{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T20:17:43Z","timestamp":1779135463635,"version":"3.51.4"},"reference-count":64,"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":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62571381"],"award-info":[{"award-number":["62571381"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development and Achievement Transformation Program of Inner Mongolia Autonomous Region","award":["2025YFHH0078"],"award-info":[{"award-number":["2025YFHH0078"]}]},{"name":"Sanya Science and Technology Special Fund","award":["2024KJFX034"],"award-info":[{"award-number":["2024KJFX034"]}]},{"name":"Hainan Province \u201cNanhai New Star\u201d Technology Innovation Talent Platform Project","award":["NHXXRCXM202361"],"award-info":[{"award-number":["NHXXRCXM202361"]}]},{"name":"General Program of Hubei Natural Science Foundation","award":["2025AFB615"],"award-info":[{"award-number":["2025AFB615"]}]},{"name":"Project of Sanya Yazhou Bay Science and Technology City","award":["SKJC-JYRC-2024-63"],"award-info":[{"award-number":["SKJC-JYRC-2024-63"]}]},{"name":"Project of Sanya Science and Education Innovation Park of Wuhan University of Technology","award":["2025ZCX005"],"award-info":[{"award-number":["2025ZCX005"]}]},{"name":"MindSpore, which is a New Deep Learning Computing Framework"},{"name":"Special Fund for Promoting High-Quality Development of Marine and Fishery Industries in Fujian Province","award":["FJHYF-L-2025-07-005"],"award-info":[{"award-number":["FJHYF-L-2025-07-005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3690309","type":"journal-article","created":{"date-parts":[[2026,5,11]],"date-time":"2026-05-11T19:49:27Z","timestamp":1778528967000},"page":"5017-5031","source":"Crossref","is-referenced-by-count":0,"title":["ReCoTR: Reducing Semantic Cognitive Shift via Dual-Consensus Token Compression for Remote Sensing Image-Text Retrieval"],"prefix":"10.1109","volume":"35","author":[{"given":"Jirui","family":"Huang","sequence":"first","affiliation":[{"name":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2903-6723","authenticated-orcid":false,"given":"Yaxiong","family":"Chen","sequence":"additional","affiliation":[{"name":"Hubei Key Laboratory of Transportation Internet of Things, Wuhan University of Technology, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-4047-6900","authenticated-orcid":false,"given":"Chuang","family":"Du","sequence":"additional","affiliation":[{"name":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4006-7029","authenticated-orcid":false,"given":"Shengwu","family":"Xiong","sequence":"additional","affiliation":[{"name":"Interdisciplinary Artificial Intelligence Research Institute, Wuhan College, Wuhan, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7037-5188","authenticated-orcid":false,"given":"Xiaoqiang","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Physics and Information Engineering, Fuzhou University, Fuzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/rs12071130"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.2747\/1548-1603.43.1.39"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2019.2910667"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.landurbplan.2020.103921"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3267890"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2013.06.011"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10888503"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.findings-acl.684"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01332"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00288"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3522293"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref13","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jia"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3131592"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3078451"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3269300"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3333375"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3215803"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9746251"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3464468"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248160"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592236"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3390838"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3449154"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3316166"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.020"},{"key":"ref34","first-page":"5583","article-title":"ViLT: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim"},{"key":"ref35","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"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"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2025.3552304"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681270"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3395313"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3318227"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3163706"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2025.3596333"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3407138"},{"key":"ref44","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017","journal-title":"arXiv:1707.05612"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.103071"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3332317"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3340870"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3466389"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3392779"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3496898"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3369042"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3509639"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2025.128454"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2025.3597055"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2025.3610428"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2025.3578962"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3374381"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3402216"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11515006.pdf?arnumber=11515006","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,18]],"date-time":"2026-05-18T19:48:54Z","timestamp":1779133734000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11515006\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3690309","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}