@inproceedings{li-etal-2022-vpai,
    title = "{VPAI}{\_}{L}ab at {M}ed{V}id{QA} 2022: A Two-Stage Cross-modal Fusion Method for Medical Instructional Video Classification",
    author = "Li, Bin  and
      Weng, Yixuan  and
      Xia, Fei  and
      Sun, Bin  and
      Li, Shutao",
    editor = "Demner-Fushman, Dina  and
      Cohen, Kevin Bretonnel  and
      Ananiadou, Sophia  and
      Tsujii, Junichi",
    booktitle = "Proceedings of the 21st Workshop on Biomedical Language Processing",
    month = may,
    year = "2022",
    address = "Dublin, Ireland",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2022.bionlp-1.21/",
    doi = "10.18653/v1/2022.bionlp-1.21",
    pages = "212--219"
}