@inproceedings{wang-etal-2023-weakly,
    title = "Weakly-Supervised Spoken Video Grounding via Semantic Interaction Learning",
    author = "Wang, Ye  and
      Lin, Wang  and
      Zhang, Shengyu  and
      Jin, Tao  and
      Li, Linjun  and
      Cheng, Xize  and
      Zhao, Zhou",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2023.acl-long.611/",
    doi = "10.18653/v1/2023.acl-long.611",
    pages = "10914--10932"
}