@inproceedings{li-etal-2022-end,
    title = "End-to-End Modeling via Information Tree for One-Shot Natural Language Spatial Video Grounding",
    author = "Li, Mengze  and
      Wang, Tianbao  and
      Zhang, Haoyu  and
      Zhang, Shengyu  and
      Zhao, Zhou  and
      Miao, Jiaxu  and
      Zhang, Wenqiao  and
      Tan, Wenming  and
      Wang, Jin  and
      Wang, Peng  and
      Pu, Shiliang  and
      Wu, Fei",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Proceedings of the 60th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.acl-long.596/",
    doi = "10.18653/v1/2022.acl-long.596",
    pages = "8707--8717"
}