@inproceedings{hessel-etal-2020-beyond,
    title = "Beyond Instructional Videos: Probing for More Diverse Visual-Textual Grounding on {Y}ou{T}ube",
    author = "Hessel, Jack  and
      Zhu, Zhenhai  and
      Pang, Bo  and
      Soricut, Radu",
    editor = "Webber, Bonnie  and
      Cohn, Trevor  and
      He, Yulan  and
      Liu, Yang",
    booktitle = "Proceedings of the 2020 Conference on Empirical Methods in Natural Language Processing (EMNLP)",
    month = nov,
    year = "2020",
    address = "Online",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.emnlp-main.709/",
    doi = "10.18653/v1/2020.emnlp-main.709",
    pages = "8812--8822"
}