@inproceedings{pennec-etal-2025-integrating,
    title = "Integrating Video and Text: A Balanced Approach to Multimodal Summary Generation and Evaluation",
    author = "Pennec, Galann  and
      Liu, Zhengyuan  and
      Asher, Nicholas  and
      Muller, Philippe  and
      Chen, Nancy F.",
    editor = "Inui, Kentaro  and
      Sakti, Sakriani  and
      Wang, Haofen  and
      Wong, Derek F.  and
      Bhattacharyya, Pushpak  and
      Banerjee, Biplab  and
      Ekbal, Asif  and
      Chakraborty, Tanmoy  and
      Singh, Dhirendra Pratap",
    booktitle = "Proceedings of the 14th International Joint Conference on Natural Language Processing and the 4th Conference of the Asia-Pacific Chapter of the Association for Computational Linguistics",
    month = dec,
    year = "2025",
    address = "Mumbai, India",
    publisher = "The Asian Federation of Natural Language Processing and The Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-ijcnlp-aacl/2025.ijcnlp-long.129/",
    pages = "2403--2426",
    ISBN = "979-8-89176-298-5"
}