@misc{chen2021multi,
  title={MM-ViT: Multi-Modal Video Transformer for Compressed Video Action Recognition},
  author={Jiawei Chen and Chiu Man Ho},
  year={2021},
  eprint={2108.09322},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2108.09322}
}