@inproceedings{li-etal-2023-unifying,
    title = "Unifying Cross-Lingual and Cross-Modal Modeling Towards Weakly Supervised Multilingual Vision-Language Pre-training",
    author = "Li, Zejun  and
      Fan, Zhihao  and
      Chen, Jingjing  and
      Zhang, Qi  and
      Huang, Xuanjing  and
      Wei, Zhongyu",
    editor = "Rogers, Anna  and
      Boyd-Graber, Jordan  and
      Okazaki, Naoaki",
    booktitle = "Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)",
    month = jul,
    year = "2023",
    address = "Toronto, Canada",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.acl-long.327/",
    doi = "10.18653/v1/2023.acl-long.327",
    pages = "5939--5958"
}