@inproceedings{zhang-etal-2025-pretrained,
    title = "Pretrained Image-Text Models are Secretly Video Captioners",
    author = "Zhang, Chunhui  and
      Jian, Yiren  and
      Ouyang, Zhongyu  and
      Vosoughi, Soroush",
    editor = "Chiruzzo, Luis  and
      Ritter, Alan  and
      Wang, Lu",
    booktitle = "Proceedings of the 2025 Conference of the Nations of the Americas Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 2: Short Papers)",
    month = apr,
    year = "2025",
    address = "Albuquerque, New Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/moar-dois/2025.naacl-short.26/",
    doi = "10.18653/v1/2025.naacl-short.26",
    pages = "292--305",
    ISBN = "979-8-89176-190-2"
}