- 💬 I have worked on human action recognition
- 🔭 I’m currently working on human pose estimation
- 🌱 I’m currently learning about vision language models
- 📫 How to reach me --> [email protected]
Computer Vision for Human Understanding
- Saarbrucken, Germany
-
05:38
(UTC +01:00) - https://www.linkedin.com/in/mnauf
Pinned Loading
-
-
self-driving-car-fyp
self-driving-car-fyp PublicBachelor thesis, training code and report on self-driving-car. Training self driving car on 100K self generated dataset on a custom track
-
vision-transformer-pytorch-implementation
vision-transformer-pytorch-implementation Publicvit_base_patch16_384 implemented from scratch
Jupyter Notebook
-
video-transformer-pytorch-implementation
video-transformer-pytorch-implementation PublicImplementation of ViViT using tubelet embedding
Jupyter Notebook
-
GPT-from-scratch
GPT-from-scratch PublicAdd building blocks one by one to the transformer decoder, and observe the resulting impact with each training
Jupyter Notebook
Something went wrong, please refresh the page to try again.
If the problem persists, check the GitHub status page or contact support.
If the problem persists, check the GitHub status page or contact support.