{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,16]],"date-time":"2026-05-16T16:12:44Z","timestamp":1778947964830,"version":"3.51.4"},"reference-count":16,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024JX070"],"award-info":[{"award-number":["2024JX070"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100012226","name":"Fundamental Research Funds for the Central Universities","doi-asserted-by":"publisher","award":["2024TD001"],"award-info":[{"award-number":["2024TD001"]}],"id":[{"id":"10.13039\/501100012226","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Geosci. Remote Sensing Lett."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/lgrs.2024.3494543","type":"journal-article","created":{"date-parts":[[2024,11,8]],"date-time":"2024-11-08T13:48:05Z","timestamp":1731073685000},"page":"1-5","source":"Crossref","is-referenced-by-count":6,"title":["Toward Efficient and Accurate Remote Sensing Image\u2013Text Retrieval With a Coarse-to-Fine Approach"],"prefix":"10.1109","volume":"22","author":[{"given":"Wenqian","family":"Zhou","sequence":"first","affiliation":[{"name":"School of Information Science and Technology, Beijing Foreign Studies University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3505-0521","authenticated-orcid":false,"given":"Hanlin","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing Foreign Studies University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Pei","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Information Science and Technology, Beijing Foreign Studies University, Beijing, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","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":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3308969"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3369042"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612374"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3333375"},{"key":"ref7","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3280546"},{"key":"ref9","first-page":"1","article-title":"SimVLM: Simple visual language model pretraining with weak supervision","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_7"},{"key":"ref11","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref12","article-title":"Deep unsupervised contrastive hashing for large-scale cross-modal text-image retrieval in remote sensing","author":"Mikriukov","year":"2022","journal-title":"arXiv:2201.08125"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883252"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"}],"container-title":["IEEE Geoscience and Remote Sensing Letters"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/8859\/10764750\/10747393.pdf?arnumber=10747393","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T19:03:22Z","timestamp":1766171002000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10747393\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":16,"URL":"https:\/\/doi.org\/10.1109\/lgrs.2024.3494543","relation":{},"ISSN":["1545-598X","1558-0571"],"issn-type":[{"value":"1545-598X","type":"print"},{"value":"1558-0571","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}