@inproceedings{kudo-etal-2023-challenging,
    title = "A Challenging Multimodal Video Summary: Simultaneously Extracting and Generating Keyframe-Caption Pairs from Video",
    author = "Kudo, Keito  and
      Nagasawa, Haruki  and
      Suzuki, Jun  and
      Shimizu, Nobuyuki",
    editor = "Bouamor, Houda  and
      Pino, Juan  and
      Bali, Kalika",
    booktitle = "Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing",
    month = dec,
    year = "2023",
    address = "Singapore",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2023.emnlp-main.457/",
    doi = "10.18653/v1/2023.emnlp-main.457",
    pages = "7380--7402"
}