@inproceedings{wang-etal-2018-watch,
    title = "Watch, Listen, and Describe: Globally and Locally Aligned Cross-Modal Attentions for Video Captioning",
    author = "Wang, Xin  and
      Wang, Yuan-Fang  and
      Wang, William Yang",
    editor = "Walker, Marilyn  and
      Ji, Heng  and
      Stent, Amanda",
    booktitle = "Proceedings of the 2018 Conference of the North {A}merican Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 2 (Short Papers)",
    month = jun,
    year = "2018",
    address = "New Orleans, Louisiana",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/add-emnlp-2024-awards/N18-2125/",
    doi = "10.18653/v1/N18-2125",
    pages = "795--801"
}