Home

Awesome

MST-GCN

This is the official implemntation for "Multi-scale spatial temporal graph convolutional network for skeleton-based action recognition" AAAI-2021 (pdf)

Requirements

Python >=3.6.7 PyTorch >=1.2.0 CUDA >=10.0.130

Data Preparation

NTU RGB+D dataset

Kinetics-Skeleton

Training-Testing

Change the config file depending on what you want.

# train on NTU RGB+D xview joint stream
$ sh run.sh 0,1,2,3 4 2022 0
# or
$ CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 --master_port=2022 main.py --config config/ntu/train_joint_amstgcn_ntu.yaml

Citation

Please cite our paper if you find this repository useful in your resesarch:

@inproceedings{chen2021multi,
  title={Multi-scale spatial temporal graph convolutional network for skeleton-based action recognition},
  author={Chen, Zhan and Li, Sicheng and Yang, Bing and Li, Qinghan and Liu, Hong},
  booktitle={Proceedings of the AAAI Conference on Artificial Intelligence},
  volume={35},
  number={2},
  pages={1113--1122},
  year={2021}
}

Acknowledgement

The framework of our code is extended from the following repositories. We sincerely thank the authors for releasing the codes.

Licence

This project is licensed under the terms of the MIT license.

Contact

For any questions, feel free to contact: zhanchen_cz@pku.edu.cn or czchenzhan@gmail.com