{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,29]],"date-time":"2026-07-29T14:12:57Z","timestamp":1785334377639,"version":"3.55.0"},"reference-count":60,"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\/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"}]},{"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"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Multimedia"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tmm.2025.3535365","type":"journal-article","created":{"date-parts":[[2025,1,27]],"date-time":"2025-01-27T13:54:42Z","timestamp":1737986082000},"page":"3966-3978","source":"Crossref","is-referenced-by-count":29,"title":["Cross-Modal Progressive Perspective Matching Network for Remote Sensing Image-Text Retrieval"],"prefix":"10.1109","volume":"27","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5948-0032","authenticated-orcid":false,"given":"Chengyu","family":"Zheng","sequence":"first","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-8822-5280","authenticated-orcid":false,"given":"Xiu","family":"Li","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4406-536X","authenticated-orcid":false,"given":"Xinyue","family":"Liang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4087-3677","authenticated-orcid":false,"given":"Lei","family":"Huang","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2281-5150","authenticated-orcid":false,"given":"Shan","family":"Du","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Mathematics, Physics, and Statistics, University of British Columbia (Okanagan Campus), Kelowna, BC, Canada"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4952-7666","authenticated-orcid":false,"given":"Jie","family":"Nie","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7012-2087","authenticated-orcid":false,"given":"Junyu","family":"Dong","sequence":"additional","affiliation":[{"name":"College of Information Science and Engineering, Ocean University of China, Qingdao, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"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\/TMM.2023.3272169"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2023.3248160"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3286710"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref9","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref10","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","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref12","first-page":"5583","article-title":"Vilt: Vision-and-language transformer without convolution or region supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Kim","year":"2021"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3280546"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3369042"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612374"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"issue":"2","key":"ref17","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","volume-title":"Proc. naacL-HLT","volume":"1","author":"Devlin","year":"2019"},{"key":"ref18","article-title":"An image is worth 16 x 16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070872"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.3390\/s23208437"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3060705"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref24","article-title":"PP-YOLO: An effective and efficient implementation of object detector","author":"Long","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3464468"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3374111"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02243"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.3390\/rs12030405"},{"key":"ref29","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023"},{"key":"ref30","article-title":"RS5M: A large scale vision-language dataset for remote sensing vision-language foundation model","author":"Zhang","year":"2023"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3374381"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612427"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3219585"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3249230"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3226325"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548184"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3401031"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3063297"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3131592"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3340870"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3406897"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612101"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-60633-6_61"},{"key":"ref44","article-title":"Vse++: Improving visual-semantic embeddings with hard negatives","author":"Faghri","year":"2017"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00645"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_13"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00586"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3343031.3350875"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16209"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01521"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.103071"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3231851"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3318227"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3332317"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3392779"}],"container-title":["IEEE Transactions on Multimedia"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6046\/10844992\/10855517.pdf?arnumber=10855517","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,9]],"date-time":"2025-07-09T23:19:58Z","timestamp":1752103198000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10855517\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/tmm.2025.3535365","relation":{},"ISSN":["1520-9210","1941-0077"],"issn-type":[{"value":"1520-9210","type":"print"},{"value":"1941-0077","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}