MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval.

@inproceedings{ge-2026-mcotmvs, author = {Xuri Ge and Chunhao Wang and Xindi Wang and Zheyun Qin and Zhumin Chen and Xin Xin}, editor = {Hakim Hacid and Yoelle Maarek and Francesco Bonchi and Ido Guy and Emine Yilmaz}, title = {{MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval}}, booktitle = {{Proceedings of the ACM Web Conference 2026, WWW 2026, Dubai, United Arab Emirates, originally scheduled for April 13-17, 2026, rescheduled for June 29 - July 3, 2026}}, pages = {2105--2113}, publisher = {ACM}, year = {2026}, url = {https://doi.org/10.1145/3774904.3792287}, doi = {https://doi.org/10.1145/3774904.3792287} }