@inproceedings{singh-etal-2021-mimoqa,
    title = "{MIMOQA}: Multimodal Input Multimodal Output Question Answering",
    author = "Singh, Hrituraj  and
      Nasery, Anshul  and
      Mehta, Denil  and
      Agarwal, Aishwarya  and
      Lamba, Jatin  and
      Srinivasan, Balaji Vasan",
    editor = "Toutanova, Kristina  and
      Rumshisky, Anna  and
      Zettlemoyer, Luke  and
      Hakkani-Tur, Dilek  and
      Beltagy, Iz  and
      Bethard, Steven  and
      Cotterell, Ryan  and
      Chakraborty, Tanmoy  and
      Zhou, Yichao",
    booktitle = "Proceedings of the 2021 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies",
    month = jun,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.naacl-main.418/",
    doi = "10.18653/v1/2021.naacl-main.418",
    pages = "5317--5332"
}