@inproceedings{jiang-etal-2024-comclip,
    title = "{C}om{CLIP}: Training-Free Compositional Image and Text Matching",
    author = "Jiang, Kenan  and
      He, Xuehai  and
      Xu, Ruize  and
      Wang, Xin",
    editor = "Duh, Kevin  and
      Gomez, Helena  and
      Bethard, Steven",
    booktitle = "Proceedings of the 2024 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies (Volume 1: Long Papers)",
    month = jun,
    year = "2024",
    address = "Mexico City, Mexico",
    publisher = "Association for Computational Linguistics",
    url = "https://aclanthology.org/2024.naacl-long.370/",
    doi = "10.18653/v1/2024.naacl-long.370",
    pages = "6639--6659"
}