@inproceedings{wiriyathammabhum-etal-2019-referring,
    title = "Referring to Objects in Videos Using Spatio-Temporal Identifying Descriptions",
    author = "Wiriyathammabhum, Peratham  and
      Shrivastava, Abhinav  and
      Morariu, Vlad  and
      Davis, Larry",
    editor = "Bernardi, Raffaella  and
      Fernandez, Raquel  and
      Gella, Spandana  and
      Kafle, Kushal  and
      Kanan, Christopher  and
      Lee, Stefan  and
      Nabi, Moin",
    booktitle = "Proceedings of the Second Workshop on Shortcomings in Vision and Language",
    month = jun,
    year = "2019",
    address = "Minneapolis, Minnesota",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/W19-1802/",
    doi = "10.18653/v1/W19-1802",
    pages = "14--25"
}