@inproceedings{chen-etal-2022-end,
    title = "End-to-End Unsupervised Vision-and-Language Pre-training with Referring Expression Matching",
    author = "Chen, Chi  and
      Li, Peng  and
      Sun, Maosong  and
      Liu, Yang",
    editor = "Goldberg, Yoav  and
      Kozareva, Zornitsa  and
      Zhang, Yue",
    booktitle = "Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2022",
    address = "Abu Dhabi, United Arab Emirates",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.emnlp-main.742/",
    doi = "10.18653/v1/2022.emnlp-main.742",
    pages = "10799--10810"
}