@inproceedings{das-etal-2016-human,
    title = "Human Attention in Visual Question Answering: Do Humans and Deep Networks look at the same regions?",
    author = "Das, Abhishek  and
      Agrawal, Harsh  and
      Zitnick, Larry  and
      Parikh, Devi  and
      Batra, Dhruv",
    editor = "Su, Jian  and
      Duh, Kevin  and
      Carreras, Xavier",
    booktitle = "Proceedings of the 2016 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2016",
    address = "Austin, Texas",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/D16-1092/",
    doi = "10.18653/v1/D16-1092",
    pages = "932--937"
}