@inproceedings{chen-etal-2026-towards,
    title = "Towards Fine-grained Audio Captioning with Multimodal Contextual Fusion",
    author = "Chen, Shunian  and
      Xie, Xinyuan  and
      Chen, Zheshu  and
      Lee, Owen  and
      Zhao, Liyan  and
      Su, Zhan  and
      Sun, Qilin  and
      Wang, Benyou",
    editor = "Liakata, Maria  and
      Moreira, Viviane P.  and
      Zhang, Jiajun  and
      Jurgens, David",
    booktitle = "Proceedings of the 64th Annual Meeting of the {A}ssociation for {C}omputational {L}inguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2026",
    address = "San Diego, California, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-acl/2026.acl-long.1285/",
    pages = "27888--27913",
    ISBN = "979-8-89176-390-6"
}