@inproceedings{chen-etal-2026-capricorn,
    title = "{C}ap{R}i{C}orn-1{K}: A Comprehensive Benchmark for Video Captioning and Subject Referential Consistency Across Temporal Scales",
    author = "Chen, Xinlong  and
      Tang, Jiafu  and
      Ding, Yue  and
      Jia, Yizhuo  and
      Li, Bozhou  and
      Zeng, Bohan  and
      Shi, Yang  and
      Li, Shihao  and
      Ji, Yiyan  and
      Liu, Qiang  and
      Lin, Weihong  and
      Zhang, Yuanxing  and
      Wan, Pengfei  and
      Wang, Liang  and
      Tan, Tieniu",
    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.272/",
    pages = "6171--6197",
    ISBN = "979-8-89176-459-0"
}