@inproceedings{mirchandani-etal-2022-fad,
    title = "{F}a{D}-{VLP}: Fashion Vision-and-Language Pre-training towards Unified Retrieval and Captioning",
    author = "Mirchandani, Suvir  and
      Yu, Licheng  and
      Wang, Mengjiao  and
      Sinha, Animesh  and
      Jiang, Wenwen  and
      Xiang, Tao  and
      Zhang, Ning",
    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.716/",
    doi = "10.18653/v1/2022.emnlp-main.716",
    pages = "10484--10497"
}