{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,24]],"date-time":"2026-03-24T15:26:22Z","timestamp":1774365982542,"version":"3.50.1"},"reference-count":55,"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":[{"name":"National Key Research and Development Program of China","award":["2021ZD0110400"],"award-info":[{"award-number":["2021ZD0110400"]}]},{"name":"National Key Research and Development Program of China","award":["2021ZD0110404"],"award-info":[{"award-number":["2021ZD0110404"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62271377"],"award-info":[{"award-number":["62271377"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62201407"],"award-info":[{"award-number":["62201407"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["62171347"],"award-info":[{"award-number":["62171347"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/jstars.2024.3510414","type":"journal-article","created":{"date-parts":[[2024,12,18]],"date-time":"2024-12-18T19:35:42Z","timestamp":1734550542000},"page":"2631-2642","source":"Crossref","is-referenced-by-count":13,"title":["CLIP-Based Grid Features and Masking for Remote Sensing Image Captioning"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-1642-5114","authenticated-orcid":false,"given":"Qiaoling","family":"Lin","sequence":"first","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4940-1211","authenticated-orcid":false,"given":"Shuang","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"}]},{"given":"Xiutiao","family":"Ye","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"}]},{"given":"Ruixuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3209-0456","authenticated-orcid":false,"given":"Rui","family":"Yang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3354-9617","authenticated-orcid":false,"given":"Licheng","family":"Jiao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Intelligent Perception and Image Understanding of Ministry of Education of China, Xidian University, Xi'an, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3295748"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224244"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3192062"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.11.020"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/rs11202349"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/rs12060939"},{"key":"ref11","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TCYB.2022.3222606"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3135711"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref17","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":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01028"},{"key":"ref19","article-title":"Bert: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2959208"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2980933"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/rs14122939"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3218921"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3425815"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7005"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58577-8_8"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr46437.2021.00553"},{"key":"ref31","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10281578"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3612207"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3479207"},{"key":"ref35","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref36","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":"ref37","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","year":"2023"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2014.2357078"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28357"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref43","first-page":"311","article-title":"BLEU: A method for automatic evaluation of machine translation","volume-title":"Proc. 40th Annu. meeting Assoc. Comput. Linguistics","author":"Papineni","year":"2002"},{"key":"ref44","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","year":"2005"},{"key":"ref45","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin","year":"2004"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref48","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref50","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"issue":"8","key":"ref51","article-title":"Language models are unsupervised multitask learners","volume":"1","author":"Radford","year":"2019","journal-title":"OpenAI Blog"},{"key":"ref52","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref53","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023"},{"issue":"3","key":"ref54","article-title":"Vicuna: An open-source chatbot impressing gpt-4 with 90 chatgpt quality","volume":"2","author":"Chiang","year":"2023"},{"issue":"70","key":"ref55","first-page":"1","article-title":"Scaling instruction-finetuned language models","volume":"25","author":"Chung","year":"2024","journal-title":"J. Mach. Learn. Res."}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/4609443\/10766875\/10806569.pdf?arnumber=10806569","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,2]],"date-time":"2025-01-02T05:47:26Z","timestamp":1735796846000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10806569\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/jstars.2024.3510414","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}