@inproceedings{xu-etal-2021-videoclip,
    title = "{V}ideo{CLIP}: Contrastive Pre-training for Zero-shot Video-Text Understanding",
    author = "Xu, Hu  and
      Ghosh, Gargi  and
      Huang, Po-Yao  and
      Okhonko, Dmytro  and
      Aghajanyan, Armen  and
      Metze, Florian  and
      Zettlemoyer, Luke  and
      Feichtenhofer, Christoph",
    editor = "Moens, Marie-Francine  and
      Huang, Xuanjing  and
      Specia, Lucia  and
      Yih, Scott Wen-tau",
    booktitle = "Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2021",
    address = "Online and Punta Cana, Dominican Republic",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2021.emnlp-main.544/",
    doi = "10.18653/v1/2021.emnlp-main.544",
    pages = "6787--6800"
}