OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning

Official implementation of the paper "OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning".

Citation

If you find our work, this repository, or pretrained models useful, please consider giving a star ⭐ and citation.

@article{liu2024omniclip,
  title={OmniCLIP: Adapting CLIP for Video Recognition with Spatial-Temporal Omni-Scale Feature Learning},
  author={Liu, Mushui and Li, Bozheng and Yu, Yunlong},
  journal={arXiv preprint arXiv:2408.06158},
  year={2024}
}

Contact

If you have any questions, please create an issue on this repository or contact at lms@zju.edu.cn.