{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,23]],"date-time":"2026-08-23T14:44:07Z","timestamp":1787496247540,"version":"build-2736575974"},"reference-count":64,"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":["62271377"],"award-info":[{"award-number":["62271377"]}],"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":["62201407"],"award-info":[{"award-number":["62201407"]}],"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":["62171347"],"award-info":[{"award-number":["62171347"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0110400"],"award-info":[{"award-number":["2021ZD0110400"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2021ZD0110404"],"award-info":[{"award-number":["2021ZD0110404"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Research and Development Program of Shannxi","award":["2021ZDLGY01-06"],"award-info":[{"award-number":["2021ZDLGY01-06"]}]},{"name":"Key Research and Development Program of Shannxi","award":["2022ZDLGY01-12"],"award-info":[{"award-number":["2022ZDLGY01-12"]}]},{"name":"Key Research and Development Program of Shannxi","award":["2023YBGY244"],"award-info":[{"award-number":["2023YBGY244"]}]},{"name":"Key Research and Development Program of Shannxi","award":["2023QCYLL28"],"award-info":[{"award-number":["2023QCYLL28"]}]},{"name":"Key Research and Development Program of Shannxi","award":["2024GX-ZDCYL-02-08"],"award-info":[{"award-number":["2024GX-ZDCYL-02-08"]}]},{"name":"Key Research and Development Program of Shannxi","award":["2024GXZDCYL-02-17"],"award-info":[{"award-number":["2024GXZDCYL-02-17"]}]},{"DOI":"10.13039\/501100002858","name":"China Postdoctoral Science Foundation","doi-asserted-by":"publisher","award":["2022M722496"],"award-info":[{"award-number":["2022M722496"]}],"id":[{"id":"10.13039\/501100002858","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/tgrs.2024.3496898","type":"journal-article","created":{"date-parts":[[2024,11,19]],"date-time":"2024-11-19T13:41:29Z","timestamp":1732023689000},"page":"1-17","source":"Crossref","is-referenced-by-count":24,"title":["Transcending Fusion: A Multiscale Alignment Method for Remote Sensing Image\u2013Text Retrieval"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3209-0456","authenticated-orcid":false,"given":"Rui","family":"Yang","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence and the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4940-1211","authenticated-orcid":false,"given":"Shuang","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yingping","family":"Han","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuanheng","family":"Li","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9880-8822","authenticated-orcid":false,"given":"Dong","family":"Zhao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6943-4657","authenticated-orcid":false,"given":"Dou","family":"Quan","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanhe","family":"Guo","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence and the Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education, Xidian University, Xi’an, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhi","family":"Yang","sequence":"additional","affiliation":[{"name":"DFH satellite Co., Ltd., CAST, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00803"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2023.3291876"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3194076"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3280546"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3318227"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3308969"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612374"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592236"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298932"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01267"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00831"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612207"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110273"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref23","first-page":"13","article-title":"VilBERT: Pretraining task-agnostic visiolinguistic representations for vision-and-language tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Lu"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref25","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020","journal-title":"arXiv:2004.00849"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref27","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":"ref28","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1907.11692"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3215803"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3231851"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2906387"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.01.025"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194505"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3255211"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3256064"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3292112"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3208107"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3243247"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.3042276"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3214889"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2023.3304411"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.3390\/s23208437"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3340870"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref49","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10590-1_53"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref53","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017","journal-title":"arXiv:1707.05612"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413961"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.103071"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/app122312221"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3226325"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3603628"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3333375"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3369042"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3332317"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref64","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10354519\/10758255.pdf?arnumber=10758255","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,29]],"date-time":"2024-11-29T13:52:58Z","timestamp":1732888378000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10758255\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":64,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3496898","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}