bermano"
            ]
        },
        {
            "paperId": "2744",
            "posterId": "245a",
            "title": "3PSDF: Three-Pole Signed Distance Function for Learning Surfaces With Arbitrary Topologies",
            "authors": [
                "Weikai Chen",
                " Cheng Lin",
                " Weiyang Li",
                " Bo Yang"
            ]
        },
        {
            "paperId": "2410",
            "posterId": "246a",
            "title": "Pop-Out Motion: 3D-Aware Image Deformation via Learning the Shape Laplacian",
            "authors": [
                "Jihyun Lee",
                " Minhyuk Sung",
                " Hyunjin Kim",
                " Tae-Kyun Kim"
            ]
        },
        {
            "paperId": "9567",
            "posterId": "247a",
            "title": "Deep Image-Based Illumination Harmonization",
            "authors": [
                "Zhongyun Bao",
                " Chengjiang Long",
                " Gang Fu",
                " Daquan Liu",
                " Yuanzhen Li",
                " Jiaming Wu",
                " Chunxia Xiao"
            ]
        },
        {
            "paperId": "1834",
            "posterId": "248a",
            "title": "Glass: Geometric Latent Augmentation for Shape Spaces",
            "authors": [
                "Sanjeev Muralikrishnan",
                " Siddhartha Chaudhuri",
                " Noam Aigerman",
                " Vladimir G. Kim",
                " Matthew Fisher",
                " Niloy J. Mitra"
            ]
        },
        {
            "paperId": "1559",
            "posterId": "249a",
            "title": "PhotoScene: Photorealistic Material and Lighting Transfer for Indoor Scenes",
            "authors": [
                "Yu-Ying Yeh",
                " Zhengqin Li",
                " Yannick Hold-Geoffroy",
                " Rui Zhu",
                " Zexiang Xu",
                " Miloš Hašan",
                " Kalyan Sunkavalli",
                " Manmohan Chandraker"
            ]
        },
        {
            "paperId": "1478",
            "posterId": "250a",
            "title": "Neural Template: Topology-Aware Reconstruction and Disentangled Generation of 3D Meshes",
            "authors": [
                "Ka-Hei Hui",
                " Ruihui Li",
                " Jingyu Hu",
                " Chi-Wing Fu"
            ]
        },
        {
            "paperId": "9364",
            "posterId": "251a",
            "title": "Neural Mesh Simplification",
            "authors": [
                "Rolandos Alexandros Potamias",
                " Stylianos Ploumpis",
                " Stefanos Zafeiriou"
            ]
        },
        {
            "paperId": "6486",
            "posterId": "252a",
            "title": "SkinningNet: Two-Stream Graph Convolutional Neural Network for Skinning Prediction of Synthetic Characters",
            "authors": [
                "Albert Mosella-Montoro",
                " Javier Ruiz-Hidalgo"
            ]
        },
        {
            "paperId": "7818",
            "posterId": "253a",
            "title": "CLIP-Forge: Towards Zero-Shot Text-To-Shape Generation",
            "authors": [
                "Aditya Sanghi",
                " Hang Chu",
                " Joseph G. Lambourne",
                " Ye Wang",
                " Chin-Yi Cheng",
                " Marco Fumero",
                " Kamal Rahimi Malekshan"
            ]
        },
        {
            "paperId": "7841",
            "posterId": "254a",
            "title": "UNIST: Unpaired Neural Implicit Shape Translation Network",
            "authors": [
                "Qimin Chen",
                " Johannes Merz",
                " Aditya Sanghi",
                " Hooman Shayani",
                " Ali Mahdavi-Amiri",
                " Hao Zhang"
            ]
        },
        {
            "paperId": "1800",
            "posterId": "255a",
            "title": "CoNeRF: Controllable Neural Radiance Fields",
            "authors": [
                "Kacper Kania",
                " Kwang Moo Yi",
                " Marek Kowalski",
                " Tomasz Trzciński",
                " Andrea Tagliasacchi"
            ]
        },
        {
            "paperId": "6407",
            "posterId": "256a",
            "title": "Neural Points: Point Cloud Representation With Neural Fields for Arbitrary Upsampling",
            "authors": [
                "Wanquan Feng",
                " Jin Li",
                " Hongrui Cai",
                " Xiaonan Luo",
                " Juyong Zhang"
            ]
        },
        {
            "paperId": "8338",
            "posterId": "257a",
            "title": "Modeling Indirect Illumination for Inverse Rendering",
            "authors": [
                "Yuanqing Zhang",
                " Jiaming Sun",
                " Xingyi He",
                " Huan Fu",
                " Rongfei Jia",
                " Xiaowei Zhou"
            ]
        },
        {
            "paperId": "3519",
            "posterId": "258a",
            "title": "Neural Head Avatars From Monocular RGB Videos",
            "authors": [
                "Philip-William Grassal",
                " Malte Prinzler",
                " Titus Leistner",
                " Carsten Rother",
                " Matthias Nießner",
                " Justus Thies"
            ]
        },
        {
            "paperId": "2341",
            "posterId": "259a",
            "title": "DeepCurrents: Learning Implicit Representations of Shapes With Boundaries",
            "authors": [
                "David Palmer",
                " Dmitriy Smirnov",
                " Stephanie Wang",
                " Albert Chern",
                " Justin Solomon"
            ]
        }
    ],
    "Biometrics, Face & Gestures, and Medical Image Analysis": [
        {
            "paperId": "4335",
            "posterId": "1b",
            "title": "Escaping Data Scarcity for High-Resolution Heterogeneous Face Hallucination",
            "authors": [
                "Yiqun Mei",
                " Pengfei Guo",
                " Vishal M. Patel"
            ]
        },
        {
            "paperId": "5110",
            "posterId": "2b",
            "title": "AnyFace: Free-Style Text-To-Face Synthesis and Manipulation",
            "authors": [
                "Jianxin Sun",
                " Qiyao Deng",
                " Qi Li",
                " Muyi Sun",
                " Min Ren",
                " Zhenan Sun"
            ]
        },
        {
            "paperId": "5301",
            "posterId": "3b",
            "title": "General Facial Representation Learning in a Visual-Linguistic Manner",
            "authors": [
                "Yinglin Zheng",
                " Hao Yang",
                " Ting Zhang",
                " Jianmin Bao",
                " Dongdong Chen",
                " Yangyu Huang",
                " Lu Yuan",
                " Dong Chen",
                " Ming Zeng",
                " Fang Wen"
            ]
        },
        {
            "paperId": "5269",
            "posterId": "4b",
            "title": "Self-Supervised Learning of Adversarial Example: Towards Good Generalizations for Deepfake Detection",
            "authors": [
                "Liang Chen",
                " Yong Zhang",
                " Yibing Song",
                " Lingqiao Liu",
                " Jue Wang"
            ]
        },
        {
            "paperId": "1219",
            "posterId": "5b",
            "title": "Detecting Deepfakes With Self-Blended Images",
            "authors": [
                "Kaede Shiohara",
                " Toshihiko Yamasaki"
            ]
        },
        {
            "paperId": "5967",
            "posterId": "6b",
            "title": "3D Shape Variational Autoencoder Latent Disentanglement via Mini-Batch Feature Swapping for Bodies and Faces",
            "authors": [
                "Simone Foti",
                " Bongjin Koo",
                " Danail Stoyanov",
                " Matthew J. Clarkson"
            ]
        },
        {
            "paperId": "9638",
            "posterId": "7b",
            "title": "Evaluation-Oriented Knowledge Distillation for Deep Face Recognition",
            "authors": [
                "Yuge Huang",
                " Jiaxiang Wu",
                " Xingkun Xu",
                " Shouhong Ding"
            ]
        },
        {
            "paperId": "6682",
            "posterId": "8b",
            "title": "AdaFace: Quality Adaptive Margin for Face Recognition",
            "authors": [
                "Minchul Kim",
                " Anil K. Jain",
                " Xiaoming Liu"
            ]
        },
        {
            "paperId": "6920",
            "posterId": "9b",
            "title": "Moving Window Regression: A Novel Approach to Ordinal Regression",
            "authors": [
                "Nyeong-Ho Shin",
                " Seon-Ho Lee",
                " Chang-Su Kim"
            ]
        },
        {
            "paperId": "10531",
            "posterId": "10b",
            "title": "FaceFormer: Speech-Driven 3D Facial Animation With Transformers",
            "authors": [
                "Yingruo Fan",
                " Zhaojiang Lin",
                " Jun Saito",
                " Wenping Wang",
                " Taku Komura"
            ]
        },
        {
            "paperId": "11053",
            "posterId": "11b",
            "title": "Neural Emotion Director: Speech-Preserving Semantic Control of Facial Expressions in “In-the-Wild” Videos",
            "authors": [
                "Foivos Paraperas Papantoniou",
                " Panagiotis P. Filntisis",
                " Petros Maragos",
                " Anastasios Roussos"
            ]
        },
        {
            "paperId": "229",
            "posterId": "12b",
            "title": "Deep Decomposition for Stochastic Normal-Abnormal Transport",
            "authors": [
                "Peirong Liu",
                " Yueh Lee",
                " Stephen Aylward",
                " Marc Niethammer"
            ]
        },
        {
            "paperId": "3114",
            "posterId": "13b",
            "title": "DTFD-MIL: Double-Tier Feature Distillation Multiple Instance Learning for Histopathology Whole Slide Image Classification",
            "authors": [
                "Hongrun Zhang",
                " Yanda Meng",
                " Yitian Zhao",
                " Yihong Qiao",
                " Xiaoyun Yang",
                " Sarah E. Coupland",
                " Yalin Zheng"
            ]
        },
        {
            "paperId": "10426",
            "posterId": "14b",
            "title": "Node-Aligned Graph Convolutional Network for Whole-Slide Image Representation and Classification",
            "authors": [
                "Yonghang Guan",
                " Jun Zhang",
                " Kuan Tian",
                " Sen Yang",
                " Pei Dong",
                " Jinxi Xiang",
                " Wei Yang",
                " Junzhou Huang",
                " Yuyao Zhang",
                " Xiao Han"
            ]
        },
        {
            "paperId": "10994",
            "posterId": "15b",
            "title": "Temporal Context Matters: Enhancing Single Image Prediction With Disease Progression Representations",
            "authors": [
                "Aishik Konwer",
                " Xuan Xu",
                " Joseph Bae",
                " Chao Chen",
                " Prateek Prasanna"
            ]
        }
    ],
    "Scene & Shape Analysis and Understanding": [
        {
            "paperId": "4710",
            "posterId": "16b",
            "title": "VRDFormer: End-to-End Video Visual Relation Detection With Transformers",
            "authors": [
                "Sipeng Zheng",
                " Shizhe Chen",
                " Qin Jin"
            ]
        },
        {
            "paperId": "720",
            "posterId": "17b",
            "title": "Video K-Net: A Simple, Strong, and Unified Baseline for Video Segmentation",
            "authors": [
                "Xiangtai Li",
                " Wenwei Zhang",
                " Jiangmiao Pang",
                " Kai Chen",
                " Guangliang Cheng",
                " Yunhai Tong",
                " Chen Change Loy"
            ]
        },
        {
            "paperId": "9896",
            "posterId": "18b",
            "title": "Visual Acoustic Matching",
            "authors": [
                "Changan Chen",
                " Ruohan Gao",
                " Paul Calamia",
                " Kristen Grauman"
            ]
        },
        {
            "paperId": "5847",
            "posterId": "19b",
            "title": "The Devil Is in the Labels: Noisy Label Correction for Robust Scene Graph Generation",
            "authors": [
                "Lin Li",
                " Long Chen",
                " Yifeng Huang",
                " Zhimeng Zhang",
                " Songyang Zhang",
                " Jun Xiao"
            ]
        },
        {
            "paperId": "4283",
            "posterId": "20b",
            "title": "Learning Multiple Dense Prediction Tasks From Partially Annotated Data",
            "authors": [
                "Wei-Hong Li",
                " Xialei Liu",
                " Hakan Bilen"
            ]
        },
        {
            "paperId": "9443",
            "posterId": "21b",
            "title": "PONI: Potential Functions for ObjectGoal Navigation With Interaction-Free Learning",
            "authors": [
                "Santhosh Kumar Ramakrishnan",
                " Devendra Singh Chaplot",
                " Ziad Al-Halah",
                " Jitendra Malik",
                " Kristen Grauman"
            ]
        },
        {
            "paperId": "5513",
            "posterId": "22b",
            "title": "Continual Stereo Matching of Continuous Driving Scenes With Growing Architecture",
            "authors": [
                "Chenghao Zhang",
                " Kun Tian",
                " Bin Fan",
                " Gaofeng Meng",
                " Zhaoxiang Zhang",
                " Chunhong Pan"
            ]
        },
        {
            "paperId": "5826",
            "posterId": "23b",
            "title": "FIFO: Learning Fog-Invariant Features for Foggy Scene Segmentation",
            "authors": [
                "Sohyun Lee",
                " Taeyoung Son",
                " Suha Kwak"
            ]
        },
        {
            "paperId": "3020",
            "posterId": "24b",
            "title": "Both Style and Fog Matter: Cumulative Domain Adaptation for Semantic Foggy Scene Understanding",
            "authors": [
                "Xianzheng Ma",
                " Zhixiang Wang",
                " Yacheng Zhan",
                " Yinqiang Zheng",
                " Zheng Wang",
                " Dengxin Dai",
                " Chia-Wen Lin"
            ]
        },
        {
            "paperId": "11019",
            "posterId": "25b",
            "title": "Equivariant Point Cloud Analysis via Learning Orientations for Message Passing",
            "authors": [
                "Shitong Luo",
                " Jiahan Li",
                " Jiaqi Guan",
                " Yufeng Su",
                " Chaoran Cheng",
                " Jian Peng",
                " Jianzhu Ma"
            ]
        },
        {
            "paperId": "2137",
            "posterId": "26b",
            "title": "Surface Representation for Point Clouds",
            "authors": [
                "Haoxi Ran",
                " Jun Liu",
                " Chengjie Wang"
            ]
        },
        {
            "paperId": "3284",
            "posterId": "27b",
            "title": "Not All Points Are Equal: Learning Highly Efficient Point-Based Detectors for 3D LiDAR Point Clouds",
            "authors": [
                "Yifan Zhang",
                " Qingyong Hu",
                " Guoquan Xu",
                " Yanxin Ma",
                " Jianwei Wan",
                " Yulan Guo"
            ]
        },
        {
            "paperId": "3846",
            "posterId": "28b",
            "title": "3D Common Corruptions and Data Augmentation",
            "authors": [
                "Oğuzhan Fatih Kar",
                " Teresa Yeo",
                " Andrei Atanov",
                " Amir Zamir"
            ]
        },
        {
            "paperId": "4027",
            "posterId": "29b",
            "title": "INS-Conv: Incremental Sparse Convolution for Online 3D Segmentation",
            "authors": [
                "Leyao Liu",
                " Tian Zheng",
                " Yun-Jou Lin",
                " Kai Ni",
                " Lu Fang"
            ]
        },
        {
            "paperId": "11446",
            "posterId": "30b",
            "title": "How Much Does Input Data Type Impact Final Face Model Accuracy?",
            "authors": [
                "Jiahao Luo",
                " Fahim Hasan Khan",
                " Issei Mori",
                " Akila de Silva",
                " Eric Sandoval Ruezga",
                " Minghao Liu",
                " Alex Pang",
                " James Davis"
            ]
        }
    ],
    "Datasets & Evaluation, Action & Event Recognition, and Visual Question Answering": [
        {
            "paperId": "7484",
            "posterId": "31b",
            "title": "Ego4D: Around the World in 3,000 Hours of Egocentric Video",
            "authors": [
                "Kristen Grauman",
                " Andrew Westbury",
                " Eugene Byrne",
                " Zachary Chavis",
                " Antonino Furnari",
                " Rohit Girdhar",
                " Jackson Hamburger",
                " Hao Jiang",
                " Miao Liu",
                " Xingyu Liu",
                " Miguel Martin",
                " Tushar Nagarajan",
                " Ilija Radosavovic",
                " Santhosh Kumar Ramakrishnan",
                " Fiona Ryan",
                " Jayant Sharma",
                " Michael Wray",
                " Mengmeng Xu",
                " Eric Zhongcong Xu",
                " Chen Zhao",
                " Siddhant Bansal",
                " Dhruv Batra",
                " Vincent Cartillier",
                " Sean Crane",
                " Tien Do",
                " Morrie Doulaty",
                " Akshay Erapalli",
                " Christoph Feichtenhofer",
                " Adriano Fragomeni",
                " Qichen Fu",
                " Abrham Gebreselasie",
                " Cristina González",
                " James Hillis",
                " Xuhua Huang",
                " Yifei Huang",
                " Wenqi Jia",
                " Weslie Khoo",
                " Jáchym Kolář",
                " Satwik Kottur",
                " Anurag Kumar",
                " Federico Landini",
                " Chao Li",
                " Yanghao Li",
                " Zhenqiang Li",
                " Karttikeya Mangalam",
                " Raghava Modhugu",
                " Jonathan Munro",
                " Tullie Murrell",
                " Takumi Nishiyasu",
                " Will Price",
                " Paola Ruiz",
                " Merey Ramazanova",
                " Leda Sari",
                " Kiran Somasundaram",
                " Audrey Southerland",
                " Yusuke Sugano",
                " Ruijie Tao",
                " Minh Vo",
                " Yuchen Wang",
                " Xindi Wu",
                " Takuma Yagi",
                " Ziwei Zhao",
                " Yunyi Zhu",
                " Pablo Arbeláez",
                " David Crandall",
                " Dima Damen",
                " Giovanni Maria Farinella",
                " Christian Fuegen",
                " Bernard Ghanem",
                " Vamsi Krishna Ithapu",
                " C. V. Jawahar",
                " Hanbyul Joo",
                " Kris Kitani",
                " Haizhou Li",
                " Richard Newcombe",
                " Aude Oliva",
                " Hyun Soo Park",
                " James M. Rehg",
                " Yoichi Sato",
                " Jianbo Shi",
                " Mike Zheng Shou",
                " Antonio Torralba",
                " Lorenzo Torresani",
                " Mingfei Yan",
                " Jitendra Malik"
            ]
        },
        {
            "paperId": "10504",
            "posterId": "32b",
            "title": "TransRAC: Encoding Multi-Scale Temporal Correlation With Transformers for Repetitive Action Counting",
            "authors": [
                "Huazhang Hu",
                " Sixun Dong",
                " Yiqun Zhao",
                " Dongze Lian",
                " Zhengxin Li",
                " Shenghua Gao"
            ]
        },
        {
            "paperId": "5075",
            "posterId": "33b",
            "title": "Animal Kingdom: A Large and Diverse Dataset for Animal Behavior Understanding",
            "authors": [
                "Xun Long Ng",
                " Kian Eng Ong",
                " Qichen Zheng",
                " Yun Ni",
                " Si Yong Yeo",
                " Jun Liu"
            ]
        },
        {
            "paperId": "2465",
            "posterId": "34b",
            "title": "vCLIMB: A Novel Video Class Incremental Learning Benchmark",
            "authors": [
                "Andrés Villa",
                " Kumail Alhamoud",
                " Victor Escorcia",
                " Fabian Caba",
                " Juan León Alcázar",
                " Bernard Ghanem"
            ]
        },
        {
            "paperId": "2221",
            "posterId": "35b",
            "title": "Opening Up Open World Tracking",
            "authors": [
                "Yang Liu",
                " Idil Esen Zulfikar",
                " Jonathon Luiten",
                " Achal Dave",
                " Deva Ramanan",
                " Bastian Leibe",
                " Aljoša Ošep",
                " Laura Leal-Taixé"
            ]
        },
        {
            "paperId": "1795",
            "posterId": "36b",
            "title": "Bongard-HOI: Benchmarking Few-Shot Visual Reasoning for Human-Object Interactions",
            "authors": [
                "Huaizu Jiang",
                " Xiaojian Ma",
                " Weili Nie",
                " Zhiding Yu",
                " Yuke Zhu",
                " Anima Anandkumar"
            ]
        },
        {
            "paperId": "8910",
            "posterId": "37b",
            "title": "CNN Filter DB: An Empirical Investigation of Trained Convolutional Filters",
            "authors": [
                "Paul Gavrikov",
                " Janis Keuper"
            ]
        },
        {
            "paperId": "11289",
            "posterId": "38b",
            "title": "Failure Modes of Domain Generalization Algorithms",
            "authors": [
                "Tigran Galstyan",
                " Hrayr Harutyunyan",
                " Hrant Khachatrian",
                " Greg Ver Steeg",
                " Aram Galstyan"
            ]
        },
        {
            "paperId": "9398",
            "posterId": "39b",
            "title": "A Comprehensive Study of Image Classification Model Sensitivity to Foregrounds, Backgrounds, and Visual Attributes",
            "authors": [
                "Mazda Moayeri",
                " Phillip Pope",
                " Yogesh Balaji",
                " Soheil Feizi"
            ]
        },
        {
            "paperId": "6567",
            "posterId": "40b",
            "title": "Grounding Answers for Visual Questions Asked by Visually Impaired People",
            "authors": [
                "Chongyan Chen",
                " Samreen Anjum",
                " Danna Gurari"
            ]
        },
        {
            "paperId": "6719",
            "posterId": "41b",
            "title": "Learning To Answer Questions in Dynamic Audio-Visual Scenarios",
            "authors": [
                "Guangyao Li",
                " Yake Wei",
                " Yapeng Tian",
                " Chenliang Xu",
                " Ji-Rong Wen",
                " Di Hu"
            ]
        },
        {
            "paperId": "1780",
            "posterId": "42b",
            "title": "Episodic Memory Question Answering",
            "authors": [
                "Samyak Datta",
                " Sameer Dharur",
                " Vincent Cartillier",
                " Ruta Desai",
                " Mukul Khanna",
                " Dhruv Batra",
                " Devi Parikh"
            ]
        },
        {
            "paperId": "11561",
            "posterId": "43b",
            "title": "ScanQA: 3D Question Answering for Spatial Scene Understanding",
            "authors": [
                "Daichi Azuma",
                " Taiki Miyanishi",
                " Shuhei Kurita",
                " Motoaki Kawanabe"
            ]
        },
        {
            "paperId": "5943",
            "posterId": "44b",
            "title": "Learning Part Segmentation Through Unsupervised Domain Adaptation From Synthetic Vehicles",
            "authors": [
                "Qing Liu",
                " Adam Kortylewski",
                " Zhishuai Zhang",
                " Zizhang Li",
                " Mengqi Guo",
                " Qihao Liu",
                " Xiaoding Yuan",
                " Jiteng Mu",
                " Weichao Qiu",
                " Alan Yuille"
            ]
        },
        {
            "paperId": "8893",
            "posterId": "45b",
            "title": "BTS: A Bi-Lingual Benchmark for Text Segmentation in the Wild",
            "authors": [
                "Xixi Xu",
                " Zhongang Qi",
                " Jianqi Ma",
                " Honglun Zhang",
                " Ying Shan",
                " Xiaohu Qie"
            ]
        }
    ],
    "Scene Analysis and Understanding": [
        {
            "paperId": "98",
            "posterId": "71b",
            "title": "Stacked Hybrid-Attention and Group Collaborative Learning for Unbiased Scene Graph Generation",
            "authors": [
                "Xingning Dong",
                " Tian Gan",
                " Xuemeng Song",
                " Jianlong Wu",
                " Yuan Cheng",
                " Liqiang Nie"
            ]
        },
        {
            "paperId": "2849",
            "posterId": "72b",
            "title": "Structured Sparse R-CNN for Direct Scene Graph Generation",
            "authors": [
                "Yao Teng",
                " Limin Wang"
            ]
        },
        {
            "paperId": "10248",
            "posterId": "73b",
            "title": "PPDL: Predicate Probability Distribution Based Loss for Unbiased Scene Graph Generation",
            "authors": [
                "Wei Li",
                " Haiwei Zhang",
                " Qijie Bai",
                " Guoqing Zhao",
                " Ning Jiang",
                " Xiaojie Yuan"
            ]
        },
        {
            "paperId": "3738",
            "posterId": "74b",
            "title": "RU-Net: Regularized Unrolling Network for Scene Graph Generation",
            "authors": [
                "Xin Lin",
                " Changxing Ding",
                " Jing Zhang",
                " Yibing Zhan",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "1142",
            "posterId": "75b",
            "title": "Fine-Grained Predicates Learning for Scene Graph Generation",
            "authors": [
                "Xinyu Lyu",
                " Lianli Gao",
                " Yuyu Guo",
                " Zhou Zhao",
                " Hao Huang",
                " Heng Tao Shen",
                " Jingkuan Song"
            ]
        },
        {
            "paperId": "3323",
            "posterId": "76b",
            "title": "HL-Net: Heterophily Learning Network for Scene Graph Generation",
            "authors": [
                "Xin Lin",
                " Changxing Ding",
                " Yibing Zhan",
                " Zijian Li",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "10227",
            "posterId": "77b",
            "title": "SGTR: End-to-End Scene Graph Generation With Transformer",
            "authors": [
                "Rongjie Li",
                " Songyang Zhang",
                " Xuming He"
            ]
        },
        {
            "paperId": "6703",
            "posterId": "78b",
            "title": "Classification-Then-Grounding: Reformulating Video Scene Graphs As Temporal Bipartite Graphs",
            "authors": [
                "Kaifeng Gao",
                " Long Chen",
                " Yulei Niu",
                " Jian Shao",
                " Jun Xiao"
            ]
        },
        {
            "paperId": "8205",
            "posterId": "79b",
            "title": "RelTransformer: A Transformer-Based Long-Tail Visual Relationship Recognition",
            "authors": [
                "Jun Chen",
                " Aniket Agarwal",
                " Sherif Abdelkarim",
                " Deyao Zhu",
                " Mohamed Elhoseiny"
            ]
        },
        {
            "paperId": "10369",
            "posterId": "80b",
            "title": "Spatial Commonsense Graph for Object Localisation in Partial Scenes",
            "authors": [
                "Francesco Giuliari",
                " Geri Skenderi",
                " Marco Cristani",
                " Yiming Wang",
                " Alessio Del Bue"
            ]
        },
        {
            "paperId": "4148",
            "posterId": "81b",
            "title": "The Pedestrian Next to the Lamppost : Adaptive Object Graphs for Better Instantaneous Mapping",
            "authors": [
                "Avishkar Saha",
                " Oscar Mendez",
                " Chris Russell",
                " Richard Bowden"
            ]
        },
        {
            "paperId": "7832",
            "posterId": "82b",
            "title": "Category-Aware Transformer Network for Better Human-Object Interaction Detection",
            "authors": [
                "Leizhen Dong",
                " Zhimin Li",
                " Kunlun Xu",
                " Zhijun Zhang",
                " Luxin Yan",
                " Sheng Zhong",
                " Xu Zou"
            ]
        },
        {
            "paperId": "7619",
            "posterId": "83b",
            "title": "Exploring Structure-Aware Transformer Over Interaction Proposals for Human-Object Interaction Detection",
            "authors": [
                "Yong Zhang",
                " Yingwei Pan",
                " Ting Yao",
                " Rui Huang",
                " Tao Mei",
                " Chang-Wen Chen"
            ]
        },
        {
            "paperId": "3379",
            "posterId": "84b",
            "title": "Distillation Using Oracle Queries for Transformer-Based Human-Object Interaction Detection",
            "authors": [
                "Xian Qu",
                " Changxing Ding",
                " Xingao Li",
                " Xubin Zhong",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "10087",
            "posterId": "85b",
            "title": "Human-Object Interaction Detection via Disentangled Transformer",
            "authors": [
                "Desen Zhou",
                " Zhichao Liu",
                " Jian Wang",
                " Leshan Wang",
                " Tao Hu",
                " Errui Ding",
                " Jingdong Wang"
            ]
        },
        {
            "paperId": "5684",
            "posterId": "86b",
            "title": "MSTR: Multi-Scale Transformer for End-to-End Human-Object Interaction Detection",
            "authors": [
                "Bumsoo Kim",
                " Jonghwan Mun",
                " Kyoung-Woon On",
                " Minchul Shin",
                " Junhyun Lee",
                " Eun-Sol Kim"
            ]
        },
        {
            "paperId": "7237",
            "posterId": "87b",
            "title": "GaTector: A Unified Framework for Gaze Object Prediction",
            "authors": [
                "Binglu Wang",
                " Tao Hu",
                " Baoshan Li",
                " Xiaojuan Chen",
                " Zhijie Zhang"
            ]
        },
        {
            "paperId": "6242",
            "posterId": "88b",
            "title": "STCrowd: A Multimodal Dataset for Pedestrian Perception in Crowded Scenes",
            "authors": [
                "Peishan Cong",
                " Xinge Zhu",
                " Feng Qiao",
                " Yiming Ren",
                " Xidong Peng",
                " Yuenan Hou",
                " Lan Xu",
                " Ruigang Yang",
                " Dinesh Manocha",
                " Yuexin Ma"
            ]
        },
        {
            "paperId": "7926",
            "posterId": "89b",
            "title": "Crowd Counting in the Frequency Domain",
            "authors": [
                "Weibo Shu",
                " Jia Wan",
                " Kay Chen Tan",
                " Sam Kwong",
                " Antoni B. Chan"
            ]
        },
        {
            "paperId": "3876",
            "posterId": "90b",
            "title": "Boosting Crowd Counting via Multifaceted Attention",
            "authors": [
                "Hui Lin",
                " Zhiheng Ma",
                " Rongrong Ji",
                " Yaowei Wang",
                " Xiaopeng Hong"
            ]
        },
        {
            "paperId": "6137",
            "posterId": "91b",
            "title": "Rethinking Spatial Invariance of Convolutional Networks for Object Counting",
            "authors": [
                "Zhi-Qi Cheng",
                " Qi Dai",
                " Hong Li",
                " Jingkuan Song",
                " Xiao Wu",
                " Alexander G. Hauptmann"
            ]
        },
        {
            "paperId": "6322",
            "posterId": "92b",
            "title": "Cerberus Transformer: Joint Semantic, Affordance and Attribute Parsing",
            "authors": [
                "Xiaoxue Chen",
                " Tianyu Liu",
                " Hao Zhao",
                " Guyue Zhou",
                " Ya-Qin Zhang"
            ]
        },
        {
            "paperId": "5725",
            "posterId": "93b",
            "title": "Collaborative Transformers for Grounded Situation Recognition",
            "authors": [
                "Junhyeong Cho",
                " Youngseok Yoon",
                " Suha Kwak"
            ]
        }
    ],
    "Action and Event Recognition": [
        {
            "paperId": "2817",
            "posterId": "115b",
            "title": "Bridge-Prompt: Towards Ordinal Action Understanding in Instructional Videos",
            "authors": [
                "Muheng Li",
                " Lei Chen",
                " Yueqi Duan",
                " Zhilan Hu",
                " Jianjiang Feng",
                " Jie Zhou",
                " Jiwen Lu"
            ]
        },
        {
            "paperId": "5042",
            "posterId": "116b",
            "title": "SVIP: Sequence VerIfication for Procedures in Videos",
            "authors": [
                "Yicheng Qian",
                " Weixin Luo",
                " Dongze Lian",
                " Xu Tang",
                " Peilin Zhao",
                " Shenghua Gao"
            ]
        },
        {
            "paperId": "3292",
            "posterId": "117b",
            "title": "Set-Supervised Action Learning in Procedural Task Videos via Pairwise Order Consistency",
            "authors": [
                "Zijia Lu",
                " Ehsan Elhamifar"
            ]
        },
        {
            "paperId": "5855",
            "posterId": "118b",
            "title": "Exploring Denoised Cross-Video Contrast for Weakly-Supervised Temporal Action Localization",
            "authors": [
                "Jingjing Li",
                " Tianyu Yang",
                " Wei Ji",
                " Jue Wang",
                " Li Cheng"
            ]
        },
        {
            "paperId": "3084",
            "posterId": "119b",
            "title": "GateHUB: Gated History Unit With Background Suppression for Online Action Detection",
            "authors": [
                "Junwen Chen",
                " Gaurav Mittal",
                " Ye Yu",
                " Yu Kong",
                " Mei Chen"
            ]
        },
        {
            "paperId": "7477",
            "posterId": "120b",
            "title": "E2(GO)MOTION: Motion Augmented Event Stream for Egocentric Action Recognition",
            "authors": [
                "Chiara Plizzari",
                " Mirco Planamente",
                " Gabriele Goletto",
                " Marco Cannici",
                " Emanuele Gusso",
                " Matteo Matteucci",
                " Barbara Caputo"
            ]
        },
        {
            "paperId": "4495",
            "posterId": "121b",
            "title": "Hybrid Relation Guided Set Matching for Few-Shot Action Recognition",
            "authors": [
                "Xiang Wang",
                " Shiwei Zhang",
                " Zhiwu Qing",
                " Mingqian Tang",
                " Zhengrong Zuo",
                " Changxin Gao",
                " Rong Jin",
                " Nong Sang"
            ]
        },
        {
            "paperId": "3385",
            "posterId": "122b",
            "title": "Spatio-Temporal Relation Modeling for Few-Shot Action Recognition",
            "authors": [
                "Anirudh Thatipelli",
                " Sanath Narayan",
                " Salman Khan",
                " Rao Muhammad Anwer",
                " Fahad Shahbaz Khan",
                " Bernard Ghanem"
            ]
        },
        {
            "paperId": "9787",
            "posterId": "123b",
            "title": "Alignment-Uniformity Aware Representation Learning for Zero-Shot Video Classification",
            "authors": [
                "Shi Pu",
                " Kaili Zhao",
                " Mao Zheng"
            ]
        },
        {
            "paperId": "1862",
            "posterId": "124b",
            "title": "Cross-Modal Representation Learning for Zero-Shot Action Recognition",
            "authors": [
                "Chung-Ching Lin",
                " Kevin Lin",
                " Lijuan Wang",
                " Zicheng Liu",
                " Linjie Li"
            ]
        },
        {
            "paperId": "6938",
            "posterId": "125b",
            "title": "Cross-Modal Background Suppression for Audio-Visual Event Localization",
            "authors": [
                "Yan Xia",
                " Zhou Zhao"
            ]
        },
        {
            "paperId": "3142",
            "posterId": "126b",
            "title": "Fine-Grained Temporal Contrastive Learning for Weakly-Supervised Temporal Action Localization",
            "authors": [
                "Junyu Gao",
                " Mengyuan Chen",
                " Changsheng Xu"
            ]
        },
        {
            "paperId": "1068",
            "posterId": "127b",
            "title": "An Empirical Study of End-to-End Temporal Action Detection",
            "authors": [
                "Xiaolong Liu",
                " Song Bai",
                " Xiang Bai"
            ]
        },
        {
            "paperId": "11191",
            "posterId": "128b",
            "title": "Everything at Once - Multi-Modal Fusion Transformer for Video Retrieval",
            "authors": [
                "Nina Shvetsova",
                " Brian Chen",
                " Andrew Rouditchenko",
                " Samuel Thomas",
                " Brian Kingsbury",
                " Rogerio S. Feris",
                " David Harwath",
                " James Glass",
                " Hilde Kuehne"
            ]
        },
        {
            "paperId": "9295",
            "posterId": "129b",
            "title": "DirecFormer: A Directed Attention in Transformer Approach to Robust Action Recognition",
            "authors": [
                "Thanh-Dat Truong",
                " Quoc-Huy Bui",
                " Chi Nhan Duong",
                " Han-Seok Seo",
                " Son Lam Phung",
                " Xin Li",
                " Khoa Luu"
            ]
        },
        {
            "paperId": "730",
            "posterId": "130b",
            "title": "MS-TCT: Multi-Scale Temporal ConvTransformer for Action Detection",
            "authors": [
                "Rui Dai",
                " Srijan Das",
                " Kumara Kahatapitiya",
                " Michael S. Ryoo",
                " François Brémond"
            ]
        },
        {
            "paperId": "2917",
            "posterId": "131b",
            "title": "Uncertainty-Guided Probabilistic Transformer for Complex Action Recognition",
            "authors": [
                "Hongji Guo",
                " Hanjing Wang",
                " Qiang Ji"
            ]
        },
        {
            "paperId": "9674",
            "posterId": "132b",
            "title": "AdaFocus V2: End-to-End Training of Spatial Dynamic Networks for Video Recognition",
            "authors": [
                "Yulin Wang",
                " Yang Yue",
                " Yuanze Lin",
                " Haojun Jiang",
                " Zihang Lai",
                " Victor Kulikov",
                " Nikita Orlov",
                " Humphrey Shi",
                " Gao Huang"
            ]
        },
        {
            "paperId": "5856",
            "posterId": "133b",
            "title": "UBoCo: Unsupervised Boundary Contrastive Learning for Generic Event Boundary Detection",
            "authors": [
                "Hyolim Kang",
                " Jinwoo Kim",
                " Taehyun Kim",
                " Seon Joo Kim"
            ]
        },
        {
            "paperId": "3946",
            "posterId": "134b",
            "title": "Detector-Free Weakly Supervised Group Activity Recognition",
            "authors": [
                "Dongkeun Kim",
                " Jinsung Lee",
                " Minsu Cho",
                " Suha Kwak"
            ]
        },
        {
            "paperId": "2870",
            "posterId": "135b",
            "title": "Multi-Grained Spatio-Temporal Features Perceived Network for Event-Based Lip-Reading",
            "authors": [
                "Ganchao Tan",
                " Yang Wang",
                " Han Han",
                " Yang Cao",
                " Feng Wu",
                " Zheng-Jun Zha"
            ]
        },
        {
            "paperId": "2752",
            "posterId": "136b",
            "title": "Efficient Two-Stage Detection of Human-Object Interactions With a Novel Unary-Pairwise Transformer",
            "authors": [
                "Frederic Z. Zhang",
                " Dylan Campbell",
                " Stephen Gould"
            ]
        },
        {
            "paperId": "517",
            "posterId": "137b",
            "title": "Interactiveness Field in Human-Object Interactions",
            "authors": [
                "Xinpeng Liu",
                " Yong-Lu Li",
                " Xiaoqian Wu",
                " Yu-Wing Tai",
                " Cewu Lu",
                " Chi-Keung Tang"
            ]
        },
        {
            "paperId": "2258",
            "posterId": "138b",
            "title": "GEN-VLKT: Simplify Association and Enhance Interaction Understanding for HOI Detection",
            "authors": [
                "Yue Liao",
                " Aixi Zhang",
                " Miao Lu",
                " Yongliang Wang",
                " Xiaobo Li",
                " Si Liu"
            ]
        },
        {
            "paperId": "7690",
            "posterId": "139b",
            "title": "Object-Relation Reasoning Graph for Action Recognition",
            "authors": [
                "Yangjun Ou",
                " Li Mi",
                " Zhenzhong Chen"
            ]
        },
        {
            "paperId": "4315",
            "posterId": "140b",
            "title": "UBnormal: New Benchmark for Supervised Open-Set Video Anomaly Detection",
            "authors": [
                "Andra Acsintoae",
                " Andrei Florescu",
                " Mariana-Iuliana Georgescu",
                " Tudor Mare",
                " Paul Sumedrea",
                " Radu Tudor Ionescu",
                " Fahad Shahbaz Khan",
                " Mubarak Shah"
            ]
        },
        {
            "paperId": "1483",
            "posterId": "141b",
            "title": "Decoupling and Recoupling Spatiotemporal Representation for RGB-D-Based Motion Recognition",
            "authors": [
                "Benjia Zhou",
                " Pichao Wang",
                " Jun Wan",
                " Yanyan Liang",
                " Fan Wang",
                " Du Zhang",
                " Zhen Lei",
                " Hao Li",
                " Rong Jin"
            ]
        },
        {
            "paperId": "9379",
            "posterId": "142b",
            "title": "SPAct: Self-Supervised Privacy Preservation for Action Recognition",
            "authors": [
                "Ishan Rajendrakumar Dave",
                " Chen Chen",
                " Mubarak Shah"
            ]
        },
        {
            "paperId": "818",
            "posterId": "143b",
            "title": "Unsupervised Action Segmentation by Joint Representation Learning and Online Clustering",
            "authors": [
                "Sateesh Kumar",
                " Sanjay Haresh",
                " Awais Ahmed",
                " Andrey Konin",
                " M. Zeeshan Zia",
                " Quoc-Huy Tran"
            ]
        },
        {
            "paperId": "28",
            "posterId": "144b",
            "title": "InfoGCN: Representation Learning for Human Skeleton-Based Action Recognition",
            "authors": [
                "Hyung-gun Chi",
                " Myoung Hoon Ha",
                " Seunggeun Chi",
                " Sang Wan Lee",
                " Qixing Huang",
                " Karthik Ramani"
            ]
        },
        {
            "paperId": "11846",
            "posterId": "145b",
            "title": "Learning Video Representations of Human Motion From Synthetic Data",
            "authors": [
                "Xi Guo",
                " Wei Wu",
                " Dongliang Wang",
                " Jing Su",
                " Haisheng Su",
                " Weihao Gan",
                " Jian Huang",
                " Qin Yang"
            ]
        },
        {
            "paperId": "6314",
            "posterId": "146b",
            "title": "Learnable Irrelevant Modality Dropout for Multimodal Action Recognition on Modality-Specific Annotated Videos",
            "authors": [
                "Saghir Alfasly",
                " Jian Lu",
                " Chen Xu",
                " Yuru Zou"
            ]
        }
    ],
    "Biometrics": [
        {
            "paperId": "1752",
            "posterId": "147b",
            "title": "EyePAD++: A Distillation-Based Approach for Joint Eye Authentication and Presentation Attack Detection Using Periocular Images",
            "authors": [
                "Prithviraj Dhar",
                " Amit Kumar",
                " Kirsten Kaplan",
                " Khushi Gupta",
                " Rakesh Ranjan",
                " Rama Chellappa"
            ]
        },
        {
            "paperId": "3373",
            "posterId": "148b",
            "title": "Gait Recognition in the Wild With Dense 3D Representations and a Benchmark",
            "authors": [
                "Jinkai Zheng",
                " Xinchen Liu",
                " Wu Liu",
                " Lingxiao He",
                " Chenggang Yan",
                " Tao Mei"
            ]
        },
        {
            "paperId": "1403",
            "posterId": "149b",
            "title": "Camera-Conditioned Stable Feature Generation for Isolated Camera Supervised Person Re-IDentification",
            "authors": [
                "Chao Wu",
                " Wenhang Ge",
                " Ancong Wu",
                " Xiaobin Chang"
            ]
        },
        {
            "paperId": "3765",
            "posterId": "150b",
            "title": "Lagrange Motion Analysis and View Embeddings for Improved Gait Recognition",
            "authors": [
                "Tianrui Chai",
                " Annan Li",
                " Shaoxiong Zhang",
                " Zilong Li",
                " Yunhong Wang"
            ]
        },
        {
            "paperId": "9404",
            "posterId": "151b",
            "title": "DeepFace-EMD: Re-Ranking Using Patch-Wise Earth Mover's Distance Improves Out-of-Distribution Face Identification",
            "authors": [
                "Hai Phan",
                " Anh Nguyen"
            ]
        },
        {
            "paperId": "1311",
            "posterId": "152b",
            "title": "Learning Second Order Local Anomaly for General Face Forgery Detection",
            "authors": [
                "Jianwei Fei",
                " Yunshu Dai",
                " Peipeng Yu",
                " Tianrun Shen",
                " Zhihua Xia",
                " Jian Weng"
            ]
        },
        {
            "paperId": "4821",
            "posterId": "153b",
            "title": "PatchNet: A Simple Face Anti-Spoofing Framework via Fine-Grained Patch Recognition",
            "authors": [
                "Chien-Yi Wang",
                " Yu-Ding Lu",
                " Shang-Ta Yang",
                " Shang-Hong Lai"
            ]
        },
        {
            "paperId": "10637",
            "posterId": "154b",
            "title": "Face2Exp: Combating Data Biases for Facial Expression Recognition",
            "authors": [
                "Dan Zeng",
                " Zhiyuan Lin",
                " Xiao Yan",
                " Yuting Liu",
                " Fei Wang",
                " Bo Tang"
            ]
        },
        {
            "paperId": "11994",
            "posterId": "155b",
            "title": "Local-Adaptive Face Recognition via Graph-Based Meta-Clustering and Regularized Adaptation",
            "authors": [
                "Wenbin Zhu",
                " Chien-Yi Wang",
                " Kuan-Lun Tseng",
                " Shang-Hong Lai",
                " Baoyuan Wang"
            ]
        }
    ],
    "Face and Gestures": [
        {
            "paperId": "4811",
            "posterId": "156b",
            "title": "EMOCA: Emotion Driven Monocular Face Capture and Animation",
            "authors": [
                "Radek Daněček",
                " Michael J. Black",
                " Timo Bolkart"
            ]
        },
        {
            "paperId": "6513",
            "posterId": "157b",
            "title": "Robust Egocentric Photo-Realistic Facial Expression Transfer for Virtual Reality",
            "authors": [
                "Amin Jourabloo",
                " Fernando De la Torre",
                " Jason Saragih",
                " Shih-En Wei",
                " Stephen Lombardi",
                " Te-Li Wang",
                " Danielle Belko",
                " Autumn Trimble",
                " Hernan Badino"
            ]
        },
        {
            "paperId": "2290",
            "posterId": "158b",
            "title": "FaceVerse: A Fine-Grained and Detail-Controllable 3D Face Morphable Model From a Hybrid Dataset",
            "authors": [
                "Lizhen Wang",
                " Zhiyuan Chen",
                " Tao Yu",
                " Chenguang Ma",
                " Liang Li",
                " Yebin Liu"
            ]
        },
        {
            "paperId": "4969",
            "posterId": "159b",
            "title": "ImFace: A Nonlinear 3D Morphable Face Model With Implicit Neural Representations",
            "authors": [
                "Mingwu Zheng",
                " Hongyu Yang",
                " Di Huang",
                " Liming Chen"
            ]
        },
        {
            "paperId": "3883",
            "posterId": "160b",
            "title": "Physically-Guided Disentangled Implicit Rendering for 3D Face Modeling",
            "authors": [
                "Zhenyu Zhang",
                " Yanhao Ge",
                " Ying Tai",
                " Weijian Cao",
                " Renwang Chen",
                " Kunlin Liu",
                " Hao Tang",
                " Xiaoming Huang",
                " Chengjie Wang",
                " Zhifeng Xie",
                " Dongjin Huang"
            ]
        },
        {
            "paperId": "736",
            "posterId": "161b",
            "title": "RigNeRF: Fully Controllable Neural 3D Portraits",
            "authors": [
                "ShahRukh Athar",
                " Zexiang Xu",
                " Kalyan Sunkavalli",
                " Eli Shechtman",
                " Zhixin Shu"
            ]
        },
        {
            "paperId": "5362",
            "posterId": "162b",
            "title": "HeadNeRF: A Real-Time NeRF-Based Parametric Head Model",
            "authors": [
                "Yang Hong",
                " Bo Peng",
                " Haiyao Xiao",
                " Ligang Liu",
                " Juyong Zhang"
            ]
        },
        {
            "paperId": "7738",
            "posterId": "163b",
            "title": "Sparse to Dense Dynamic 3D Facial Expression Generation",
            "authors": [
                "Naima Otberdout",
                " Claudio Ferrari",
                " Mohamed Daoudi",
                " Stefano Berretti",
                " Alberto Del Bimbo"
            ]
        },
        {
            "paperId": "812",
            "posterId": "164b",
            "title": "Learning To Listen: Modeling Non-Deterministic Dyadic Facial Motion",
            "authors": [
                "Evonne Ng",
                " Hanbyul Joo",
                " Liwen Hu",
                " Hao Li",
                " Trevor Darrell",
                " Angjoo Kanazawa",
                " Shiry Ginosar"
            ]
        },
        {
            "paperId": "7201",
            "posterId": "165b",
            "title": "Speech Driven Tongue Animation",
            "authors": [
                "Salvador Medina",
                " Denis Tome",
                " Carsten Stoll",
                " Mark Tiede",
                " Kevin Munhall",
                " Alexander G. Hauptmann",
                " Iain Matthews"
            ]
        },
        {
            "paperId": "6728",
            "posterId": "166b",
            "title": "Knowledge-Driven Self-Supervised Representation Learning for Facial Action Unit Recognition",
            "authors": [
                "Yanan Chang",
                " Shangfei Wang"
            ]
        },
        {
            "paperId": "980",
            "posterId": "167b",
            "title": "gDNA: Towards Generative Detailed Neural Avatars",
            "authors": [
                "Xu Chen",
                " Tianjian Jiang",
                " Jie Song",
                " Jinlong Yang",
                " Michael J. Black",
                " Andreas Geiger",
                " Otmar Hilliges"
            ]
        },
        {
            "paperId": "1874",
            "posterId": "168b",
            "title": "GraFormer: Graph-Oriented Transformer for 3D Pose Estimation",
            "authors": [
                "Weixi Zhao",
                " Weiqiang Wang",
                " Yunjie Tian"
            ]
        },
        {
            "paperId": "10976",
            "posterId": "169b",
            "title": "Uncertainty-Aware Adaptation for Self-Supervised 3D Human Pose Estimation",
            "authors": [
                "Jogendra Nath Kundu",
                " Siddharth Seth",
                " Pradyumna YM",
                " Varun Jampani",
                " Anirban Chakraborty",
                " R. Venkatesh Babu"
            ]
        },
        {
            "paperId": "501",
            "posterId": "170b",
            "title": "Towards Diverse and Natural Scene-Aware 3D Human Motion Synthesis",
            "authors": [
                "Jingbo Wang",
                " Yu Rong",
                " Jingyuan Liu",
                " Sijie Yan",
                " Dahua Lin",
                " Bo Dai"
            ]
        },
        {
            "paperId": "2836",
            "posterId": "171b",
            "title": "PINA: Learning a Personalized Implicit Neural Avatar From a Single RGB-D Video Sequence",
            "authors": [
                "Zijian Dong",
                " Chen Guo",
                " Jie Song",
                " Xu Chen",
                " Andreas Geiger",
                " Otmar Hilliges"
            ]
        },
        {
            "paperId": "4356",
            "posterId": "172b",
            "title": "The Wanderings of Odysseus in 3D Scenes",
            "authors": [
                "Yan Zhang",
                " Siyu Tang"
            ]
        },
        {
            "paperId": "6883",
            "posterId": "173b",
            "title": "OSSO: Obtaining Skeletal Shape From Outside",
            "authors": [
                "Marilyn Keller",
                " Silvia Zuffi",
                " Michael J. Black",
                " Sergi Pujades"
            ]
        },
        {
            "paperId": "11477",
            "posterId": "174b",
            "title": "LiDARCap: Long-Range Marker-Less 3D Human Motion Capture With LiDAR Point Clouds",
            "authors": [
                "Jialian Li",
                " Jingyi Zhang",
                " Zhiyong Wang",
                " Siqi Shen",
                " Chenglu Wen",
                " Yuexin Ma",
                " Lan Xu",
                " Jingyi Yu",
                " Cheng Wang"
            ]
        },
        {
            "paperId": "3402",
            "posterId": "175b",
            "title": "Unimodal-Concentrated Loss: Fully Adaptive Label Distribution Learning for Ordinal Regression",
            "authors": [
                "Qiang Li",
                " Jingjing Wang",
                " Zhaoliang Yao",
                " Yachun Li",
                " Pengju Yang",
                " Jingwei Yan",
                " Chunmao Wang",
                " Shiliang Pu"
            ]
        },
        {
            "paperId": "2046",
            "posterId": "176b",
            "title": "Spatial-Temporal Parallel Transformer for Arm-Hand Dynamic Estimation",
            "authors": [
                "Shuying Liu",
                " Wenbin Wu",
                " Jiaxian Wu",
                " Yue Lin"
            ]
        },
        {
            "paperId": "6216",
            "posterId": "177b",
            "title": "LISA: Learning Implicit Shape and Appearance of Hands",
            "authors": [
                "Enric Corona",
                " Tomas Hodan",
                " Minh Vo",
                " Francesc Moreno-Noguer",
                " Chris Sweeney",
                " Richard Newcombe",
                " Lingni Ma"
            ]
        },
        {
            "paperId": "3384",
            "posterId": "178b",
            "title": "MobRecon: Mobile-Friendly Hand Mesh Reconstruction From Monocular Image",
            "authors": [
                "Xingyu Chen",
                " Yufeng Liu",
                " Yajiao Dong",
                " Xiong Zhang",
                " Chongyang Ma",
                " Yanmin Xiong",
                " Yuan Zhang",
                " Xiaoyan Guo"
            ]
        },
        {
            "paperId": "5835",
            "posterId": "179b",
            "title": "Mining Multi-View Information: A Strong Self-Supervised Framework for Depth-Based 3D Hand Pose and Mesh Estimation",
            "authors": [
                "Pengfei Ren",
                " Haifeng Sun",
                " Jiachang Hao",
                " Jingyu Wang",
                " Qi Qi",
                " Jianxin Liao"
            ]
        },
        {
            "paperId": "7098",
            "posterId": "180b",
            "title": "Low-Resource Adaptation for Personalized Co-Speech Gesture Generation",
            "authors": [
                "Chaitanya Ahuja",
                " Dong Won Lee",
                " Louis-Philippe Morency"
            ]
        },
        {
            "paperId": "921",
            "posterId": "181b",
            "title": "D-Grasp: Physically Plausible Dynamic Grasp Synthesis for Hand-Object Interactions",
            "authors": [
                "Sammy Christen",
                " Muhammed Kocabas",
                " Emre Aksan",
                " Jemin Hwangbo",
                " Jie Song",
                " Otmar Hilliges"
            ]
        }
    ],
    "Medical, Biological and Cell Microscopy": [
        {
            "paperId": "1104",
            "posterId": "182b",
            "title": "Synthetic Generation of Face Videos With Plethysmograph Physiology",
            "authors": [
                "Zhen Wang",
                " Yunhao Ba",
                " Pradyumna Chari",
                " Oyku Deniz Bozkurt",
                " Gianna Brown",
                " Parth Patwa",
                " Niranjan Vaddi",
                " Laleh Jalilian",
                " Achuta Kadambi"
            ]
        },
        {
            "paperId": "9240",
            "posterId": "183b",
            "title": "Contour-Hugging Heatmaps for Landmark Detection",
            "authors": [
                "James McCouat",
                " Irina Voiculescu"
            ]
        },
        {
            "paperId": "4486",
            "posterId": "184b",
            "title": "Which Images To Label for Few-Shot Medical Landmark Detection?",
            "authors": [
                "Quan Quan",
                " Qingsong Yao",
                " Jun Li",
                " S. Kevin Zhou"
            ]
        },
        {
            "paperId": "4473",
            "posterId": "185b",
            "title": "Self-Supervised Bulk Motion Artifact Removal in Optical Coherence Tomography Angiography",
            "authors": [
                "Jiaxiang Ren",
                " Kicheon Park",
                " Yingtian Pan",
                " Haibin Ling"
            ]
        },
        {
            "paperId": "8680",
            "posterId": "186b",
            "title": "Multi-Marginal Contrastive Learning for Multi-Label Subcellular Protein Localization",
            "authors": [
                "Ziyi Liu",
                " Zengmao Wang",
                " Bo Du"
            ]
        },
        {
            "paperId": "8210",
            "posterId": "187b",
            "title": "Transformer-Empowered Multi-Scale Contextual Matching and Aggregation for Multi-Contrast MRI Super-Resolution",
            "authors": [
                "Guangyuan Li",
                " Jun Lv",
                " Yapeng Tian",
                " Qi Dou",
                " Chengyan Wang",
                " Chenliang Xu",
                " Jing Qin"
            ]
        },
        {
            "paperId": "6627",
            "posterId": "188b",
            "title": "Harmony: A Generic Unsupervised Approach for Disentangling Semantic Content From Parameterized Transformations",
            "authors": [
                "Mostofa Rafid Uddin",
                " Gregory Howe",
                " Xiangrui Zeng",
                " Min Xu"
            ]
        },
        {
            "paperId": "3856",
            "posterId": "189b",
            "title": "Cross-Modal Clinical Graph Transformer for Ophthalmic Report Generation",
            "authors": [
                "Mingjie Li",
                " Wenjia Cai",
                " Karin Verspoor",
                " Shirui Pan",
                " Xiaodan Liang",
                " Xiaojun Chang"
            ]
        },
        {
            "paperId": "6449",
            "posterId": "190b",
            "title": "BoostMIS: Boosting Medical Image Semi-Supervised Learning With Adaptive Pseudo Labeling and Informative Active Annotation",
            "authors": [
                "Wenqiao Zhang",
                " Lei Zhu",
                " James Hallinan",
                " Shengyu Zhang",
                " Andrew Makmur",
                " Qingpeng Cai",
                " Beng Chin Ooi"
            ]
        },
        {
            "paperId": "6189",
            "posterId": "191b",
            "title": "Incremental Cross-View Mutual Distillation for Self-Supervised Medical CT Synthesis",
            "authors": [
                "Chaowei Fang",
                " Liang Wang",
                " Dingwen Zhang",
                " Jun Xu",
                " Yixuan Yuan",
                " Junwei Han"
            ]
        },
        {
            "paperId": "9027",
            "posterId": "192b",
            "title": "Towards Low-Cost and Efficient Malaria Detection",
            "authors": [
                "Waqas Sultani",
                " Wajahat Nawaz",
                " Syed Javed",
                " Muhammad Sohail Danish",
                " Asma Saadia",
                " Mohsen Ali"
            ]
        },
        {
            "paperId": "5588",
            "posterId": "193b",
            "title": "ACPL: Anti-Curriculum Pseudo-Labelling for Semi-Supervised Medical Image Classification",
            "authors": [
                "Fengbei Liu",
                " Yu Tian",
                " Yuanhong Chen",
                " Yuyuan Liu",
                " Vasileios Belagiannis",
                " Gustavo Carneiro"
            ]
        },
        {
            "paperId": "2696",
            "posterId": "194b",
            "title": "Multimodal Dynamics: Dynamical Fusion for Trustworthy Multimodal Classification",
            "authors": [
                "Zongbo Han",
                " Fan Yang",
                " Junzhou Huang",
                " Changqing Zhang",
                " Jianhua Yao"
            ]
        },
        {
            "paperId": "9084",
            "posterId": "195b",
            "title": "M3T: Three-Dimensional Medical Image Classifier Using Multi-Plane and Multi-Slice Transformer",
            "authors": [
                "Jinseong Jang",
                " Dosik Hwang"
            ]
        },
        {
            "paperId": "121",
            "posterId": "196b",
            "title": "Self-Supervised Pre-Training of Swin Transformers for 3D Medical Image Analysis",
            "authors": [
                "Yucheng Tang",
                " Dong Yang",
                " Wenqi Li",
                " Holger R. Roth",
                " Bennett Landman",
                " Daguang Xu",
                " Vishwesh Nath",
                " Ali Hatamizadeh"
            ]
        },
        {
            "paperId": "10799",
            "posterId": "197b",
            "title": "HyperSegNAS: Bridging One-Shot Neural Architecture Search With 3D Medical Image Segmentation Using HyperNet",
            "authors": [
                "Cheng Peng",
                " Andriy Myronenko",
                " Ali Hatamizadeh",
                " Vishwesh Nath",
                " Md Mahfuzur Rahman Siddiquee",
                " Yufan He",
                " Daguang Xu",
                " Rama Chellappa",
                " Dong Yang"
            ]
        },
        {
            "paperId": "2649",
            "posterId": "198b",
            "title": "DArch: Dental Arch Prior-Assisted 3D Tooth Instance Segmentation With Weak Annotations",
            "authors": [
                "Liangdong Qiu",
                " Chongjie Ye",
                " Pei Chen",
                " Yunbi Liu",
                " Xiaoguang Han",
                " Shuguang Cui"
            ]
        },
        {
            "paperId": "10420",
            "posterId": "199b",
            "title": "Clean Implicit 3D Structure From Noisy 2D STEM Images",
            "authors": [
                "Hannah Kniesel",
                " Timo Ropinski",
                " Tim Bergner",
                " Kavitha Shaga Devan",
                " Clarissa Read",
                " Paul Walther",
                " Tobias Ritschel",
                " Pedro Hermosilla"
            ]
        },
        {
            "paperId": "7672",
            "posterId": "200b",
            "title": "Vox2Cortex: Fast Explicit Reconstruction of Cortical Surfaces From 3D MRI Scans With Geometric Deep Neural Networks",
            "authors": [
                "Fabian Bongratz",
                " Anne-Marie Rickmann",
                " Sebastian Pölsterl",
                " Christian Wachinger"
            ]
        },
        {
            "paperId": "4123",
            "posterId": "201b",
            "title": "Aladdin: Joint Atlas Building and Diffeomorphic Registration Learning With Pairwise Alignment",
            "authors": [
                "Zhipeng Ding",
                " Marc Niethammer"
            ]
        },
        {
            "paperId": "3819",
            "posterId": "202b",
            "title": "Learning Optimal K-Space Acquisition and Reconstruction Using Physics-Informed Neural Networks",
            "authors": [
                "Wei Peng",
                " Li Feng",
                " Guoying Zhao",
                " Fang Liu"
            ]
        },
        {
            "paperId": "2466",
            "posterId": "203b",
            "title": "NODEO: A Neural Ordinary Differential Equation Based Optimization Framework for Deformable Image Registration",
            "authors": [
                "Yifan Wu",
                " Tom Z. Jiahao",
                " Jiancong Wang",
                " Paul A. Yushkevich",
                " M. Ani Hsieh",
                " James C. Gee"
            ]
        },
        {
            "paperId": "4362",
            "posterId": "204b",
            "title": "SMPL-A: Modeling Person-Specific Deformable Anatomy",
            "authors": [
                "Hengtao Guo",
                " Benjamin Planche",
                " Meng Zheng",
                " Srikrishna Karanam",
                " Terrence Chen",
                " Ziyan Wu"
            ]
        },
        {
            "paperId": "1830",
            "posterId": "205b",
            "title": "DiRA: Discriminative, Restorative, and Adversarial Learning for Self-Supervised Medical Image Analysis",
            "authors": [
                "Fatemeh Haghighi",
                " Mohammad Reza Hosseinzadeh Taher",
                " Michael B. Gotway",
                " Jianming Liang"
            ]
        },
        {
            "paperId": "1826",
            "posterId": "206b",
            "title": "Affine Medical Image Registration With Coarse-To-Fine Vision Transformer",
            "authors": [
                "Tony C. W. Mok",
                " Albert C. S. Chung"
            ]
        },
        {
            "paperId": "9880",
            "posterId": "207b",
            "title": "Topology-Preserving Shape Reconstruction and Registration via Neural Diffeomorphic Flow",
            "authors": [
                "Shanlin Sun",
                " Kun Han",
                " Deying Kong",
                " Hao Tang",
                " Xiangyi Yan",
                " Xiaohui Xie"
            ]
        },
        {
            "paperId": "1002",
            "posterId": "208b",
            "title": "Generalizable Cross-Modality Medical Image Segmentation via Style Augmentation and Dual Normalization",
            "authors": [
                "Ziqi Zhou",
                " Lei Qi",
                " Xin Yang",
                " Dong Ni",
                " Yinghuan Shi"
            ]
        },
        {
            "paperId": "6023",
            "posterId": "209b",
            "title": "Closing the Generalization Gap of Cross-Silo Federated Medical Image Segmentation",
            "authors": [
                "An Xu",
                " Wenqi Li",
                " Pengfei Guo",
                " Dong Yang",
                " Holger R. Roth",
                " Ali Hatamizadeh",
                " Can Zhao",
                " Daguang Xu",
                " Heng Huang",
                " Ziyue Xu"
            ]
        },
        {
            "paperId": "6328",
            "posterId": "210b",
            "title": "FIBA: Frequency-Injection Based Backdoor Attack in Medical Image Analysis",
            "authors": [
                "Yu Feng",
                " Benteng Ma",
                " Jing Zhang",
                " Shanshan Zhao",
                " Yong Xia",
                " Dacheng Tao"
            ]
        },
        {
            "paperId": "8360",
            "posterId": "211b",
            "title": "Surpassing the Human Accuracy: Detecting Gallbladder Cancer From USG Images With Curriculum Learning",
            "authors": [
                "Soumen Basu",
                " Mayank Gupta",
                " Pratyaksha Rana",
                " Pankaj Gupta",
                " Chetan Arora"
            ]
        },
        {
            "paperId": "5948",
            "posterId": "212b",
            "title": "CellTypeGraph: A New Geometric Computer Vision Benchmark",
            "authors": [
                "Lorenzo Cerrone",
                " Athul Vijayan",
                " Tejasvinee Mody",
                " Kay Schneitz",
                " Fred A. Hamprecht"
            ]
        },
        {
            "paperId": "8619",
            "posterId": "213b",
            "title": "ContIG: Self-Supervised Multimodal Contrastive Learning for Medical Imaging With Genetics",
            "authors": [
                "Aiham Taleb",
                " Matthias Kirchler",
                " Remo Monti",
                " Christoph Lippert"
            ]
        }
    ],
    "Datasets and Evaluation": [
        {
            "paperId": "378",
            "posterId": "214b",
            "title": "FERV39k: A Large-Scale Multi-Scene Dataset for Facial Expression Recognition in Videos",
            "authors": [
                "Yan Wang",
                " Yixuan Sun",
                " Yiwen Huang",
                " Zhongying Liu",
                " Shuyong Gao",
                " Wei Zhang",
                " Weifeng Ge",
                " Wenqiang Zhang"
            ]
        },
        {
            "paperId": "675",
            "posterId": "215b",
            "title": "Multi-Dimensional, Nuanced and Subjective - Measuring the Perception of Facial Expressions",
            "authors": [
                "De'Aira Bryant",
                " Siqi Deng",
                " Nashlie Sephus",
                " Wei Xia",
                " Pietro Perona"
            ]
        },
        {
            "paperId": "10327",
            "posterId": "216b",
            "title": "DAD-3DHeads: A Large-Scale Dense, Accurate and Diverse Dataset for 3D Head Alignment From a Single Image",
            "authors": [
                "Tetiana Martyniuk",
                " Orest Kupyn",
                " Yana Kurlyak",
                " Igor Krashenyi",
                " Jiří Matas",
                " Viktoriia Sharmanska"
            ]
        },
        {
            "paperId": "583",
            "posterId": "217b",
            "title": "OakInk: A Large-Scale Knowledge Repository for Understanding Hand-Object Interaction",
            "authors": [
                "Lixin Yang",
                " Kailin Li",
                " Xinyu Zhan",
                " Fei Wu",
                " Anran Xu",
                " Liu Liu",
                " Cewu Lu"
            ]
        },
        {
            "paperId": "9029",
            "posterId": "218b",
            "title": "PoseTrack21: A Dataset for Person Search, Multi-Object Tracking and Multi-Person Pose Tracking",
            "authors": [
                "Andreas Döring",
                " Di Chen",
                " Shanshan Zhang",
                " Bernt Schiele",
                " Jürgen Gall"
            ]
        },
        {
            "paperId": "6336",
            "posterId": "219b",
            "title": "Learning Modal-Invariant and Temporal-Memory for Video-Based Visible-Infrared Person Re-Identification",
            "authors": [
                "Xinyu Lin",
                " Jinxing Li",
                " Zeyu Ma",
                " Huafeng Li",
                " Shuang Li",
                " Kaixiong Xu",
                " Guangming Lu",
                " David Zhang"
            ]
        },
        {
            "paperId": "3564",
            "posterId": "220b",
            "title": "JRDB-Act: A Large-Scale Dataset for Spatio-Temporal Action, Social Group and Activity Detection",
            "authors": [
                "Mahsa Ehsanpour",
                " Fatemeh Saleh",
                " Silvio Savarese",
                " Ian Reid",
                " Hamid Rezatofighi"
            ]
        },
        {
            "paperId": "1672",
            "posterId": "221b",
            "title": "DanceTrack: Multi-Object Tracking in Uniform Appearance and Diverse Motion",
            "authors": [
                "Peize Sun",
                " Jinkun Cao",
                " Yi Jiang",
                " Zehuan Yuan",
                " Song Bai",
                " Kris Kitani",
                " Ping Luo"
            ]
        },
        {
            "paperId": "9778",
            "posterId": "222b",
            "title": "Egocentric Prediction of Action Target in 3D",
            "authors": [
                "Yiming Li",
                " Ziang Cao",
                " Andrew Liang",
                " Benjamin Liang",
                " Luoyao Chen",
                " Hang Zhao",
                " Chen Feng"
            ]
        },
        {
            "paperId": "1950",
            "posterId": "223b",
            "title": "HOI4D: A 4D Egocentric Dataset for Category-Level Human-Object Interaction",
            "authors": [
                "Yunze Liu",
                " Yun Liu",
                " Che Jiang",
                " Kangbo Lyu",
                " Weikang Wan",
                " Hao Shen",
                " Boqiang Liang",
                " Zhoujie Fu",
                " He Wang",
                " Li Yi"
            ]
        },
        {
            "paperId": "10801",
            "posterId": "224b",
            "title": "Amodal Panoptic Segmentation",
            "authors": [
                "Rohit Mohan",
                " Abhinav Valada"
            ]
        },
        {
            "paperId": "8175",
            "posterId": "225b",
            "title": "Large-Scale Video Panoptic Segmentation in the Wild: A Benchmark",
            "authors": [
                "Jiaxu Miao",
                " Xiaohan Wang",
                " Yu Wu",
                " Wei Li",
                " Xu Zhang",
                " Yunchao Wei",
                " Yi Yang"
            ]
        },
        {
            "paperId": "4070",
            "posterId": "226b",
            "title": "YouMVOS: An Actor-Centric Multi-Shot Video Object Segmentation Dataset",
            "authors": [
                "Donglai Wei",
                " Siddhant Kharbanda",
                " Sarthak Arora",
                " Roshan Roy",
                " Nishant Jain",
                " Akash Palrecha",
                " Tanav Shah",
                " Shray Mathur",
                " Ritik Mathur",
                " Abhijay Kemkar",
                " Anirudh Chakravarthy",
                " Zudi Lin",
                " Won-Dong Jang",
                " Yansong Tang",
                " Song Bai",
                " James Tompkin",
                " Philip H.S. Torr",
                " Hanspeter Pfister"
            ]
        },
        {
            "paperId": "9179",
            "posterId": "227b",
            "title": "The DEVIL Is in the Details: A Diagnostic Evaluation Benchmark for Video Inpainting",
            "authors": [
                "Ryan Szeto",
                " Jason J. Corso"
            ]
        },
        {
            "paperId": "10392",
            "posterId": "228b",
            "title": "3MASSIV: Multilingual, Multimodal and Multi-Aspect Dataset of Social Media Short Videos",
            "authors": [
                "Vikram Gupta",
                " Trisha Mittal",
                " Puneet Mathur",
                " Vaibhav Mishra",
                " Mayank Maheshwari",
                " Aniket Bera",
                " Debdoot Mukherjee",
                " Dinesh Manocha"
            ]
        },
        {
            "paperId": "8328",
            "posterId": "229b",
            "title": "AxIoU: An Axiomatically Justified Measure for Video Moment Retrieval",
            "authors": [
                "Riku Togashi",
                " Mayu Otani",
                " Yuta Nakashima",
                " Esa Rahtu",
                " Janne Heikkilä",
                " Tetsuya Sakai"
            ]
        },
        {
            "paperId": "4732",
            "posterId": "230b",
            "title": "A Large-Scale Comprehensive Dataset and Copy-Overlap Aware Evaluation Protocol for Segment-Level Video Copy Detection",
            "authors": [
                "Sifeng He",
                " Xudong Yang",
                " Chen Jiang",
                " Gang Liang",
                " Wei Zhang",
                " Tan Pan",
                " Qing Wang",
                " Furong Xu",
                " Chunguang Li",
                " JinXiong Liu",
                " Hui Xu",
                " Kaiming Huang",
                " Yuan Cheng",
                " Feng Qian",
                " Xiaobo Zhang",
                " Lei Yang"
            ]
        },
        {
            "paperId": "2077",
            "posterId": "231b",
            "title": "Assembly101: A Large-Scale Multi-View Video Dataset for Understanding Procedural Activities",
            "authors": [
                "Fadime Sener",
                " Dibyadip Chatterjee",
                " Daniel Shelepov",
                " Kun He",
                " Dipika Singhania",
                " Robert Wang",
                " Angela Yao"
            ]
        },
        {
            "paperId": "8123",
            "posterId": "232b",
            "title": "Optimal Correction Cost for Object Detection Evaluation",
            "authors": [
                "Mayu Otani",
                " Riku Togashi",
                " Yuta Nakashima",
                " Esa Rahtu",
                " Janne Heikkilä",
                " Shin'ichi Satoh"
            ]
        },
        {
            "paperId": "7936",
            "posterId": "233b",
            "title": "GrainSpace: A Large-Scale Dataset for Fine-Grained and Domain-Adaptive Recognition of Cereal Grains",
            "authors": [
                "Lei Fan",
                " Yiwen Ding",
                " Dongdong Fan",
                " Donglin Di",
                " Maurice Pagnucco",
                " Yang Song"
            ]
        },
        {
            "paperId": "6061",
            "posterId": "234b",
            "title": "ABO: Dataset and Benchmarks for Real-World 3D Object Understanding",
            "authors": [
                "Jasmine Collins",
                " Shubham Goel",
                " Kenan Deng",
                " Achleshwar Luthra",
                " Leon Xu",
                " Erhan Gundogdu",
                " Xi Zhang",
                " Tomas F. Yago Vicente",
                " Thomas Dideriksen",
                " Himanshu Arora",
                " Matthieu Guillaumin",
                " Jitendra Malik"
            ]
        },
        {
            "paperId": "11100",
            "posterId": "235b",
            "title": "Improving Segmentation of the Inferior Alveolar Nerve Through Deep Label Propagation",
            "authors": [
                "Marco Cipriano",
                " Stefano Allegretti",
                " Federico Bolelli",
                " Federico Pollastri",
                " Costantino Grana"
            ]
        },
        {
            "paperId": "4346",
            "posterId": "236b",
            "title": "ZeroWaste Dataset: Towards Deformable Object Segmentation in Cluttered Scenes",
            "authors": [
                "Dina Bashkirova",
                " Mohamed Abdelfattah",
                " Ziliang Zhu",
                " James Akl",
                " Fadi Alladkani",
                " Ping Hu",
                " Vitaly Ablavsky",
                " Berk Calli",
                " Sarah Adel Bargal",
                " Kate Saenko"
            ]
        },
        {
            "paperId": "4313",
            "posterId": "237b",
            "title": "DynamicEarthNet: Daily Multi-Spectral Satellite Dataset for Semantic Change Segmentation",
            "authors": [
                "Aysim Toker",
                " Lukas Kondmann",
                " Mark Weber",
                " Marvin Eisenberger",
                " Andrés Camero",
                " Jingliang Hu",
                " Ariadna Pregel Hoderlein",
                " Çağlar Şenaras",
                " Timothy Davis",
                " Daniel Cremers",
                " Giovanni Marchisio",
                " Xiao Xiang Zhu",
                " Laura Leal-Taixé"
            ]
        },
        {
            "paperId": "4793",
            "posterId": "238b",
            "title": "Open Challenges in Deep Stereo: The Booster Dataset",
            "authors": [
                "Pierluigi Zama Ramirez",
                " Fabio Tosi",
                " Matteo Poggi",
                " Samuele Salti",
                " Stefano Mattoccia",
                " Luigi Di Stefano"
            ]
        },
        {
            "paperId": "2647",
            "posterId": "239b",
            "title": "No-Reference Point Cloud Quality Assessment via Domain Adaptation",
            "authors": [
                "Qi Yang",
                " Yipeng Liu",
                " Siheng Chen",
                " Yiling Xu",
                " Jun Sun"
            ]
        },
        {
            "paperId": "1637",
            "posterId": "240b",
            "title": "Exploring Endogenous Shift for Cross-Domain Detection: A Large-Scale Benchmark and Perturbation Suppression Network",
            "authors": [
                "Renshuai Tao",
                " Hainan Li",
                " Tianbo Wang",
                " Yanlu Wei",
                " Yifu Ding",
                " Bowei Jin",
                " Hongping Zhi",
                " Xianglong Liu",
                " Aishan Liu"
            ]
        },
        {
            "paperId": "2810",
            "posterId": "241b",
            "title": "How Good Is Aesthetic Ability of a Fashion Model?",
            "authors": [
                "Xingxing Zou",
                " Kaicheng Pang",
                " Wen Zhang",
                " Waikeung Wong"
            ]
        },
        {
            "paperId": "656",
            "posterId": "242b",
            "title": "Instance-Wise Occlusion and Depth Orders in Natural Scenes",
            "authors": [
                "Hyunmin Lee",
                " Jaesik Park"
            ]
        },
        {
            "paperId": "7655",
            "posterId": "243b",
            "title": "PhoCaL: A Multi-Modal Dataset for Category-Level Object Pose Estimation With Photometrically Challenging Objects",
            "authors": [
                "Pengyuan Wang",
                " HyunJun Jung",
                " Yitong Li",
                " Siyuan Shen",
                " Rahul Parthasarathy Srikanth",
                " Lorenzo Garattoni",
                " Sven Meier",
                " Nassir Navab",
                " Benjamin Busam"
            ]
        },
        {
            "paperId": "436",
            "posterId": "244b",
            "title": "Replacing Labeled Real-Image Datasets With Auto-Generated Contours",
            "authors": [
                "Hirokatsu Kataoka",
                " Ryo Hayamizu",
                " Ryosuke Yamada",
                " Kodai Nakashima",
                " Sora Takashima",
                " Xinyu Zhang",
                " Edgar Josafat Martinez-Noriega",
                " Nakamasa Inoue",
                " Rio Yokota"
            ]
        },
        {
            "paperId": "7315",
            "posterId": "245b",
            "title": "V2C: Visual Voice Cloning",
            "authors": [
                "Qi Chen",
                " Mingkui Tan",
                " Yuankai Qi",
                " Jiaqiu Zhou",
                " Yuanqing Li",
                " Qi Wu"
            ]
        },
        {
            "paperId": "6786",
            "posterId": "246b",
            "title": "M5Product: Self-Harmonized Contrastive Learning for E-Commercial Multi-Modal Pretraining",
            "authors": [
                "Xiao Dong",
                " Xunlin Zhan",
                " Yangxin Wu",
                " Yunchao Wei",
                " Michael C. Kampffmeyer",
                " Xiaoyong Wei",
                " Minlong Lu",
                " Yaowei Wang",
                " Xiaodan Liang"
            ]
        },
        {
            "paperId": "11067",
            "posterId": "247b",
            "title": "It Is Okay To Not Be Okay: Overcoming Emotional Bias in Affective Image Captioning by Contrastive Data Collection",
            "authors": [
                "Youssef Mohamed",
                " Faizan Farooq Khan",
                " Kilichbek Haydarov",
                " Mohamed Elhoseiny"
            ]
        },
        {
            "paperId": "4520",
            "posterId": "248b",
            "title": "From Representation to Reasoning: Towards Both Evidence and Commonsense Reasoning for Video Question-Answering",
            "authors": [
                "Jiangtong Li",
                " Li Niu",
                " Liqing Zhang"
            ]
        },
        {
            "paperId": "718",
            "posterId": "249b",
            "title": "Point Cloud Pre-Training With Natural 3D Structures",
            "authors": [
                "Ryosuke Yamada",
                " Hirokatsu Kataoka",
                " Naoya Chiba",
                " Yukiyasu Domae",
                " Tetsuya Ogata"
            ]
        },
        {
            "paperId": "1658",
            "posterId": "250b",
            "title": "The Auto Arborist Dataset: A Large-Scale Benchmark for Multiview Urban Forest Monitoring Under Domain Shift",
            "authors": [
                "Sara Beery",
                " Guanhang Wu",
                " Trevor Edwards",
                " Filip Pavetic",
                " Bo Majewski",
                " Shreyasee Mukherjee",
                " Stanley Chan",
                " John Morgan",
                " Vivek Rathod",
                " Jonathan Huang"
            ]
        },
        {
            "paperId": "9913",
            "posterId": "251b",
            "title": "AutoMine: An Unmanned Mine Dataset",
            "authors": [
                "Yuchen Li",
                " Zixuan Li",
                " Siyu Teng",
                " Yu Zhang",
                " Yuhang Zhou",
                " Yuchang Zhu",
                " Dongpu Cao",
                " Bin Tian",
                " Yunfeng Ai",
                " Zhe Xuanyuan",
                " Long Chen"
            ]
        },
        {
            "paperId": "11097",
            "posterId": "252b",
            "title": "SmartPortraits: Depth Powered Handheld Smartphone Dataset of Human Portraits for State Estimation, Reconstruction and Synthesis",
            "authors": [
                "Anastasiia Kornilova",
                " Marsel Faizullin",
                " Konstantin Pakulev",
                " Andrey Sadkov",
                " Denis Kukushkin",
                " Azat Akhmetyanov",
                " Timur Akhtyamov",
                " Hekmat Taherinejad",
                " Gonzalo Ferrer"
            ]
        },
        {
            "paperId": "4797",
            "posterId": "253b",
            "title": "BigDatasetGAN: Synthesizing ImageNet With Pixel-Wise Annotations",
            "authors": [
                "Daiqing Li",
                " Huan Ling",
                " Seung Wook Kim",
                " Karsten Kreis",
                " Sanja Fidler",
                " Antonio Torralba"
            ]
        },
        {
            "paperId": "2027",
            "posterId": "254b",
            "title": "Rope3D: The Roadside Perception Dataset for Autonomous Driving and Monocular 3D Object Detection Task",
            "authors": [
                "Xiaoqing Ye",
                " Mao Shu",
                " Hanyu Li",
                " Yifeng Shi",
                " Yingying Li",
                " Guangjie Wang",
                " Xiao Tan",
                " Errui Ding"
            ]
        },
        {
            "paperId": "8222",
            "posterId": "255b",
            "title": "Unifying Panoptic Segmentation for Autonomous Driving",
            "authors": [
                "Oliver Zendel",
                " Matthias Schörghuber",
                " Bernhard Rainer",
                " Markus Murschitz",
                " Csaba Beleznai"
            ]
        },
        {
            "paperId": "10407",
            "posterId": "256b",
            "title": "DAIR-V2X: A Large-Scale Dataset for Vehicle-Infrastructure Cooperative 3D Object Detection",
            "authors": [
                "Haibao Yu",
                " Yizhen Luo",
                " Mao Shu",
                " Yiyi Huo",
                " Zebang Yang",
                " Yifeng Shi",
                " Zhenglong Guo",
                " Hanyu Li",
                " Xing Hu",
                " Jirui Yuan",
                " Zaiqing Nie"
            ]
        },
        {
            "paperId": "3296",
            "posterId": "257b",
            "title": "SHIFT: A Synthetic Driving Dataset for Continuous Multi-Task Domain Adaptation",
            "authors": [
                "Tao Sun",
                " Mattia Segu",
                " Janis Postels",
                " Yuxuan Wang",
                " Luc Van Gool",
                " Bernt Schiele",
                " Federico Tombari",
                " Fisher Yu"
            ]
        },
        {
            "paperId": "11670",
            "posterId": "258b",
            "title": "Ithaca365: Dataset and Driving Perception Under Repeated and Challenging Weather Conditions",
            "authors": [
                "Carlos A. Diaz-Ruiz",
                " Youya Xia",
                " Yurong You",
                " Jose Nino",
                " Junan Chen",
                " Josephine Monica",
                " Xiangyu Chen",
                " Katie Luo",
                " Yan Wang",
                " Marc Emond",
                " Wei-Lun Chao",
                " Bharath Hariharan",
                " Kilian Q. Weinberger",
                " Mark Campbell"
            ]
        },
        {
            "paperId": "",
            "posterId": "",
            "title": "",
            "authors": [
                ""
            ]
        }
    ]
}