@inproceedings{li-etal-2021-unsupervised,
    title = "Unsupervised Vision-and-Language Pre-training Without Parallel Images and Captions",
    author = "Li, Liunian Harold  and
      You, Haoxuan  and
      Wang, Zhecan  and
      Zareian, Alireza  and
      Chang, Shih-Fu  and
      Chang, Kai-Wei",
    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/Author-page-Marten-During-lu/2021.naacl-main.420/",
    doi = "10.18653/v1/2021.naacl-main.420",
    pages = "5339--5350"
}