@inproceedings{zaranis-etal-2026-well,
    title = "How Well Do Vision-Language Models Understand Movies?",
    author = "Zaranis, Emmanouil  and
      Farinhas, Ant{\'o}nio  and
      Santos, Saul  and
      Canaverde, Beatriz  and
      Ramos, Miguel Moura  and
      Mohammed, Wafaa  and
      Attanasio, Giuseppe  and
      Zerva, Chrysoula  and
      Sivakumaran, Nithin  and
      Yu, Shoubin  and
      Bueno-Benito, Elena  and
      Surikuchi, Aditya K  and
      Peters, Ben  and
      Sanchez Villegas, Danae  and
      Viveiros, Andre G.  and
      Vasylenko, Pavlo  and
      Liao, Baohao  and
      Sannigrahi, Sonal  and
      Yoon, Jaehong  and
      Stengel-Eskin, Elias  and
      Dimiccoli, Mariella  and
      Lanz, Oswald  and
      Suglia, Alessandro  and
      Bansal, Mohit  and
      Pezzelle, Sandro  and
      Frank, Stella  and
      Niculae, Vlad  and
      Elliott, Desmond  and
      Bernardi, Raffaella  and
      Fern{\'a}ndez, Raquel  and
      Martins, Andre",
    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.1702/",
    pages = "38762--38801",
    ISBN = "979-8-89176-459-0"
}