@inproceedings{yu-etal-2025-multimodal,
    title = "Multimodal Fusion and Coherence Modeling for Video Topic Segmentation",
    author = "Yu, Hai  and
      Deng, Chong  and
      Zhang, Qinglin  and
      Liu, Jiaqing  and
      Chen, Qian  and
      Wang, Wen",
    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.904/",
    pages = "17577--17593",
    ISBN = "979-8-89176-256-5"
}