@inproceedings{himakunthala-etal-2023-lets,
    title = "Let`s Think Frame by Frame with {VIP}: A Video Infilling and Prediction Dataset for Evaluating Video Chain-of-Thought",
    author = "Himakunthala, Vaishnavi  and
      Ouyang, Andy  and
      Rose, Daniel  and
      He, Ryan  and
      Mei, Alex  and
      Lu, Yujie  and
      Sonar, Chinmay  and
      Saxon, Michael  and
      Wang, William",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.emnlp-main.15/",
    doi = "10.18653/v1/2023.emnlp-main.15",
    pages = "204--219"
}