@inproceedings{kim-etal-2026-seeing,
    title = "Seeing Before Synthesizing: {VLM}-Guided Transition Event Discovery for Weakly-Supervised Dense Video Captioning",
    author = "Kim, Ye-Chan  and
      Choi, Seunghee  and
      Cha, SeungJu  and
      Kim, Si-Woo  and
      Kim, Hwiseon  and
      Kim, HyunGee  and
      Kim, Dong-Jin",
    editor = "Lee, Hung-Yi  and
      Dev, Sunipa  and
      Li, Jessy  and
      Elliott, Desmond",
    booktitle = "Proceedings of the 2026 Conference on Empirical Methods in Natural Language Processing",
    month = oct,
    year = "2026",
    address = "Budapest, Hungary",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2026.emnlp-main.1555/",
    pages = "35464--35475",
    ISBN = "979-8-89176-459-0"
}