@inproceedings{ayyubi-etal-2024-views,
    title = "{VIEWS}: Entity-Aware News Video Captioning",
    author = "Ayyubi, Hammad  and
      Liu, Tianqi  and
      Nagrani, Arsha  and
      Lin, Xudong  and
      Zhang, Mingda  and
      Arnab, Anurag  and
      Han, Feng  and
      Zhu, Yukun  and
      Feng, Xuande  and
      Zhang, Kevin  and
      Liu, Jialu  and
      Chang, Shih-Fu",
    editor = "Al-Onaizan, Yaser  and
      Bansal, Mohit  and
      Chen, Yun-Nung",
    booktitle = "Proceedings of the 2024 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2024",
    address = "Miami, Florida, USA",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.emnlp-main.1128/",
    doi = "10.18653/v1/2024.emnlp-main.1128",
    pages = "20220--20239"
}