{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:12Z","timestamp":1777889652364,"version":"3.51.4"},"reference-count":53,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62176224,62176092,62222602,62306165"],"award-info":[{"award-number":["62176224,62176092,62222602,62306165"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01860","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"19999-20008","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Schema Proximity Network for Composed Image Retrieval"],"prefix":"10.1109","author":[{"given":"Jiangming","family":"Shi","sequence":"first","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangbo","family":"Yin","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yeyun","family":"Chen","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yachao","family":"Zhang","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhizhong","family":"Zhang","sequence":"additional","affiliation":[{"name":"East China Normal University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yuan","family":"Xie","sequence":"additional","affiliation":[{"name":"Shanghai Innovation Institute"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yanyun","family":"Qu","sequence":"additional","affiliation":[{"name":"Xiamen University,Key Laboratory of Multimedia Trusted Perception and Efficient Computing, Ministry of Education of China, School of Informatics"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00213"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3346434"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02308"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01828"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i3.32301"},{"key":"ref7","article-title":"Composed image retrieval with text feedback via multi-grained uncertainty regularization","author":"Chen","year":"2024","journal-title":"ICLR"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2022.3222965"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01030"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_26"},{"key":"ref11","first-page":"99715","article-title":"Learning commonality, divergence and variety for unsupervised visible-infrared person reidentification","volume":"37","author":"Shi","year":"2024","journal-title":"NeurIPS"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374221"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2023.3309551"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2025.3558586"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3359062"},{"key":"ref17","author":"Dodds","year":"2020","journal-title":"Modality-agnostic attention fusion for visual search with text feedback"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01407"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01850"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28324"},{"key":"ref23","article-title":"Sentence-level prompts benefit composed image retrieval","author":"Bai","year":"2024","journal-title":"ICLR"},{"key":"ref24","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","author":"Radford","year":"2021","journal-title":"ICML"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3462996"},{"key":"ref26","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","author":"Bao","year":"2022","journal-title":"NeurIPS"},{"key":"ref27","first-page":"12888","article-title":"Blip: Bootstrapping language-image pre-training for unified vision-language understanding and generation","author":"Li","year":"2022","journal-title":"ICML"},{"key":"ref28","first-page":"19730","article-title":"Blip-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"ICML"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00543"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i13.29416"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01343"},{"key":"ref32","article-title":"Sinkhorn distances: Lightspeed computation of optimal transport","volume":"26","author":"Cuturi","year":"2013","journal-title":"NeurIPS"},{"issue":"1","key":"ref33","first-page":"723","article-title":"A kernel two-sample test","volume":"13","author":"Gretton","year":"2012","journal-title":"The Journal of Machine Learning Research"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.175"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01653"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680808"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.5040\/9798216007562-117"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00565"},{"key":"ref40","author":"Gu","year":"2023","journal-title":"Compodiff: Versatile composed image retrieval with latent diffusion"},{"issue":"3","key":"ref41","first-page":"7","volume":"2","author":"Levy","year":"2023","journal-title":"Data roaming and early fusion for composed image retrieval"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"ref43","author":"Jiang","year":"2023","journal-title":"Dual relation alignment for composed image retrieval"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657823"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58542-6_9"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref49","author":"Yu","year":"2020","journal-title":"Curlingnet: Compositional learning between images and text for fashion iq data"},{"key":"ref50","author":"Shin","year":"2021","journal-title":"Rtic: Residual learning for text and image composition using graph convolutional network"},{"key":"ref51","author":"Chen","year":"2022","journal-title":"Composed image retrieval with text feedback via multi-grained uncertainty regularization"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112135"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00262"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11443457.pdf?arnumber=11443457","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:21Z","timestamp":1777612461000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443457\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":53,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01860","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}