{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T19:05:47Z","timestamp":1772737547964,"version":"3.50.1"},"reference-count":69,"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\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["2024124"],"award-info":[{"award-number":["2024124"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U24B20177"],"award-info":[{"award-number":["U24B20177"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Natural Science Foundation of Beijing Municipality","doi-asserted-by":"publisher","award":["L222041"],"award-info":[{"award-number":["L222041"]}],"id":[{"id":"10.13039\/501100004826","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.2025.3547988","type":"journal-article","created":{"date-parts":[[2025,3,4]],"date-time":"2025-03-04T18:48:09Z","timestamp":1741114089000},"page":"1-18","source":"Crossref","is-referenced-by-count":19,"title":["RS-MoE: A Vision\u2013Language Model With Mixture of Experts for Remote Sensing Image Captioning and Visual Question Answering"],"prefix":"10.1109","volume":"63","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0190-969X","authenticated-orcid":false,"given":"Hui","family":"Lin","sequence":"first","affiliation":[{"name":"China Academy of Electronics and Information Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3212-9584","authenticated-orcid":false,"given":"Danfeng","family":"Hong","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}]},{"given":"Shuhang","family":"Ge","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4848-609X","authenticated-orcid":false,"given":"Chuyao","family":"Luo","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Harbin Institute of Technology, Shenzhen, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2784-8397","authenticated-orcid":false,"given":"Kai","family":"Jiang","sequence":"additional","affiliation":[{"name":"China Academy of Electronics and Information Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-1932-9178","authenticated-orcid":false,"given":"Hao","family":"Jin","sequence":"additional","affiliation":[{"name":"China Academy of Electronics and Information Technology, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6448-003X","authenticated-orcid":false,"given":"Congcong","family":"Wen","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, New York University Abu Dhabi, Abu Dhabi, United Arab Emirates"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/tcsvt.2025.3528262"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3028468"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2677464"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10593-2_35"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.298"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2020.105920"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3070383"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2022.102741"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3224244"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.02.001"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.23919\/JSEE.2023.000035"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01653-1"},{"key":"ref14","article-title":"How secure are large language models (LLMs) for navigation in urban environments?","author":"Wen","year":"2024","journal-title":"arXiv:2402.09546"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-78456-9_25"},{"key":"ref16","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"},{"key":"ref17","article-title":"MiniGPT-4: Enhancing vision-language understanding with advanced large language models","author":"Zhu","year":"2023","journal-title":"arXiv:2304.10592"},{"key":"ref18","article-title":"InstructBLIP: Towards general-purpose vision-language models with instruction tuning","author":"Dai","year":"2023","journal-title":"arXiv:2305.06500"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2023.103497"},{"key":"ref20","article-title":"RSGPT: A remote sensing vision language model and benchmark","author":"Hu","year":"2023","journal-title":"arXiv:2307.15266"},{"key":"ref21","article-title":"GeoChat: Grounded large vision-language model for remote sensing","author":"Kuckreja","year":"2023","journal-title":"arXiv:2311.15826"},{"key":"ref22","article-title":"H2RSVLM: Towards helpful and honest remote sensing large vision language model","author":"Pang","year":"2024","journal-title":"arXiv:2403.20213"},{"key":"ref23","article-title":"EarthGPT: A universal multi-modal large language model for multi-sensor image comprehension in remote sensing domain","author":"Zhang","year":"2024","journal-title":"arXiv:2401.16822"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3362475"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.59717\/j.xinn-geo.2024.100055"},{"key":"ref26","article-title":"SeaMo: A multi-seasonal and multimodal remote sensing foundation model","author":"Li","year":"2024","journal-title":"arXiv:2412.19237"},{"key":"ref27","first-page":"1","article-title":"Visual instruction tuning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Liu"},{"key":"ref28","article-title":"Qwen2-VL: Enhancing vision-language model\u2019s perception of the world at any resolution","author":"Wang","year":"2024","journal-title":"arXiv:2409.12191"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3383473"},{"key":"ref30","article-title":"FedRSClip: Federated learning for remote sensing scene classification using vision-language models","author":"Lin","year":"2025","journal-title":"arXiv:2501.02461"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1162\/neco.1991.3.1.79"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1145\/3219819.3220007"},{"key":"ref33","article-title":"ST-MoE: Designing stable and transferable sparse expert models","author":"Zoph","year":"2022","journal-title":"arXiv:2202.08906"},{"key":"ref34","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. NIPS","volume":"34","author":"Riquelme"},{"key":"ref35","first-page":"9564","article-title":"Multimodal contrastive learning with LIMoE: The language-image mixture of experts","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Mustafa"},{"key":"ref36","article-title":"MoE-LLaVA: Mixture of experts for large vision-language models","author":"Lin","year":"2024","journal-title":"arXiv:2401.15947"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10641296"},{"key":"ref38","first-page":"478","article-title":"Mixture-of-experts for semantic segmentation of remoting sensing image","volume-title":"Proc. SPIE","volume":"13213","author":"He"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref40","article-title":"Qwen2 technical report","volume-title":"arXiv:2407.10671","author":"Yang","year":"2024"},{"key":"ref41","article-title":"LLaVA-NeXT-interleave: Tackling multi-image, video, and 3D in large multimodal models","author":"Li","year":"2024","journal-title":"arXiv:2407.07895"},{"key":"ref42","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref43","article-title":"Vicuna: An open-source chatbot impressing GPT-4 with 90% ChatGPT quality","author":"Chiang","year":"2023"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2776321"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CITS.2016.7546397"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/s11042-018-5856-1"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2019.2893772"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2951636"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045336"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3031111"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2019.2959208"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3105004"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3281334"},{"key":"ref54","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":"ref55","doi-asserted-by":"publisher","DOI":"10.3390\/rs16091477"},{"key":"ref56","article-title":"Large language models for captioning and retrieving remote sensing images","author":"Daniel Silva","year":"2024","journal-title":"arXiv:2402.06475"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3150957"},{"key":"ref58","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref59","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":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref61","article-title":"Mini-Gemini: Mining the potential of multi-modality vision language models","author":"Li","year":"2024","journal-title":"arXiv:2403.18814"},{"key":"ref62","article-title":"Stable LM 2 1.6B technical report","volume-title":"arXiv:2402.17834","author":"Bellagente","year":"2024"},{"key":"ref63","article-title":"Qwen technical report","volume-title":"arXiv:2309.16609","author":"Bai","year":"2023"},{"issue":"3","key":"ref64","first-page":"1","article-title":"Phi-2: The surprising power of small language models","volume":"1","author":"Javaheripi","year":"2023","journal-title":"Microsoft Research Blog"},{"key":"ref65","article-title":"LLaMA: Open and efficient foundation language models","author":"Touvron","year":"2023","journal-title":"arXiv:2302.13971"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3079918"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3173811"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3237606"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3413174"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/36\/10807682\/10909568.pdf?arnumber=10909568","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,3,24]],"date-time":"2025-03-24T18:23:30Z","timestamp":1742840610000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10909568\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2025.3547988","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}