AimCLR
This is an official PyTorch implementation of “Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition” in AAAI2022.
Model | NTU 60 xsub (%) | NTU 60 xview (%) | PKU-MMD Part I (%) |
---|---|---|---|
AimCLR-joint | 74.34 | 79.68 | 83.43 |
AimCLR-motion | 68.68 | 71.83 | 72.00 |
AimCLR-bone | 71.87 | 77.02 | 82.03 |
3s-AimCLR | 79.18 | 84.02 | 87.79 |
Visualization
The t-SNE visualization of the embeddings after AimCLR pre-training on NTU60-xsub.
Citation
Please cite our paper if you find this repository useful in your resesarch:
@inproceedings{guo2022aimclr,
Title= {Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition},
Author= {Tianyu, Guo and Hong, Liu and Zhan, Chen and Mengyuan, Liu and Tao, Wang and Runwei, Ding},
Booktitle= {AAAI},
Year= {2022}
}
Acknowledgement
The framework of our code is extended from the following repositories. We sincerely thank the authors for releasing the codes.
- The framework of our code is based on CrosSCLR.
- The encoder is based on .
Licence
This project is licensed under the terms of the MIT license.