{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,25]],"date-time":"2026-02-25T17:07:28Z","timestamp":1772039248159,"version":"3.50.1"},"reference-count":117,"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":[{"name":"National Key Research and Development Program of China","award":["2021YFB3900504"],"award-info":[{"award-number":["2021YFB3900504"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62302501"],"award-info":[{"award-number":["62302501"]}],"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":["62306302"],"award-info":[{"award-number":["62306302"]}],"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":["62301538"],"award-info":[{"award-number":["62301538"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key Laboratory of Target Cognition and Application Technology","award":["2023-CXPT-LC-005"],"award-info":[{"award-number":["2023-CXPT-LC-005"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2024.3510833","type":"journal-article","created":{"date-parts":[[2024,12,4]],"date-time":"2024-12-04T19:06:41Z","timestamp":1733339201000},"page":"1-20","source":"Crossref","is-referenced-by-count":14,"title":["RingMoGPT: A Unified Remote Sensing Foundation Model for Vision, Language, and Grounded Tasks"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0371-5584","authenticated-orcid":false,"given":"Peijin","family":"Wang","sequence":"first","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-4573-0428","authenticated-orcid":false,"given":"Huiyang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5100-5918","authenticated-orcid":false,"given":"Boyuan","family":"Tong","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5937-183X","authenticated-orcid":false,"given":"Ziqi","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Multimodal Artificial Intelligence Systems, Institute of Automation, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4187-9755","authenticated-orcid":false,"given":"Fanglong","family":"Yao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4017-8885","authenticated-orcid":false,"given":"Yingchao","family":"Feng","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0854-5382","authenticated-orcid":false,"given":"Zining","family":"Zhu","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7082-2526","authenticated-orcid":false,"given":"Hao","family":"Chang","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3931-3974","authenticated-orcid":false,"given":"Wenhui","family":"Diao","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1215-6259","authenticated-orcid":false,"given":"Qixiang","family":"Ye","sequence":"additional","affiliation":[{"name":"School of Electronic, Electrical and Communication Engineering, University of Chinese Academy of Sciences, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0038-9816","authenticated-orcid":false,"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Key Laboratory of Network Information System Technology (NIST), Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.11834\/jig.220049"},{"key":"ref3","article-title":"RSGPT: A remote sensing vision language model and benchmark","author":"Hu","year":"2023","journal-title":"arXiv:2307.15266"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2954328"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.12.015"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2959208"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201474"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01329"},{"key":"ref12","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"OpenAI","year":"2023"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01457"},{"key":"ref14","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv:2305.06500"},{"key":"ref15","article-title":"Improved baselines with visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2310.03744"},{"key":"ref16","article-title":"RemoteCLIP: A vision language foundation model for remote sensing","author":"Liu","year":"2023","journal-title":"arXiv:2306.11029"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref18","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref20","article-title":"MiniGPT-v2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023","journal-title":"arXiv:2310.09478"},{"key":"ref21","article-title":"Qwen-VL: A versatile vision-language model for understanding, localization, text reading, and beyond","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref22","article-title":"GeoChat: Grounded large vision-language model for remote sensing","author":"Kuckreja","year":"2023","journal-title":"arXiv:2311.15826"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.3390\/rs16091477"},{"key":"ref24","article-title":"SkyEyeGPT: Unifying remote sensing vision-language tasks via instruction tuning with large language model","author":"Zhan","year":"2024","journal-title":"arXiv:2401.09712"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3449154"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.3390\/s20061594"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2475299"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.3390\/rs13010108"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.004"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2864987"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/s20041226"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref36","article-title":"HRVQA: A visual question answering benchmark for high-resolution aerial images","author":"Li","year":"2023","journal-title":"arXiv:2301.09460"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3218921"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref39","first-page":"298","article-title":"Structural high-resolution satellite image indexing","volume-title":"Proc. ISPRS TC VII Symp. Years (ISPRS)","volume":"38","author":"Xia"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2014.10.002"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01855"},{"key":"ref43","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref44","article-title":"Graph attention networks","author":"Veli\u010dkovi\u0107","year":"2017","journal-title":"arXiv:1710.10903"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref46","volume-title":"Vicuna","year":"2023"},{"key":"ref47","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","author":"Li","year":"2023","journal-title":"arXiv:2301.12597"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1002\/nav.3800020109"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2951636"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00583"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3044054"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3105004"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3132095"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3102590"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102741"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2022.105076"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2783902"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2845668"},{"key":"ref63","first-page":"266","article-title":"Recurrent transformer network for remote sensing scene categorisation","volume-title":"Proc. BMVC","author":"Chen"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3390\/rs11050494"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2019.2920374"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2987060"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2983560"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3011405"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3114404"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3127851"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093914"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109061"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3092816"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106391"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3126770"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref79","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":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.10"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.285"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00644"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2988782"},{"key":"ref84","first-page":"20989","article-title":"Sparse and continuous attention mechanisms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Martins"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00208"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00181"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3173811"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00502"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2601622"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2778300"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2867198"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46448-0_2"},{"key":"ref95","article-title":"YOLOv3: An incremental improvement","author":"Redmon","year":"2018","journal-title":"arXiv:1804.02767"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.106"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_45"},{"key":"ref100","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3015049"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2975541"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3166956"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00511"},{"key":"ref104","first-page":"91","article-title":"Faster R-CNN: Towards real-time object detection with region proposal networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"28","author":"Ren"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00296"},{"key":"ref107","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref108","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3376384"},{"key":"ref109","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3424335"},{"key":"ref110","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2023.3328224"},{"key":"ref111","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3148210"},{"key":"ref112","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2020.2969330"},{"key":"ref113","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00472"},{"key":"ref114","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00198"},{"key":"ref115","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS52108.2023.10283451"},{"key":"ref116","article-title":"Pixel-level change detection pseudo-label learning for remote sensing change captioning","author":"Liu","year":"2023","journal-title":"arXiv:2312.15311"},{"key":"ref117","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10777289.pdf?arnumber=10777289","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,26]],"date-time":"2025-02-26T18:56:36Z","timestamp":1740596196000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10777289\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":117,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3510833","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}