@inproceedings{wang-etal-2023-vstar,
    title = "{VSTAR}: A Video-grounded Dialogue Dataset for Situated Semantic Understanding with Scene and Topic Transitions",
    author = "Wang, Yuxuan  and
      Zheng, Zilong  and
      Zhao, Xueliang  and
      Li, Jinpeng  and
      Wang, Yueqian  and
      Zhao, Dongyan",
    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://preview.aclanthology.org/landing_page/2023.acl-long.276/",
    doi = "10.18653/v1/2023.acl-long.276",
    pages = "5036--5048"
}