ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning.

@inproceedings{luo-2025-imagescope, author = {Pengfei Luo and Jingbo Zhou and Tong Xu and Yuan Xia and Linli Xu and Enhong Chen}, editor = {Guodong Long and Michale Blumestein and Yi Chang and Liane Lewin-Eytan and Zi Huang and Elad Yom-Tov}, title = {{ImageScope: Unifying Language-Guided Image Retrieval via Large Multimodal Model Collective Reasoning}}, booktitle = {{Proceedings of the ACM on Web Conference 2025, WWW 2025, Sydney, NSW, Australia, 28 April 2025- 2 May 2025}}, pages = {1666--1682}, publisher = {ACM}, year = {2025}, url = {https://doi.org/10.1145/3696410.3714777}, doi = {https://doi.org/10.1145/3696410.3714777} }