This is the implementation of our AURL paper "Alignment-Uniformity aware Representation Learning for Zero-shot Video Classification".
The pipeline is built upon the CVPR 2020 work for your reference: https://github.com/bbrattoli/ZeroShotVideoClassification.
If you find the code useful, please cite both AURL and the CVPR 2020 work:
@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}
}
@inproceedings{brattoli2020rethinking,
title={Rethinking zero-shot video classification: End-to-end training for realistic applications},
author={Brattoli, Biagio and Tighe, Joseph and Zhdanov, Fedor and Perona, Pietro and Chalupka, Krzysztof},
booktitle={IEEE Conference on Computer Vision and Pattern Recognition},
pages={4613--4623},
year={2020}
}