{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T20:16:22Z","timestamp":1778271382921,"version":"3.51.4"},"reference-count":63,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T00:00:00Z","timestamp":1777593600000},"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":["62276155"],"award-info":[{"award-number":["62276155"]}],"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":["62576195"],"award-info":[{"award-number":["62576195"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,5]]},"DOI":"10.1109\/tcsvt.2025.3643601","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T18:37:50Z","timestamp":1765564670000},"page":"7155-7167","source":"Crossref","is-referenced-by-count":0,"title":["Redundancy Mitigation: Toward Accurate and Efficient Image\u2013Text Retrieval"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-4856-8806","authenticated-orcid":false,"given":"Kun","family":"Wang","sequence":"first","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5653-8286","authenticated-orcid":false,"given":"Yupeng","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-1026-4499","authenticated-orcid":false,"given":"Hao","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Software, Shandong University, Jinan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-6895-3558","authenticated-orcid":false,"given":"Lirong","family":"Jie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1476-0273","authenticated-orcid":false,"given":"Liqiang","family":"Nie","sequence":"additional","affiliation":[{"name":"School of Computer Science and Technology, Harbin Institute of Technology, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358411"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3558996"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3480949"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3527032"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01603"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3289882"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3485447.3512022"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/LSP.2022.3165426"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01093"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3539618.3591712"},{"key":"ref12","first-page":"1554","article-title":"Guided similarity separation for image retrieval","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Liu"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.348"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401086"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2021.3109433"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3559758"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1145\/3570725"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2023.3283984"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3374791"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3234037"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2025.3545643"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TKDE.2024.3396492"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP39728.2021.9414247"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICICIP53388.2021.9642180"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350934"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/2911451.2911493"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v31i1.11218"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2018.2793863"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2010.57"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2017.03.021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3404835.3462829"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2012.6248018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-017-1016-8"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2846566"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.105"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00796"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2018.2876833"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.389"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2007.4408891"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3369968"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01847"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01455"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1162"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref50","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref51","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.","author":"Li"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1162\/tacl_a_00166"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3182426"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/158"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3266887"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3443097"},{"issue":"86","key":"ref63","first-page":"2579","article-title":"Visualizing data using t-SNE","volume":"9","author":"Maaten","year":"2008","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11511351\/11299108.pdf?arnumber=11299108","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T19:42:35Z","timestamp":1778269355000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11299108\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5]]},"references-count":63,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3643601","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,5]]}}}