@inproceedings{gupta-etal-2026-visual,
    title = "From Visual Cues to Spoken Narration: Rethinking Audio Description",
    author = "Gupta, Akshita  and
      Arora, Aditya  and
      Tombari, Federico  and
      Rohrbach, Marcus  and
      Rohrbach, Anna",
    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.432/",
    pages = "9913--9938",
    ISBN = "979-8-89176-459-0"
}