{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:05:45Z","timestamp":1778947545403,"version":"3.51.4"},"reference-count":55,"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":["62271302"],"award-info":[{"award-number":["62271302"]}],"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":["62101316"],"award-info":[{"award-number":["62101316"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005089","name":"Shanghai Municipal Natural Science Foundation","doi-asserted-by":"publisher","award":["20ZR1423500"],"award-info":[{"award-number":["20ZR1423500"]}],"id":[{"id":"10.13039\/501100005089","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.2024.3489224","type":"journal-article","created":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T17:24:13Z","timestamp":1730481853000},"page":"1-18","source":"Crossref","is-referenced-by-count":11,"title":["Cross-Modal Prealigned Method With Global and Local Information for Remote Sensing Image and Text Retrieval"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-3417-8063","authenticated-orcid":false,"given":"Zengbao","family":"Sun","sequence":"first","affiliation":[{"name":"Department of Information Engineering, Shanghai Maritime University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Zhao","sequence":"additional","affiliation":[{"name":"Department of Information Engineering, Shanghai Maritime University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gaorui","family":"Liu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Infrared Perception, Shanghai Institute of Technical Physics, Chinese Academy of Sciences, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0929-5074","authenticated-orcid":false,"given":"Andr\u00e9","family":"Kaup","sequence":"additional","affiliation":[{"name":"Chair of Multimedia Communications and Signal Processing, Friedrich-Alexander University Erlangen-Nürnberg, Erlangen, Germany"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.future.2014.10.029"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/jproc.2016.2598228"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.04.014"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCCIS48478.2019.8974502"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3021052"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3201474"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3131592"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP49359.2023.10222159"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00963"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3333375"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3318227"},{"key":"ref17","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref19","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3340870"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3280546"},{"key":"ref23","first-page":"9694","article-title":"Align before fuse: Vision and language representation learning with momentum distillation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Li"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3255302"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3304847"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref27","first-page":"12633","article-title":"Global context vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hatamizadeh"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref29","first-page":"1","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Faghri"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/cits.2016.7546397"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00601"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.12176"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3383184"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01064"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2020.2967597"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00475"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148470"},{"key":"ref41","first-page":"1","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":"ref42","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1514"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401430"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01553"},{"key":"ref45","article-title":"Pixel-BERT: Aligning image pixels with text by deep multi-modal transformers","author":"Huang","year":"2020","journal-title":"arXiv:2004.00849"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00512"},{"key":"ref48","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":"ref49","first-page":"32897","article-title":"Vlmo: Unified vision-language pre-training with mixture-of-modality-experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bao"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3332317"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883252"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3308969"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3369042"},{"key":"ref54","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","volume-title":"North American Chapter of the Association for Computational Linguistics","author":"Devlin","year":"2019"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10354519\/10740340.pdf?arnumber=10740340","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,26]],"date-time":"2024-11-26T22:37:55Z","timestamp":1732660675000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10740340\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3489224","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}