@inproceedings{wang-etal-2022-distilled,
    title = "Distilled Dual-Encoder Model for Vision-Language Understanding",
    author = "Wang, Zekun  and
      Wang, Wenhui  and
      Zhu, Haichao  and
      Liu, Ming  and
      Qin, Bing  and
      Wei, Furu",
    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://preview.aclanthology.org/fix-sig-urls/2022.emnlp-main.608/",
    doi = "10.18653/v1/2022.emnlp-main.608",
    pages = "8901--8913"
}