{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,28]],"date-time":"2026-07-28T14:32:08Z","timestamp":1785249128023,"version":"3.55.0"},"reference-count":107,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["92152109"],"award-info":[{"award-number":["92152109"]}],"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":["T2225019"],"award-info":[{"award-number":["T2225019"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"General Program of the National Natural Science Foundation of China","award":["62371048"],"award-info":[{"award-number":["62371048"]}]},{"name":"Ministry of Education (MOE) Tier-2 Project of Singapore","award":["MOE-T2EP20123-0003"],"award-info":[{"award-number":["MOE-T2EP20123-0003"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2025.3626941","type":"journal-article","created":{"date-parts":[[2025,10,30]],"date-time":"2025-10-30T18:01:56Z","timestamp":1761847316000},"page":"1-21","source":"Crossref","is-referenced-by-count":2,"title":["EarthGPT-X: A Spatial MLLM for Multilevel Multisource Remote Sensing Imagery Understanding With Visual Prompting"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-7332-126X","authenticated-orcid":false,"given":"Wei","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Interdisciplinary Science, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-2584-5949","authenticated-orcid":false,"given":"Miaoxin","family":"Cai","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaqian","family":"Ning","sequence":"additional","affiliation":[{"name":"School of Optics and Photonics, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1769-9829","authenticated-orcid":false,"given":"Tong","family":"Zhang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0443-1081","authenticated-orcid":false,"given":"Yin","family":"Zhuang","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6766-2506","authenticated-orcid":false,"given":"Shijian","family":"Lu","sequence":"additional","affiliation":[{"name":"College of Computing and Data Science, Nanyang Technological University, Jurong West, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4182-6493","authenticated-orcid":false,"given":"He","family":"Chen","sequence":"additional","affiliation":[{"name":"National Key Laboratory of Science and Technology on Space-Born Intelligent Information Processing, Beijing Institute of Technology, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1613-9448","authenticated-orcid":false,"given":"Jun","family":"Li","sequence":"additional","affiliation":[{"name":"School of Computer Science and Hubei Key Laboratory of Intelligent Geo-Information Processing, China University of Geosciences, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xuerui","family":"Mao","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology (Zhuhai), Zhuhai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv:2310.07704"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref3","article-title":"Osprey: Pixel understanding with visual instruction tuning","author":"Yuan","year":"2023","journal-title":"arXiv:2312.10032"},{"key":"ref4","article-title":"GPT4RoI: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2023","journal-title":"arXiv:2307.03601"},{"key":"ref5","article-title":"RegionBLIP: A unified multi-modal pre-training framework for holistic and regional comprehension","author":"Zhou","year":"2023","journal-title":"arXiv:2308.02299"},{"key":"ref6","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00688"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_41"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","article-title":"Visual prompting in multimodal large language models: A survey","author":"Wu","year":"2024","journal-title":"arXiv:2409.15310"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3523505"},{"key":"ref15","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-91813-1_4"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.3390\/rs16091477"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3488034"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72904-1_26"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32683"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01334"},{"key":"ref23","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NIPS","author":"Brown"},{"key":"ref24","volume-title":"Chatgpt","year":"2023"},{"key":"ref25","article-title":"LLaMA-adapter: Efficient fine-tuning of language models with zero-init attention","author":"Zhang","year":"2023","journal-title":"arXiv:2303.16199"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01750"},{"key":"ref27","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":"ref28","first-page":"34892","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Liu"},{"key":"ref29","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref30","first-page":"32400","article-title":"SPHINX-x: Scaling data and parameters for a family of multi-modal large language models","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","volume":"235","author":"Liu"},{"key":"ref31","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref32","article-title":"LLaMA-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv:2304.15010"},{"key":"ref33","article-title":"MPLUG-owl: Modularization empowers large language models with multimodality","author":"Ye","year":"2023","journal-title":"arXiv:2304.14178"},{"key":"ref34","volume-title":"Qwen2.5-VL","year":"2025"},{"key":"ref35","article-title":"MiniCPM-V: A GPT-4V level MLLM on your phone","author":"Yao","year":"2024","journal-title":"arXiv:2408.01800"},{"key":"ref36","article-title":"Expanding performance boundaries of open-source multimodal models with model, data, and test-time scaling","author":"Chen","year":"2024","journal-title":"arXiv:2412.05271"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2025.findings-acl.340"},{"key":"ref38","article-title":"DeepSeek-VL2: Mixture-of-experts vision-language models for advanced multimodal understanding","author":"Wu","year":"2024","journal-title":"arXiv:2412.10302"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3574657"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2024.09.013"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3117857"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00331"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72855-6_14"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.03.028"},{"key":"ref45","article-title":"Instructblip: Towards general-purpose vision-language models with instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref46","article-title":"LLaVA-med: Training a large language-and-vision assistant for biomedicine in one day","author":"Li","year":"2023","journal-title":"arXiv:2306.00890"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2025.3560293"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2025.01.020"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.aiopen.2024.01.004"},{"key":"ref52","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref53","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":"ref54","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D18-2012"},{"key":"ref56","article-title":"Efficient estimation of word representations in vector space","author":"Mikolov","year":"2013","journal-title":"arXiv:1301.3781"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01326"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2015.2475299"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2918242"},{"key":"ref62","first-page":"8815","article-title":"SAMRS: Scaling-up remote sensing segmentation dataset with segment anything model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.12000\/JR19097"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183690"},{"key":"ref65","article-title":"SARDet-100K: Towards open-source benchmark and ToolKit for large-scale SAR object detection","author":"Li","year":"2024","journal-title":"arXiv:2403.06534"},{"issue":"4","key":"ref66","first-page":"906","article-title":"SAR-aircraft-1.0: High-resolution SAR aircraft detection and recognition dataset","volume":"12","author":"Zhirui","year":"2023","journal-title":"J. Radars"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.3390\/rs11070765"},{"key":"ref68","article-title":"Large-scale multi-class SAR image target detection dataset-1.0","volume-title":"J. Radars","volume":"14","author":"Chen","year":"2022"},{"key":"ref69","volume-title":"Sea-Shipping","year":"2021"},{"key":"ref70","volume-title":"Infrared-Security","year":"2021"},{"key":"ref71","volume-title":"Aerial-Mancar","year":"2021"},{"key":"ref72","volume-title":"Double-Light-Vehicle","year":"2021"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-020-01316-z"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-016-0981-7"},{"key":"ref75","article-title":"Gpt-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref76","article-title":"Draw-and-understand: Leveraging visual prompts to enable MLLMs to comprehend what you want","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Lin"},{"key":"ref77","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V","author":"Yang","year":"2023","journal-title":"arXiv:2310.11441"},{"key":"ref78","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref79","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3115\/1073083.1073135"},{"key":"ref81","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":"ref82","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches out","author":"Lin"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref88","article-title":"Qwen-VL: A frontier large vision-language model with versatile abilities","author":"Bai","year":"2023","journal-title":"arXiv:2308.12966"},{"key":"ref89","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":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73033-7_3"},{"key":"ref91","volume-title":"Internvl2: Better Than the Best\u2014Expanding Performance Boundaries of Open-Source Multimodal Models With the Progressive Scaling Strategy","year":"2024"},{"key":"ref92","article-title":"InternVL3: Exploring advanced training and test-time recipes for open-source multimodal models","author":"Zhu","year":"2025","journal-title":"arXiv:2504.10479"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201474"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883199"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-50069-5_10"},{"key":"ref98","article-title":"Large language models for captioning and retrieving remote sensing images","author":"Daniel Silva","year":"2024","journal-title":"arXiv:2402.06475"},{"key":"ref99","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01236"},{"key":"ref100","volume-title":"GPT-4o System Card","year":"2024"},{"key":"ref101","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3423663"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1038\/s41597-023-02066-6"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3327123"},{"key":"ref104","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409637"},{"key":"ref105","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3368158"},{"key":"ref106","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3168279"},{"key":"ref107","volume-title":"SAR Vehicle Detection Dataset","year":"2025"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/11222109.pdf?arnumber=11222109","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,5]],"date-time":"2025-12-05T06:16:46Z","timestamp":1764915406000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11222109\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":107,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3626941","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}