{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,26]],"date-time":"2026-03-26T15:38:22Z","timestamp":1774539502575,"version":"3.50.1"},"reference-count":56,"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":[{"name":"Research on Key Technologies of Knowledge Evolution Representation and Collaborative Inference for Complex Problems in Ocean Big Data","award":["U23A20320"],"award-info":[{"award-number":["U23A20320"]}]},{"name":"Regional Innovation and Development Joint Fund of the National Natural Science Foundation of China","award":["U22A2068"],"award-info":[{"award-number":["U22A2068"]}]},{"name":"Central Government Guides Local Science and Technology Development Fund","award":["YDZX2022028"],"award-info":[{"award-number":["YDZX2022028"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62172376"],"award-info":[{"award-number":["62172376"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3561626","type":"journal-article","created":{"date-parts":[[2025,4,16]],"date-time":"2025-04-16T17:50:53Z","timestamp":1744825853000},"page":"1-13","source":"Crossref","is-referenced-by-count":3,"title":["Frequency- and Spatial-Domain Saliency Network for Remote Sensing Cross-Modal Retrieval"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5948-0032","authenticated-orcid":false,"given":"Chengyu","family":"Zheng","sequence":"first","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4952-7666","authenticated-orcid":false,"given":"Jie","family":"Nie","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6318-0174","authenticated-orcid":false,"given":"Bo","family":"Yin","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8822-5280","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7418-5891","authenticated-orcid":false,"given":"Yuntao","family":"Qian","sequence":"additional","affiliation":[{"name":"College of Computer Science, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2830-8301","authenticated-orcid":false,"given":"Zhiqiang","family":"Wei","sequence":"additional","affiliation":[{"name":"Faculty of Information Science and Engineering, Ocean University of China, Qingdao, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2021.3080121"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2845549"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3202246"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3013818"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3021390"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2019.8900431"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref8","article-title":"Empirical evaluation of gated recurrent neural networks on sequence modeling","author":"Chung","year":"2014","journal-title":"arXiv:1412.3555"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref10","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":"ref11","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3390838"},{"key":"ref13","article-title":"RS5M and GeoRSCLIP: A large scale vision-language dataset and a large vision-language model for remote sensing","author":"Zhang","year":"2023","journal-title":"arXiv:2306.11300"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3308969"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3249230"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3219585"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-97-7244-5_9"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1145\/3591106.3592236"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JAS.2022.105773"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3333375"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3163706"},{"key":"ref22","article-title":"PP-YOLO: An effective and efficient implementation of object detector","author":"Long","year":"2020","journal-title":"arXiv:2007.12099"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3332317"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612374"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s23208437"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3280546"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3131592"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/M2GARSS47143.2020.9105191"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3402216"},{"key":"ref37","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":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3374381"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3226325"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3392779"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3406897"},{"key":"ref42","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":"ref43","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref44","article-title":"Factorized Fourier neural operators","author":"Tran","year":"2023","journal-title":"arXiv:2111.13802"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref46","article-title":"VSE++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017","journal-title":"arXiv:1707.05612"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.103071"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3231851"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3318227"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3401031"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3207171"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10966929.pdf?arnumber=10966929","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,5,9]],"date-time":"2025-05-09T04:21:33Z","timestamp":1746764493000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10966929\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":56,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3561626","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}