{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T00:52:08Z","timestamp":1784335928748,"version":"3.55.0"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"4","license":[{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,4,1]],"date-time":"2026-04-01T00:00:00Z","timestamp":1775001600000},"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":["62301538"],"award-info":[{"award-number":["62301538"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,4]]},"DOI":"10.1109\/tpami.2025.3643453","type":"journal-article","created":{"date-parts":[[2025,12,12]],"date-time":"2025-12-12T18:35:38Z","timestamp":1765564538000},"page":"4388-4405","source":"Crossref","is-referenced-by-count":11,"title":["RingMoE: Mixture-of-Modality-Experts Multi-Modal Foundation Models for Universal Remote Sensing Image Interpretation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-4209-5461","authenticated-orcid":false,"given":"Hanbo","family":"Bi","sequence":"first","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4017-8885","authenticated-orcid":false,"given":"Yingchao","family":"Feng","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Boyuan","family":"Tong","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-0644-260X","authenticated-orcid":false,"given":"Mengyu","family":"Wang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-8123-417X","authenticated-orcid":false,"given":"Haichen","family":"Yu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9256-3668","authenticated-orcid":false,"given":"Yongqiang","family":"Mao","sequence":"additional","affiliation":[{"name":"Department of Electronic Engineering, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hao","family":"Chang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3931-3974","authenticated-orcid":false,"given":"Wenhui","family":"Diao","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0371-5584","authenticated-orcid":false,"given":"Peijin","family":"Wang","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9865-2212","authenticated-orcid":false,"given":"Yue","family":"Yu","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hanyang","family":"Peng","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yehong","family":"Zhang","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory, Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8647-9627","authenticated-orcid":false,"given":"Kun","family":"Fu","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0038-9816","authenticated-orcid":false,"given":"Xian","family":"Sun","sequence":"additional","affiliation":[{"name":"Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-023-37136-1"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1038\/s41467-022-29543-7"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1038\/s41559-022-01702-5"},{"key":"ref4","article-title":"Ten thousand active satellites now orbiting Earth","year":"2024"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"ref6","article-title":"MiniGPT-V2: Large language model as a unified interface for vision-language multi-task learning","author":"Chen","year":"2023"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00943"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-06555-x"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1038\/s41586-023-05881-4"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1038\/s42256-023-00667-9"},{"key":"ref12","article-title":"A unified view of masked image modeling","author":"Peng","year":"2022"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.5555\/3524938.3525087"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00304"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2024.3401772"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3362475"},{"key":"ref19","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Cong","year":"2022"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3531988"},{"key":"ref21","article-title":"DiffusionSAT: A generative foundation model for satellite imagery","author":"Khanna","year":"2023"},{"key":"ref22","article-title":"Multimodal contrastive learning for remote sensing tasks","author":"Jain","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS46834.2022.9883983"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2024.3493237"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0241"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02613"},{"key":"ref27","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref28","article-title":"Self-supervised pretraining of visual features in the wild","author":"Goyal","year":"2021"},{"key":"ref29","first-page":"4904","article-title":"Scaling up visual and vision-language representation learning with noisy text supervision","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Jia","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref31","first-page":"7480","article-title":"Scaling vision transformers to 22 billion parameters","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Dehghani","year":"2023"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref33","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. 35th Int. Conf. Neural Inf. Process. Syst.","volume":"34","author":"Riquelme"},{"key":"ref34","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref35","first-page":"19730","article-title":"BLIP-2: Bootstrapping language-image pre-training with frozen image encoders and large language models","volume-title":"Proc. 40th Int. Conf. Mach. Learn.","author":"Li","year":"2023"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3390838"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3109345"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2015.2462751"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/MGRS.2024.3404506"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.05.008"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3177323"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3267185"},{"key":"ref44","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","volume":"33","author":"Brown","year":"2020"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2024.acl-long.70"},{"key":"ref46","article-title":"Scaling efficient masked autoencoder learning on large remote sensing dataset","author":"Wang","year":"2024"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01138"},{"issue":"120","key":"ref48","first-page":"5232","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","volume":"23","author":"Fedus","year":"2022","journal-title":"J. Mach. Learn. Res."},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2005.852084"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01002"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS53475.2024.10641637"},{"key":"ref53","first-page":"7103","article-title":"Mixture-of-experts with expert choice routing","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Zhou"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.278"},{"key":"ref55","first-page":"28441","article-title":"M $^{3}$3 ViT: Mixture-of-experts vision transformer for efficient multi-task learning with model-accelerator co-design","volume-title":"Proc. 36th Int. Conf. Neural Inf. Process. Syst.","volume":"35","author":"Fan"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00131"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01886-8"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2011.608740"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref61","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","year":"2019"},{"key":"ref62","article-title":"Loveda: A remote sensing land-cover dataset for domain adaptive semantic segmentation","author":"Wang","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02224"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3268232"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00509"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01538"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01541"},{"key":"ref70","first-page":"8815","article-title":"SAMRS: Scaling-up remote sensing segmentation dataset with segment anything model","volume":"36","author":"Wang","year":"2023","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref71","article-title":"2D semantic labeling contest","volume-title":"ISPRS","year":"2025"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02048"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3130174"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2022.3170326"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2021.102638"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00147"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2024.3401772"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.5220\/0006120603240331"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2020.3005861"},{"issue":"4","key":"ref81","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":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3152250"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3401573"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.3390\/rs12101662"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLII-2-565-2018"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02484"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.02629"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3409624"},{"key":"ref89","first-page":"128430","article-title":"SARdet-100k: Towards open-source benchmark and toolkit for large-scale SAR object detection","volume-title":"Proc. 38th Int. Conf. Neural Inf. Process. Syst.","volume":"37","author":"Li","year":"2024"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.3233\/faia240489"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11424231\/11298536.pdf?arnumber=11298536","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T01:34:38Z","timestamp":1773106478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11298536\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,4]]},"references-count":90,"journal-issue":{"issue":"4"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3643453","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,4]]}}}