@inproceedings{han-etal-2020-victr,
    title = "{VICTR}: Visual Information Captured Text Representation for Text-to-Vision Multimodal Tasks",
    author = "Han, Caren  and
      Long, Siqu  and
      Luo, Siwen  and
      Wang, Kunze  and
      Poon, Josiah",
    editor = "Scott, Donia  and
      Bel, Nuria  and
      Zong, Chengqing",
    booktitle = "Proceedings of the 28th International Conference on Computational Linguistics",
    month = dec,
    year = "2020",
    address = "Barcelona, Spain (Online)",
    publisher = "International Committee on Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2020.coling-main.277/",
    doi = "10.18653/v1/2020.coling-main.277",
    pages = "3107--3117"
}