{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,8]],"date-time":"2026-04-08T16:20:47Z","timestamp":1775665247088,"version":"3.50.1"},"reference-count":101,"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"}]},{"DOI":"10.13039\/501100001809","name":"General Program of the National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62371048"],"award-info":[{"award-number":["62371048"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tgrs.2024.3523505","type":"journal-article","created":{"date-parts":[[2024,12,30]],"date-time":"2024-12-30T19:28:27Z","timestamp":1735586907000},"page":"1-19","source":"Crossref","is-referenced-by-count":31,"title":["EarthMarker: A Visual Prompting Multimodal Large Language Model for Remote Sensing"],"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":"Advanced Research Institute of Multidisciplinary Sciences and the School of Mechatronical Engineering, Beijing Institute of Technology, Beijing, China"}]},{"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"}]},{"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"}]},{"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"}]},{"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"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8452-5773","authenticated-orcid":false,"given":"Xuerui","family":"Mao","sequence":"additional","affiliation":[{"name":"Beijing Institute of Technology, Zhuhai Beijing Institute of Technology (BIT), Zhuhai, China"}]}],"member":"263","reference":[{"key":"ref1","article-title":"ChatSpot: Bootstrapping multimodal LLMs via precise referring instruction tuning","author":"Zhao","year":"2023","journal-title":"arXiv:2307.09474"},{"key":"ref2","article-title":"Learning visual prompts for guiding the attention of vision transformers","author":"Rezaei","year":"2024","journal-title":"arXiv:2406.03303"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3488034"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2017.2762307"},{"key":"ref5","first-page":"1","article-title":"Position-enhanced visual instruction tuning for multimodal large language models","volume-title":"Proc. 62nd Annu. Meeting Assoc. Comput. Linguistics (ACL)","author":"Chen"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3449154"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.emnlp-main.346"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref12","article-title":"GPT4RoI: Instruction tuning large language model on region-of-interest","author":"Zhang","year":"2023","journal-title":"arXiv:2307.03601"},{"key":"ref13","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":"ref14","article-title":"Osprey: Pixel understanding with visual instruction tuning","author":"Yuan","year":"2023","journal-title":"arXiv:2312.10032"},{"key":"ref15","article-title":"Ferret: Refer and ground anything anywhere at any granularity","author":"You","year":"2023","journal-title":"arXiv:2310.07704"},{"key":"ref16","article-title":"Draw-and-understand: Leveraging visual prompts to enable MLLMs to comprehend what you want","author":"Lin","year":"2024","journal-title":"arXiv:2403.20271"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3250471"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103540"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2024.3385425"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3356074"},{"key":"ref22","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref23","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Brown"},{"key":"ref24","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref25","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"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":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Alayrac"},{"key":"ref29","article-title":"LLaMA-adapter v2: Parameter-efficient visual instruction model","author":"Gao","year":"2023","journal-title":"arXiv:2304.15010"},{"key":"ref30","article-title":"SPHINX: The joint mixing of weights, tasks, and visual embeddings for multi-modal large language models","author":"Lin","year":"2023","journal-title":"arXiv:2311.07575"},{"key":"ref31","first-page":"1","article-title":"VisionLLM: Large language model is also an open-ended decoder for vision-centric tasks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang"},{"key":"ref32","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":"ref33","article-title":"LHRS-bot: Empowering remote sensing with VGI-enhanced large multimodal language model","author":"Muhtar","year":"2024","journal-title":"arXiv:2402.02544"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01369"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_41"},{"key":"ref36","article-title":"Semantic-SAM: Segment and recognize anything at any granularity","author":"Li","year":"2023","journal-title":"arXiv:2307.04767"},{"key":"ref37","article-title":"CPT: Colorful prompt tuning for pre-trained vision-language models","author":"Yao","year":"2021","journal-title":"arXiv:2109.11797"},{"key":"ref38","article-title":"Kosmos-2: Grounding multimodal large language models to the world","author":"Peng","year":"2023","journal-title":"arXiv:2306.14824"},{"key":"ref39","article-title":"Shikra: Unleashing multimodal LLM\u2019s referential dialogue magic","author":"Chen","year":"2023","journal-title":"arXiv:2306.15195"},{"key":"ref40","first-page":"25005","article-title":"Visual prompting via image inpainting","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Bar"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01874"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3327123"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3368158"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28357"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3343806"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3348459"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46478-7_34"},{"key":"ref48","article-title":"PCAMs: Weakly supervised semantic segmentation using point supervision","author":"Austin McEver","year":"2020","journal-title":"arXiv:2007.05615"},{"key":"ref49","article-title":"Visual genome: Connecting language and vision using crowdsourced dense image annotations","author":"Krishna","year":"2016","journal-title":"arXiv:1602.07332"},{"key":"ref50","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":"ref51","article-title":"A unified theory of scene representation learning and object representation learning","author":"Komatsu","year":"2024"},{"key":"ref52","article-title":"SPHINX-X: Scaling data and parameters for a family of multi-modal large language models","author":"Liu","year":"2024","journal-title":"arXiv:2402.05935"},{"key":"ref53","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023","journal-title":"arXiv:2304.07193"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1016\/j.swevo.2024.101665"},{"key":"ref55","article-title":"Microsoft COCO captions: Data collection and evaluation server","author":"Chen","year":"2015","journal-title":"arXiv:1504.00325"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3115\/v1\/D14-1086"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46475-6_5"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3201474"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3078451"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2864987"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2645610"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2010.2055033"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3117983"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.12.004"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2601622"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2015.7351502"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2021.3119563"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.11834\/jrs.20222139"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3123666"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2017.2773199"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.5220\/0006120603240331"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2900302"},{"key":"ref75","volume-title":"Urban Modelling and Semantic Labelling Benchmark","year":"2021"},{"key":"ref76","article-title":"Hi-UCD: A large-scale dataset for urban semantic change detection in remote sensing imagery","author":"Tian","year":"2020","journal-title":"arXiv:2011.03247"},{"key":"ref77","first-page":"28","article-title":"iSAID: A large-scale dataset for instance segmentation in aerial images","volume-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. Workshops","author":"Zamir"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.05.009"},{"key":"ref79","first-page":"1","article-title":"SAMRS: Scaling-up remote sensing segmentation dataset with segment anything model","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Wang"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2858817"},{"key":"ref81","article-title":"Set-of-mark prompting unleashes extraordinary visual grounding in GPT-4V","author":"Yang","year":"2023","journal-title":"arXiv:2310.11441"},{"key":"ref82","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"},{"key":"ref83","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":"ref84","first-page":"74","article-title":"Rouge: A package for automatic evaluation of summaries","volume-title":"Proc. Text Summarization Branches Out","author":"Lin"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7299087"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_24"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00075"},{"key":"ref88","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref91","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":"ref92","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":"ref93","article-title":"Visual instruction tuning","author":"Liu","year":"2023","journal-title":"arXiv:2304.08485"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.3390\/rs11060612"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409637"},{"key":"ref98","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01227"},{"key":"ref99","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":"ref100","article-title":"GLaMM: Pixel grounding large multimodal model","author":"Rasheed","year":"2023","journal-title":"arXiv:2311.03356"},{"key":"ref101","article-title":"Collaborative secret and covert communications for multi-user multi-antenna uplink UAV systems: Design and optimization","author":"Xu","year":"2024","journal-title":"arXiv:2407.05738"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10817639.pdf?arnumber=10817639","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,20]],"date-time":"2025-01-20T18:50:35Z","timestamp":1737399035000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10817639\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":101,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2024.3523505","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}