@inproceedings{wang-etal-2026-avscap,
    title = "{AVSC}ap: Orchestrating Audio-Visual Synergy for Omni-modal Video Captioning",
    author = "Wang, Yanghai  and
      Wang, Jiahao  and
      Tang, Jiafu  and
      Zhang, Yuanxing  and
      Cao, Zhe  and
      Bian, Hanyan  and
      Zhang, Zijie  and
      Luo, Weiliang  and
      Pan, Zhiyu  and
      Dong, Zixuan  and
      Liu, Jiaheng  and
      Zhang, Zhaoxiang",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1433/",
    pages = "32731--32761",
    ISBN = "979-8-89176-459-0"
}