{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,24]],"date-time":"2026-07-24T15:11:32Z","timestamp":1784905892475,"version":"3.55.0"},"reference-count":79,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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":["62220106008"],"award-info":[{"award-number":["62220106008"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U20B2063"],"award-info":[{"award-number":["U20B2063"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102070"],"award-info":[{"award-number":["62102070"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62306067"],"award-info":[{"award-number":["62306067"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62102069"],"award-info":[{"award-number":["62102069"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U23B2011"],"award-info":[{"award-number":["U23B2011"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Sichuan Science and Technology Program","award":["2023NSFSC1392"],"award-info":[{"award-number":["2023NSFSC1392"]}]},{"name":"Sichuan Province Innovative Talent Funding Project for Postdoctoral Fellows, the China Postdoctoral Science Foundation","award":["2022M720660"],"award-info":[{"award-number":["2022M720660"]}]},{"name":"Key R&D Program of Zhejiang","award":["2024SSYS0091"],"award-info":[{"award-number":["2024SSYS0091"]}]},{"name":"New Cornerstone Science Foundation"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tmm.2024.3417694","type":"journal-article","created":{"date-parts":[[2024,6,21]],"date-time":"2024-06-21T17:59:41Z","timestamp":1718992781000},"page":"9936-9948","source":"Crossref","is-referenced-by-count":15,"title":["Align and Retrieve: Composition and Decomposition Learning in Image Retrieval With Text Feedback"],"prefix":"10.1109","volume":"26","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1123-6129","authenticated-orcid":false,"given":"Yahui","family":"Xu","sequence":"first","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9714-8738","authenticated-orcid":false,"given":"Yi","family":"Bin","sequence":"additional","affiliation":[{"name":"National University of Singapore, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3912-1742","authenticated-orcid":false,"given":"Jiwei","family":"Wei","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5070-4511","authenticated-orcid":false,"given":"Yang","family":"Yang","sequence":"additional","affiliation":[{"name":"Center for Future Media, and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3938-5994","authenticated-orcid":false,"given":"Guoqing","family":"Wang","sequence":"additional","affiliation":[{"name":"Center for Future Media and School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2999-2088","authenticated-orcid":false,"given":"Heng Tao","family":"Shen","sequence":"additional","affiliation":[{"name":"Center for Future Multimedia and the School of Computer Science and Engineering, University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tmm.2017.2785253"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2023.103434"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141267"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1145\/3331184.3331198"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475451"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413917"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00307"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3469877.3490601"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475659"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475483"},{"key":"ref13","first-page":"1","article-title":"Artemis: Attention-based retrieval with text-explicit matching and implicit similarity","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Delmas","year":"2022"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01371"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475619"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00365"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1038\/nrn755"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v33i01.33013705"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00473"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1146\/annurev.neuro.26.041002.131047"},{"key":"ref23","first-page":"2204","article-title":"Recurrent models of visual attention","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Mnih","year":"2014"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3065578"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3123266.3123326"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICME.2017.8019425"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612427"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3235495"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00553"},{"key":"ref31","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3477495.3532047"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00262"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00213"},{"key":"ref36","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li","year":"2022"},{"key":"ref37","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"202","author":"Li","year":"2023"},{"key":"ref38","first-page":"1","article-title":"Sentence-level prompts benefit composed image retrieval","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bai","year":"2024"},{"key":"ref39","article-title":"Candidate set re-ranking for composed image retrieval with dual multi-modal encoder","author":"Liu","year":"2023"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00565"},{"key":"ref41","article-title":"Ranking-aware uncertainty for text-guided image retrieval","author":"Chen","year":"2023"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i4.28081"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28334"},{"key":"ref44","first-page":"1","article-title":"Composed image retrieval with text feedback via multi-grained uncertainty regulariza","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen","year":"2024"},{"key":"ref45","article-title":"CompoDiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2023"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16271"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D15-1166"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11971"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/d18-1370"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298186"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3090274"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2862341"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3126686.3126717"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063297"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3238514"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3097502"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3088863"},{"key":"ref61","article-title":"Modality-agnostic attention fusion for visual search with text feedback","author":"Dodds","year":"2020"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref67","first-page":"1","article-title":"Mine: Mutual information neural estimation","volume-title":"Proc. Int. Conf. Mach Learn.","author":"Belghazi","year":"2018"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-15549-9_48"},{"key":"ref70","first-page":"1","article-title":"Dialog-based interactive image retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Guo","year":"2018"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.163"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref73","first-page":"1","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma","year":"2015"},{"key":"ref74","first-page":"1","article-title":"Multimodal residual learning for visual QA","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Kim","year":"2016"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref76","first-page":"4967","article-title":"A simple neural network module for relational reasoning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Santoro","year":"2017"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3208742"},{"key":"ref78","article-title":"Relieving triplet ambiguity: Consensus network for language-guided image retrieval","author":"Zhang","year":"2023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10384483\/10568424.pdf?arnumber=10568424","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,18]],"date-time":"2024-10-18T04:37:09Z","timestamp":1729226229000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10568424\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":79,"URL":"https:\/\/doi.org\/10.1109\/tmm.2024.3417694","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}