pengzhansun / Occluded-Pose-Reasoning

[WACV 2024 Oral] Rethinking Visibility in Human Pose Estimation: Occluded Pose Reasoning via Transformers

Rethinking Visibility in Human Pose Estimation: Occluded Pose Reasoning via Transformers

This code base is the pytorch implementation of the paper:
Rethinking Visibility in Human Pose Estimation: Occluded Pose Reasoning via Transformers, WACV 2024, Oral
Pengzhan Sun, Kerui Gu, Yunsong Wang, Linlin Yang, Angela Yao

• Todo
• Introduction
• Requirements
• Getting Started
• Citation

Todo

1. Clean the codebase
2. Write a Readme for training and inference scripts

Introduction

Requirements

pip install -r requirements.txt

Getting Started

Checkpoint

Citation

If you use this code repository in your research, please cite this paper.

@inproceedings{sun2024rethinking,
  title={Rethinking Visibility in Human Pose Estimation: Occluded Pose Reasoning via Transformers},
  author={Sun, Pengzhan and Gu, Kerui and Wang, Yunsong and Yang, Linlin and Yao, Angela},
  booktitle={Proceedings of the IEEE/CVF Winter Conference on Applications of Computer Vision},
  pages={5903--5912},
  year={2024}
}

Contact: [e-mail]