@article{evilmefficientvideolanguagemodelvia,
  title = {E-ViLM: Efficient Video-Language Model via Masked Video Modeling with Semantic Vector-Quantized Tokenizer},
  author = {Jacob Zhiyuan Fang and Skyler Zheng and Vasu Sharma and Robinson Piramuthu},
  year = {2023},
  eprint = {2311.17267},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2311.17267v1},
}