DecoupleGCN-DropGraph, ASGCN, AGCN, STGCN.
You need to download Paddle Video and add them in the folder about action recognition.
Ensemble these methods can yield good results. We won the top 1% in the figure skater action recognition competition held by Baidu 2021.
@misc{LiASGCN,
title={Actional-Structural Graph Convolutional Networks for Skeleton-based Action Recognition},
author={Maosen Li, Siheng Chen, Xu Chen, Ya Zhang, Yanfeng Wang, Qi Tian},
year={2019},
eprint={1904.12659},
archivePrefix={arXiv},
primaryClass={eess.IV}
}
@inproceedings{cheng2020eccv,
title = {Decoupling GCN with DropGraph Module for Skeleton-Based Action Recognition},
author = {Ke Cheng and Yifan Zhang and Congqi Cao and Lei Shi and Jian Cheng and Hanqing Lu},
booktitle = {Proceedings of the European Conference on Computer Vision (ECCV)},
year = {2020},
}
@article{shi_skeleton-based_2019,
title = {Skeleton-{Based} {Action} {Recognition} with {Multi}-{Stream} {Adaptive} {Graph} {Convolutional} {Networks}},
journal = {arXiv:1912.06971 [cs]},
author = {Shi, Lei and Zhang, Yifan and Cheng, Jian and LU, Hanqing},
month = dec,
year = {2019},
}
@inproceedings{2sagcn2019cvpr,
title = {Two-Stream Adaptive Graph Convolutional Networks for Skeleton-Based Action Recognition},
author = {Lei Shi and Yifan Zhang and Jian Cheng and Hanqing Lu},
booktitle = {CVPR},
year = {2019},
}
@inproceedings{yan2018spatial,
title={Spatial temporal graph convolutional networks for skeleton-based action recognition},
author={Yan, Sijie and Xiong, Yuanjun and Lin, Dahua},
booktitle={Thirty-Second AAAI Conference on Artificial Intelligence},
year={2018}
}