{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T16:20:39Z","timestamp":1782836439197,"version":"3.54.5"},"reference-count":43,"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:\/\/creativecommons.org\/licenses\/by\/4.0\/legalcode"}],"funder":[{"DOI":"10.13039\/501100001809","name":"Liaoning Provincial Natural Science Foundation of China","doi-asserted-by":"publisher","award":["2022-MS-168"],"award-info":[{"award-number":["2022-MS-168"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Ministry of Public Security Science and Technology Plan Project","award":["2022JSYJC26"],"award-info":[{"award-number":["2022JSYJC26"]}]},{"DOI":"10.13039\/501100012260","name":"Ministry of Public Security Soft Science Project","doi-asserted-by":"publisher","award":["2023LL43"],"award-info":[{"award-number":["2023LL43"]}],"id":[{"id":"10.13039\/501100012260","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/access.2024.3522585","type":"journal-article","created":{"date-parts":[[2024,12,25]],"date-time":"2024-12-25T19:34:01Z","timestamp":1735155241000},"page":"904-915","source":"Crossref","is-referenced-by-count":7,"title":["Enhanced CLIP-GPT Framework for Cross-Lingual Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"13","author":[{"given":"Rui","family":"Song","sequence":"first","affiliation":[{"name":"College of Public Security Information Technology and Intelligence, Criminal Investigation Police University of China, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Beigeng","family":"Zhao","sequence":"additional","affiliation":[{"name":"College of Public Security Information Technology and Intelligence, Criminal Investigation Police University of China, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lizhi","family":"Yu","sequence":"additional","affiliation":[{"name":"Yuhong Sub-Bureau, Shenyang Public Security Bureau, Shenyang, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1007\/s40010-017-0428-8"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.111402"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1145\/3617592"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2021.3128140"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1038\/nature14539"},{"key":"ref9","article-title":"Sequence to sequence learning with neural networks","author":"Sutskever","year":"2014","journal-title":"arXiv:1409.3215"},{"key":"ref10","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"issue":"8","key":"ref11","first-page":"9","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI blog"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref14","first-page":"65","article-title":"METEOR: An automatic metric for MT evaluation with improved correlation with human judgments","volume-title":"Proc. ACL Workshop Intrinsic Extrinsic Eval. Measures Mach. Transl. Summarization","author":"Banerjee"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2980933"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-02698-1_49"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3070383"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3009243"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS39084.2020.9323213"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.3390\/rs11202349"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN48605.2020.9207381"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060939"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-020-09294-7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR48806.2021.9412486"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109893"},{"key":"ref29","article-title":"ClipCap: CLIP prefix for image captioning","author":"Mokady","year":"2021","journal-title":"arXiv:2111.09734"},{"key":"ref30","article-title":"How much can CLIP benefit vision-and-language tasks?","author":"Shen","journal-title":"arXiv:2107.06383"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00512"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IJCNN60899.2024.10650602"},{"key":"ref33","article-title":"Revisiting image captioning training paradigm via direct CLIP-based optimization","author":"Moratelli","year":"2024","journal-title":"arXiv:2408.14547"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_7"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.3390\/rs16010196"},{"key":"ref36","volume-title":"A PyTorch Tutorial to Image Captioning","author":"Vinodababu","year":"2020"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1207\/s15516709cog1402_1"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3281336"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.123"},{"key":"ref43","volume-title":"Jieba: Chinese Text Segmentation","author":"Sun","year":"2012"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10816156.pdf?arnumber=10816156","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,3]],"date-time":"2025-01-03T05:25:47Z","timestamp":1735881947000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10816156\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":43,"URL":"https:\/\/doi.org\/10.1109\/access.2024.3522585","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}