{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T22:11:37Z","timestamp":1782857497820,"version":"3.54.5"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2021ZD0114504"],"award-info":[{"award-number":["2021ZD0114504"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61873066"],"award-info":[{"award-number":["61873066"]}],"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":["62173090"],"award-info":[{"award-number":["62173090"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tmm.2026.3664964","type":"journal-article","created":{"date-parts":[[2026,2,23]],"date-time":"2026-02-23T20:48:39Z","timestamp":1771879719000},"page":"5106-5117","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Constraint Relational Semantic Alignment Toward Image-Text Retrieval"],"prefix":"10.1109","volume":"28","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8030-0868","authenticated-orcid":false,"given":"Yi","family":"Xiao","sequence":"first","affiliation":[{"name":"State Key Laboratory of Digital Medical Engineering, Jiangsu Key Lab of Robot Sensing and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3074-2465","authenticated-orcid":false,"given":"Jun","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Digital Medical Engineering, Jiangsu Key Lab of Robot Sensing and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1982-6780","authenticated-orcid":false,"given":"Aiguo","family":"Song","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Digital Medical Engineering, Jiangsu Key Lab of Robot Sensing and Control, School of Instrument Science and Engineering, Southeast University, Nanjing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3177356"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3128744"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3273719"},{"key":"ref5","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3310118"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2022.3185233"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01280"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20020"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00273"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/62"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3721482"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3407664"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3068825"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266887"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3225754"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3327924"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_42"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3330091"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25072-9_42"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3251104"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3368217"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3152086"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2022.04.081"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01452"},{"key":"ref30","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":"ref31","doi-asserted-by":"publisher","DOI":"10.1145\/3543507.3583251"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3306489"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00221"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02549"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.102077"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3293335"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3200671"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2021.naacl-main.77"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01336"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25397"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01060"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01524"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548028"},{"key":"ref45","article-title":"Learning deep representations by mutual information estimation and maximization","author":"Hjelm","year":"2019"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3221486"},{"key":"ref47","first-page":"990","article-title":"Probabilistic contrastive learning for domain adaptation","volume-title":"Proc. Int. Joint Conf. Artif. Intell","author":"Li","year":"2024"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3241539"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i8.26162"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i1.25093"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3252270"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.551"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475369"},{"key":"ref56","article-title":"Semantically self-aligned network for text-to-image part-aware person re-identification","author":"Ding","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3247939"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00119"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548057"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547753"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548166"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01026"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611832"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3344354"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i4.20370"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/11342315\/11408098.pdf?arnumber=11408098","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T21:37:42Z","timestamp":1782855462000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11408098\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":65,"URL":"https:\/\/doi.org\/10.1109\/tmm.2026.3664964","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}