@inproceedings{du-etal-2025-vc4vg,
    title = "{VC}4{VG}: Optimizing Video Captions for Text-to-Video Generation",
    author = "Du, Yang  and
      Lin, Zhuoran  and
      Song, Kaiqiang  and
      Wang, Biao  and
      Zheng, Zhicheng  and
      Ge, Tiezheng  and
      Zheng, Bo  and
      Jin, Qin",
    editor = "Christodoulopoulos, Christos  and
      Chakraborty, Tanmoy  and
      Rose, Carolyn  and
      Peng, Violet",
    booktitle = "Proceedings of the 2025 Conference on Empirical Methods in Natural Language Processing",
    month = nov,
    year = "2025",
    address = "Suzhou, China",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/ingest-emnlp/2025.emnlp-main.59/",
    pages = "1124--1138",
    ISBN = "979-8-89176-332-6",
    abstract = "Recent advances in text-to-video (T2V) generation highlight the critical role of high-quality video-text pairs in training models capable of producing coherent and instruction-aligned videos. However, strategies for optimizing video captions specifically for T2V training remain underexplored. In this paper, we introduce VC4VG (Video Captioning for Video Generation), a comprehensive caption optimization framework tailored to the needs of T2V models. We begin by analyzing caption content from a T2V perspective, decomposing the essential elements required for video reconstruction into multiple dimensions, and proposing a principled caption design methodology. To support evaluation, we construct VC4VG-Bench, a new benchmark featuring fine-grained, multi-dimensional, and necessity-graded metrics aligned with T2V-specific requirements. Extensive T2V fine-tuning experiments demonstrate a strong correlation between improved caption quality and video generation performance, validating the effectiveness of our approach. We release all benchmark tools and code (https://github.com/qyr0403/VC4VG) to support further research."
}