@inproceedings{wazni-etal-2024-verbclip,
    title = "{V}erb{CLIP}: Improving Verb Understanding in Vision-Language Models with Compositional Structures",
    author = "Wazni, Hadi  and
      Lo, Kin Ian  and
      Sadrzadeh, Mehrnoosh",
    editor = "Gu, Jing  and
      Fu, Tsu-Jui (Ray)  and
      Hudson, Drew  and
      Celikyilmaz, Asli  and
      Wang, William",
    booktitle = "Proceedings of the 3rd Workshop on Advances in Language and Vision Research (ALVR)",
    month = aug,
    year = "2024",
    address = "Bangkok, Thailand",
    publisher = "Association for Computational Linguistics",
    url = "https://preview.aclanthology.org/fix-sig-urls/2024.alvr-1.17/",
    doi = "10.18653/v1/2024.alvr-1.17",
    pages = "195--201"
}