@inproceedings{le-etal-2022-vgnmn,
    title = "{VGNMN}: Video-grounded Neural Module Networks for Video-Grounded Dialogue Systems",
    author = "Le, Hung  and
      Chen, Nancy  and
      Hoi, Steven",
    editor = "Carpuat, Marine  and
      de Marneffe, Marie-Catherine  and
      Meza Ruiz, Ivan Vladimir",
    booktitle = "Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jul,
    year = "2022",
    address = "Seattle, United States",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/jlcl-multiple-ingestion/2022.naacl-main.247/",
    doi = "10.18653/v1/2022.naacl-main.247",
    pages = "3377--3393"
}