ShakedDovrat / mmskeleton

Spatial Temporal Graph Convolutional Networks (ST-GCN) for Skeleton-Based Action Recognition in PyTorch

MMSkeleton

Introduction

MMSkeleton is an open source toolbox for skeleton-based human understanding. It is a part of the open-mmlab project in the charge of Multimedia Laboratory, CUHK. MMSkeleton is developed on our research project ST-GCN.

Updates

• [2019-08-29] MMSkeleton v0.5 is released.
• [2019-09-23] Add video-based pose estimation demo.

Features

• High extensibility

  MMSkeleton provides a flexible framework for organizing codes and projects systematically, with the ability to extend to various tasks and scale up to complex deep models.

• Multiple tasks

  MMSkeleton addresses to multiple tasks in human understanding, including but not limited to:

  • skeleton-based action recognition: [ST-GCN]
  • 2D pose estimation: [START_POSE_ESTIMATION.md]
  • skeleton-based action generation
  • 3D pose estimation
  • pose tracking

Getting Started

Please see GETTING_STARTED.md and START_RECOGNITION.md for more details of MMSkeleton.

License

The project is release under the Apache 2.0 license.

Contributing

We appreciate all contributions to improve MMSkeleton. Please refer to CONTRIBUTING.md for the contributing guideline.

Citation

Please cite the following paper if you use this repository in your reseach.

@inproceedings{stgcn2018aaai,
  title     = {Spatial Temporal Graph Convolutional Networks for Skeleton-Based Action Recognition},
  author    = {Sijie Yan and Yuanjun Xiong and Dahua Lin},
  booktitle = {AAAI},
  year      = {2018},
}

Contact

For any question, feel free to contact

Sijie Yan     : [e-mail]
Yuanjun Xiong : [e-mail]