{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,15]],"date-time":"2026-06-15T12:07:14Z","timestamp":1781525234110,"version":"3.54.1"},"reference-count":73,"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":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62376283"],"award-info":[{"award-number":["62376283"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62531026"],"award-info":[{"award-number":["62531026"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"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.2025.3603036","type":"journal-article","created":{"date-parts":[[2025,8,27]],"date-time":"2025-08-27T18:31:14Z","timestamp":1756319474000},"page":"24011-24026","source":"Crossref","is-referenced-by-count":3,"title":["Multimodal Large Models Driven SAR Image Captioning: A Benchmark Dataset and Baselines"],"prefix":"10.1109","volume":"18","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-9262-8332","authenticated-orcid":false,"given":"Ziyi","family":"Gao","sequence":"first","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8453-3346","authenticated-orcid":false,"given":"Shuzhou","family":"Sun","sequence":"additional","affiliation":[{"name":"Department of Computer Science and Technology, Institute for AI, BNRist Center, THBI Lab, Tsinghua-Bosch Joint Center for ML, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-8758","authenticated-orcid":false,"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"TKLNDST, College of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yongxiang","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2011-2873","authenticated-orcid":false,"given":"Li","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Electronic Science and Technology, National University of Defense Technology (NUDT), Changsha, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.3390\/rs16020431"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.3390\/rs16183419"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3353868"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.compag.2024.109340"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2024.3386020"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3502055"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.04.011"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3236987"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.11.010"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/app14073025"},{"key":"ref11","first-page":"128430","article-title":"SARDet-100K: Towards open-source benchmark and toolkit for large-scale sar object detection","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"37","author":"Li","year":"2024"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3574657"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2023.3280442"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2023.12.004"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3531988"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3537283"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3568644"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3285009"},{"key":"ref19","first-page":"220","article-title":"Composing simple image descriptions using web-scale n-grams","volume-title":"Proc. 15th Conf. Comput. Natural Lang. Learn.","author":"Li","year":"2011"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-642-34500-5_24"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2012.162"},{"key":"ref22","first-page":"359","article-title":"Collective generation of natural image descriptions","volume-title":"Proc. 50th Annu. Meeting Assoc. Comput. Linguistics (Volume 1: Long Papers)","author":"Kuznetsova","year":"2012"},{"key":"ref23","first-page":"1","article-title":"Sequence to sequence learning with neural networks","volume":"27","author":"Sutskever","year":"2014","journal-title":"Adv. Neural Inf. Process. syst."},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0840-y"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00636"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01059"},{"key":"ref27","article-title":"Clipcap: Clip prefix for image captioning","author":"Mokady","year":"2021"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2015.303"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2022.3202193"},{"key":"ref31","article-title":"SARLANG-1 M: A Benchmark for Vision-Language Modeling in SAR Image Understanding","author":"Wei","year":"2025"},{"key":"ref32","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume":"35","author":"Alayrac","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref33","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":"ref34","article-title":"The dawn of LMMS: Preliminary explorations with GPT-4V (ISION)","author":"Yang","year":"2023"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.191"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1038\/s41598-023-31223-5"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1080\/10095020.2022.2085633"},{"key":"ref38","article-title":"LowCLIP: Adapting the CLIP model architecture for low-resource languages in multimodal image retrieval task","author":"Asgarov","year":"2024"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298935"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2024.3383276"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.31577\/cai_2025_1_92"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1997.9.8.1735"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/icassp49660.2025.10888271"},{"key":"ref50","first-page":"3229","article-title":"Vrsbench: A versatile vision-language benchmark dataset for remote sensing image understanding","volume-title":"Proc. Adv. Neural Inform. Process. Syst.","volume":"37","author":"Li","year":"2024"},{"key":"ref51","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":"ref52","first-page":"12888","article-title":"BLIP: Bootstrapping language-image pre-training for unified vision-language understanding and generation","volume-title":"Proc. 39th Int. Conf. Mach. Learn., Ser. Proc. Mach. Learn. Res.","author":"Li","year":"2022"},{"key":"ref53","article-title":"Gpt-4o system card","author":"Hurst","year":"2024"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3409563"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref56","article-title":"Can GPT-4V (ISION) serve medical applications? case studies on GPT-4V for multimodal medical diagnosis","author":"Wu","year":"2023"},{"key":"ref57","article-title":"MM-VID: Advancing video understanding with GPT-4V (ISION)","author":"Lin","year":"2023"},{"key":"ref58","article-title":"Multimodal chatgpt for medical applications: An experimental study of GPT-4V","author":"Yan","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2024.3477090"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.3390\/ijgi13040127"},{"key":"ref61","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref62","article-title":"Very deep convolutional networks for large-scale image recognition","author":"Simonyan","year":"2014"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref64","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. and\/or Summarization","author":"Banerjee","year":"2005"},{"key":"ref65","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":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3401576"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3385500"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2025.3548664"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref73","article-title":"Describe anything: Detailed localized image and video captioning","author":"Lian","year":"2025"}],"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\/11142698.pdf?arnumber=11142698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,30]],"date-time":"2025-09-30T12:17:21Z","timestamp":1759234641000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11142698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/jstars.2025.3603036","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}