@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" }