@misc{zhang2023video,
  title={Video-LLaMA: An Instruction-tuned Audio-Visual Language Model for Video Understanding},
  author={Hang Zhang and Xin Li and Lidong Bing},
  year={2023},
  eprint={2306.02858},
  archivePrefix={arXiv},
  primaryClass={cs.CL},
  url={https://arxiv.org/abs/2306.02858}
}