{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:19:46Z","timestamp":1783153186458,"version":"3.54.6"},"publisher-location":"New York, NY, USA","reference-count":35,"publisher":"ACM","funder":[{"name":"Natural Science Foundation of China","award":["62202271"],"award-info":[{"award-number":["62202271"]}]},{"name":"Natural Science Foundation of China","award":["62472261"],"award-info":[{"award-number":["62472261"]}]},{"name":"Natural Science Foundation of China","award":["62372275"],"award-info":[{"award-number":["62372275"]}]},{"name":"Natural Science Foundation of China","award":["62272274"],"award-info":[{"award-number":["62272274"]}]},{"name":"National Natural Science Foundation of China","award":["T2293773"],"award-info":[{"award-number":["T2293773"]}]},{"name":"the National Key R&D Program of China","award":["2024YFC3307300"],"award-info":[{"award-number":["2024YFC3307300"]}]},{"name":"the Provincial Key R&D Program of Shandong Province","award":["2024CXGC010108"],"award-info":[{"award-number":["2024CXGC010108"]}]},{"name":"the Natural Science Foundation of Shandong Province","award":["ZR2024QF203"],"award-info":[{"award-number":["ZR2024QF203"]}]},{"name":"the Technology Innovation Guidance Program of Shandong Province","award":["YDZX2024088"],"award-info":[{"award-number":["YDZX2024088"]}]},{"name":"the National Key R&D Program of China","award":["2022YFC3303004"],"award-info":[{"award-number":["2022YFC3303004"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,4,13]]},"DOI":"10.1145\/3774904.3792287","type":"proceedings-article","created":{"date-parts":[[2026,4,9]],"date-time":"2026-04-09T21:54:34Z","timestamp":1775771674000},"page":"2105-2113","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["MCoT-MVS: Multi-level Vision Selection by Multi-modal Chain-of-Thought Reasoning for Composed Image Retrieval"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3925-4951","authenticated-orcid":false,"given":"Xuri","family":"Ge","sequence":"first","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-9224-1621","authenticated-orcid":false,"given":"Chunhao","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6548-3547","authenticated-orcid":false,"given":"Xindi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2564-071X","authenticated-orcid":false,"given":"Zheyun","family":"Qin","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4592-4074","authenticated-orcid":false,"given":"Zhumin","family":"Chen","sequence":"additional","affiliation":[{"name":"Shandong University, Jinan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6116-9115","authenticated-orcid":false,"given":"Xin","family":"Xin","sequence":"additional","affiliation":[{"name":"Shandong University, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,4,12]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Learning Representations","author":"Bai Yang","year":"2024","unstructured":"Yang Bai, Xinxing Xu, Yong Liu, Salman Khan, Fahad Khan, Wangmeng Zuo, Rick Siow Mong Goh, and Chun-Mei Feng. 2024. Sentence-level prompts benefit composed image retrieval. International Conference on Learning Representations (2024)."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3617597"},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i2.27885"},{"key":"e_1_3_2_1_6_1","volume-title":"International Conference on Learning Representations","author":"Delmas Ginger","year":"2022","unstructured":"Ginger Delmas, Rafael Sampaio de Rezende, Gabriela Csurka, and Diane Larlus. 2022. Artemis: Attention-based retrieval with text-explicit matching and implicit similarity. International Conference on Learning Representations (2022)."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2025.3608071"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2022.3187290"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/2.410145"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657823"},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the IEEE conference on computer vision and pattern recognition","author":"Karthik Shyamgopal","year":"2023","unstructured":"Shyamgopal Karthik, Karsten Roth, Massimiliano Mancini, and Zeynep Akata. 2023. Vision-by-language for training-free compositional image retrieval. In Proceedings of the IEEE conference on computer vision and pattern recognition (2023)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i5.32541"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1145\/3696410.3714777"},{"key":"e_1_3_2_1_18_1","volume-title":"International conference on machine learning. PmLR, 8748-8763","author":"Radford Alec","year":"2021","unstructured":"Alec Radford, Jong Wook Kim, Chris Hallacy, Aditya Ramesh, Gabriel Goh, Sandhini Agarwal, Girish Sastry, Amanda Askell, Pamela Mishkin, Jack Clark, et al., 2021. Learning transferable visual models from natural language supervision. In International conference on machine learning. PmLR, 8748-8763."},{"key":"e_1_3_2_1_19_1","volume-title":"International Conference on Computer Vision (ICCV) Demo Paper","author":"Ren Tianhe","year":"2024","unstructured":"Tianhe Ren, Shilong Liu, Ailing Zeng, Jing Lin, Kunchang Li, He Cao, Jiayu Chen, Xinyu Huang, Yukang Chen, Feng Yan, et al., 2024. Grounded sam: Assembling open-world models for diverse visual tasks. International Conference on Computer Vision (ICCV) Demo Paper (2024)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P19-1644"},{"key":"e_1_3_2_1_21_1","volume-title":"CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image Retrieval. arXiv preprint arXiv:2502.20826","author":"Sun Zelong","year":"2025","unstructured":"Zelong Sun, Dong Jing, and Zhiwu Lu. 2025a. CoTMR: Chain-of-Thought Multi-Scale Reasoning for Training-Free Zero-Shot Composed Image Retrieval. arXiv preprint arXiv:2502.20826 (2025)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i7.32768"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00376"},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00107"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681493"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657727"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462967"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3357498"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401423"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3235495"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28479"}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774904.3792287","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T08:00:07Z","timestamp":1783152007000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774904.3792287"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4,12]]},"references-count":35,"alternative-id":["10.1145\/3774904.3792287","10.1145\/3774904"],"URL":"https:\/\/doi.org\/10.1145\/3774904.3792287","relation":{},"subject":[],"published":{"date-parts":[[2026,4,12]]},"assertion":[{"value":"2026-04-12","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}