@misc{yang2023large,
  title={Vid2Seq: Large-Scale Pretraining of a Visual Language Model for Dense Video Captioning},
  author={Antoine Yang and Arsha Nagrani and Paul Hongsuck Seo and Antoine Miech and Jordi Pont-Tuset and Ivan Laptev and Josef Sivic and Cordelia Schmid},
  year={2023},
  eprint={2302.14115},
  archivePrefix={arXiv},
  primaryClass={cs.CV},
  url={https://arxiv.org/abs/2302.14115}
}