@inproceedings{pirhadi-etal-2025-cvt5,
    title = "{CVT}5: Using Compressed Video Encoder and {UMT}5 for Dense Video Captioning",
    author = "Pirhadi, Mohammad Javad  and
      Mirzaei, Motahhare  and
      Eetemadi, Sauleh",
    editor = "Zhang, Wei Emma  and
      Dai, Xiang  and
      Elliot, Desmond  and
      Fang, Byron  and
      Sim, Mongyuan  and
      Zhuang, Haojie  and
      Chen, Weitong",
    booktitle = "Proceedings of the First Workshop of Evaluation of Multi-Modal Generation",
    month = jan,
    year = "2025",
    address = "Abu Dhabi, UAE",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2025.evalmg-1.2/",
    pages = "10--23"
}