CVPR2022-AURL

This is the implementation of our AURL paper "Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification".

Results on the UCF-101 dataset:

Results on the HMDB-51 dataset:

Citation

If you find the code useful, please cite our AURL:

@inproceedings{shi-cvpr22-AURL,
    author    = {Shi Pu, Kaili Zhao, and Mao Zheng}, 
    title     = {Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification}, 
    booktitle = {IEEE Conference on Computer Vision and Pattern Recognition},    
    year      = {2022}
}

Acknowledgment

The code of our work is based on the pipeline of "https://github.com/bbrattoli/ZeroShotVideoClassification".
Thanks for the code and training protocol.