@inproceedings{cho-etal-2025-learning,
    title = "Learning to See through Sound: From {V}gg{C}aps to {M}ulti2{C}ap for Richer Automated Audio Captioning",
    author = "Cho, Sangyeon  and
      Kim, Mingi  and
      Hwang, Jinkwon  and
      Go, Jaehoon  and
      Ma, Minuk  and
      Yoon, Sunjae  and
      Kim, Junyeong",
    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.715/",
    pages = "14168--14186",
    ISBN = "979-8-89176-332-6"
}