@inproceedings{fang-etal-2020-video2commonsense,
    title = "{V}ideo2{C}ommonsense: Generating Commonsense Descriptions to Enrich Video Captioning",
    author = "Fang, Zhiyuan  and
      Gokhale, Tejas  and
      Banerjee, Pratyay  and
      Baral, Chitta  and
      Yang, Yezhou",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/2020.emnlp-main.61/",
    doi = "10.18653/v1/2020.emnlp-main.61",
    pages = "840--860"
}