@misc{qian2022multimodal,
  title={Multimodal Open-Vocabulary Video Classification via Pre-Trained Vision and Language Models},
  author={Rui Qian and Yeqing Li and Zheng Xu and Ming-Hsuan Yang and Serge Belongie and Yin Cui},
  year={2022},
  eprint={2207.07646},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2207.07646}
}