@inproceedings{zhang-etal-2024-unsupervised,
    title = "Unsupervised Multimodal Clustering for Semantics Discovery in Multimodal Utterances",
    author = "Zhang, Hanlei  and
      Xu, Hua  and
      Long, Fei  and
      Wang, Xin  and
      Gao, Kai",
    editor = "Ku, Lun-Wei  and
      Martins, Andre  and
      Srikumar, Vivek",
    booktitle = "Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.acl-long.2/",
    doi = "10.18653/v1/2024.acl-long.2",
    pages = "18--35"
}