@inproceedings{xu-etal-2021-vlm,
    title = "{VLM}: Task-agnostic Video-Language Model Pre-training for Video Understanding",
    author = "Xu, Hu  and
      Ghosh, Gargi  and
      Huang, Po-Yao  and
      Arora, Prahal  and
      Aminzadeh, Masoumeh  and
      Feichtenhofer, Christoph  and
      Metze, Florian  and
      Zettlemoyer, Luke",
    editor = "Zong, Chengqing  and
      Xia, Fei  and
      Li, Wenjie  and
      Navigli, Roberto",
    booktitle = "Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021",
    month = aug,
    year = "2021",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.findings-acl.370/",
    doi = "10.18653/v1/2021.findings-acl.370",
    pages = "4227--4239"
}