Home

Awesome

AdaSGN

AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition

Note

pytorch>=1.6

Data Preparation

Under the "code" forder:

Training & Testing

Using NTU-60-CV as an example:

Citation

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

@inproceedings{adasgn2021iccv,  
      title     = {AdaSGN: Adapting Joint Number and Model Size for Efficient Skeleton-Based Action Recognition},  
      author    = {Lei Shi and Yifan Zhang and Jian Cheng and Hanqing Lu},  
      booktitle = {ICCV},  
      year      = {2021},  
}

Contact

For any questions, feel free to contact: lei.shi@nlpr.ia.ac.cn