@inproceedings{li-etal-2022-unimo,
    title = "{UNIMO}-2: End-to-End Unified Vision-Language Grounded Learning",
    author = "Li, Wei  and
      Gao, Can  and
      Niu, Guocheng  and
      Xiao, Xinyan  and
      Liu, Hao  and
      Liu, Jiachen  and
      Wu, Hua  and
      Wang, Haifeng",
    editor = "Muresan, Smaranda  and
      Nakov, Preslav  and
      Villavicencio, Aline",
    booktitle = "Findings of the Association for Computational Linguistics: ACL 2022",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.findings-acl.251/",
    doi = "10.18653/v1/2022.findings-acl.251",
    pages = "3187--3201"
}