@inproceedings{chen-etal-2025-vidcapbench,
    title = "{V}id{C}ap{B}ench: A Comprehensive Benchmark of Video Captioning for Controllable Text-to-Video Generation",
    author = "Chen, Xinlong  and
      Zhang, Yuanxing  and
      Rao, Chongling  and
      Guan, Yushuo  and
      Liu, Jiaheng  and
      Zhang, Fuzheng  and
      Song, Chengru  and
      Liu, Qiang  and
      Zhang, Di  and
      Tan, Tieniu",
    editor = "Che, Wanxiang  and
      Nabende, Joyce  and
      Shutova, Ekaterina  and
      Pilehvar, Mohammad Taher",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2025",
    month = jul,
    year = "2025",
    address = "Vienna, Austria",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/landing_page/2025.findings-acl.449/",
    pages = "8543--8563",
    ISBN = "979-8-89176-256-5"
}