{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,12]],"date-time":"2026-06-12T16:58:30Z","timestamp":1781283510596,"version":"3.54.1"},"reference-count":66,"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\/501100002367","name":"Key Deployment Program of the Chinese Academy of Sciences","doi-asserted-by":"publisher","award":["KGFZD-145-23-18"],"award-info":[{"award-number":["KGFZD-145-23-18"]}],"id":[{"id":"10.13039\/501100002367","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.2025.3572827","type":"journal-article","created":{"date-parts":[[2025,5,22]],"date-time":"2025-05-22T17:59:49Z","timestamp":1747936789000},"page":"1-15","source":"Crossref","is-referenced-by-count":3,"title":["Language-Empowered Conversion for Remote Sensing Image Retrieval With Text Feedback"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5180-7451","authenticated-orcid":false,"given":"Jian","family":"Yang","sequence":"first","affiliation":[{"name":"Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9888-9869","authenticated-orcid":false,"given":"Shengyang","family":"Li","sequence":"additional","affiliation":[{"name":"Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2493-2166","authenticated-orcid":false,"given":"Yuhan","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0924-5138","authenticated-orcid":false,"given":"Han","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6544-4858","authenticated-orcid":false,"given":"Zhuang","family":"Zhou","sequence":"additional","affiliation":[{"name":"Key Laboratory of Space Utilization, Technology and Engineering Center for Space Utilization, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3159528"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3368630"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2024.103740"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3158703"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00660"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00118"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02080"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00086"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00107"},{"key":"ref10","article-title":"Composed image retrieval with text feedback via multi-grained uncertainty regularization","author":"Chen","year":"2022","journal-title":"arXiv:2211.07394"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3404605"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-93417-4_38"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110537"},{"key":"ref14","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":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3308969"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00311"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103497"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3163706"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124252"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1179"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28393"},{"key":"ref26","article-title":"Remote sensing vision-language foundation models without annotations via ground remote alignment","author":"Mall","year":"2023","journal-title":"arXiv:2312.06960"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s40998-019-00237-z"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.652"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00804"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01115"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref33","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i3.28004"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611817"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3467259"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3326293"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110802"},{"key":"ref39","article-title":"CompoDiff: Versatile composed image retrieval with latent diffusion","author":"Gu","year":"2023","journal-title":"arXiv:2303.11916"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.2307\/j.ctv1tjrvk1.47"},{"key":"ref41","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref42","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref43","article-title":"Qwen2.5 technical report","volume-title":"arXiv:2412.15115","author":"Yang","year":"2024"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3616855.3635752"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2023.emnlp-main.574"},{"key":"ref46","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":"ref47","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Li"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.01.004"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3626772.3657740"},{"key":"ref50","article-title":"Vision-by-Language for training-free compositional image retrieval","author":"Karthik","year":"2023","journal-title":"arXiv:2310.09291"},{"key":"ref51","article-title":"Training-free zero-shot composed image retrieval with local concept reranking","author":"Sun","year":"2023","journal-title":"arXiv:2312.08924"},{"key":"ref52","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2012.05.002"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.004"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.3390\/rs10060964"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00276"},{"key":"ref59","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00166"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref62","article-title":"The falcon 3 family of open models","author":"Team","year":"2024"},{"key":"ref63","article-title":"DeepSeek-V3 technical report","volume-title":"arXiv:2412.19437","author":"Liu","year":"2024"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3558246"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.3390\/rs16091477"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11010086.pdf?arnumber=11010086","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,2]],"date-time":"2025-06-02T18:00:34Z","timestamp":1748887234000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11010086\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":66,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3572827","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}