@inproceedings{bhattacharyya-etal-2023-video,
    title = "A Video Is Worth 4096 Tokens: Verbalize Videos To Understand Them In Zero Shot",
    author = "Bhattacharyya, Aanisha  and
      Singla, Yaman K  and
      Krishnamurthy, Balaji  and
      Shah, Rajiv Ratn  and
      Chen, Changyou",
    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.608/",
    doi = "10.18653/v1/2023.emnlp-main.608",
    pages = "9822--9839"
}