@inproceedings{wang-etal-2024-videocot,
    title = "{V}ideo{C}o{T}: A Video Chain-of-Thought Dataset with Active Annotation Tool",
    author = "Wang, Yan  and
      Zeng, Yawen  and
      Zheng, Jingsheng  and
      Xing, Xiaofen  and
      Xu, Jin  and
      Xu, Xiangmin",
    editor = "Gu, Jing  and
      Fu, Tsu-Jui (Ray)  and
      Hudson, Drew  and
      Celikyilmaz, Asli  and
      Wang, William",
    booktitle = "Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.alvr-1.8/",
    doi = "10.18653/v1/2024.alvr-1.8",
    pages = "92--101"
}