{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,11]],"date-time":"2026-03-11T15:32:54Z","timestamp":1773243174223,"version":"3.50.1"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":["42201472"],"award-info":[{"award-number":["42201472"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Comprehensive Research Project"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Aerosp. Electron. Syst."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/taes.2025.3649185","type":"journal-article","created":{"date-parts":[[2025,12,29]],"date-time":"2025-12-29T18:40:09Z","timestamp":1767033609000},"page":"3736-3757","source":"Crossref","is-referenced-by-count":0,"title":["Foundation Model-Based Auxiliary Framework for Object Detection in Aerial Remote Sensing Images"],"prefix":"10.1109","volume":"62","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-7210-7670","authenticated-orcid":false,"given":"Wanjie","family":"Lu","sequence":"first","affiliation":[{"name":"Institute of Data and Target Engineering, Information Engineering University, Zhengzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5144-8815","authenticated-orcid":false,"given":"Chaoyang","family":"Niu","sequence":"additional","affiliation":[{"name":"Institute of Data and Target Engineering, Information Engineering University, Zhengzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3395-6696","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Institute of Data and Target Engineering, Information Engineering University, Zhengzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6860-3882","authenticated-orcid":false,"given":"Chaozhen","family":"Lan","sequence":"additional","affiliation":[{"name":"Institute of Data and Target Engineering, Information Engineering University, Zhengzhou, China"}]},{"given":"Shiju","family":"Wang","sequence":"additional","affiliation":[{"name":"Institute of Data and Target Engineering, Information Engineering University, Zhengzhou, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00852"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2024.3401772"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3222818"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3194732"},{"key":"ref8","first-page":"197","article-title":"SatMAE: Pre-training transformers for temporal and multi-spectral satellite imagery","volume-title":"Proc. 36th Conf. Neural Inf. Process. Syst.","author":"Cong","year":"2022"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2022.3176603"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3316166"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01541"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1120"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2024.01.012"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.compeleceng.2024.109710"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3447085"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3392238"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00716"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01264-9_8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2019.00941"},{"key":"ref20","article-title":"MobileNets: Efficient convolutional neural networks for mobile Vis. applications","author":"Howard","year":"2017"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00474"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00140"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01506"},{"key":"ref24","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. 36th Int. Conf. Mach. Learn.","author":"Tan","year":"2019"},{"key":"ref25","first-page":"6105","article-title":"EfficientNetV2: Smaller models and faster training","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Tan","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00764"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02617"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01548"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01167"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.00134"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-981-99-8079-6_29"},{"key":"ref33","first-page":"1","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly Vis. transformer","volume-title":"Proc. 10th Int. Conf. Learn. Representations","author":"Mehta","year":"2022"},{"key":"ref34","first-page":"12934","article-title":"EfficientFormer: Vis. transformers at MobileNet speed","volume-title":"Proc. 36th Annu. Conf. Neural Inf. Process. Syst.","author":"Li","year":"2022"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref37","first-page":"5961","article-title":"FLatten transformer: Vis. transformer using focused linear attention","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Han","year":"2023"},{"key":"ref38","article-title":"Separable self-attention for mobile Vis. transformers","author":"Mehta","year":"2022"},{"key":"ref39","article-title":"Mobilevitv3: Mobile-friendly Vis. transformer with simple and effective fusion of local, global and input features","author":"Wadekar","year":"2022"},{"key":"ref40","article-title":"LightViT: Towards light-weight convolution-free Vis. transformers","author":"Huang","year":"2022"},{"key":"ref41","first-page":"17256","article-title":"EfficientViT: Multi-scale linear attention for high-resolution dense prediction","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Cai","year":"2022"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01169"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01183"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19803-8_5"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3367709"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.00520"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2023.3265499"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.5555\/3495724.3497510"},{"key":"ref51","first-page":"22243","article-title":"Big self-supervised models are strong semi-supervised learners","volume-title":"Proc. 34th Int. Conf. Neural Inf. Process. Syst.","author":"Chen","year":"2020"},{"key":"ref52","first-page":"8748","article-title":"Learning transferable visual models from natural language superVis.","volume-title":"Proc. 38th Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01179"},{"key":"ref54","first-page":"1","article-title":"ViTAE: Vis. transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Xu","year":"2021"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3653070"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1016\/j.heliyon.2024.e37962"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00378"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2024.3469568"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2023.3344698"},{"key":"ref61","article-title":"Foundation models for generalist geospatial artificial intelligence","author":"Jakubik","year":"2023"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3362475"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2023.3316302"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2021.3115569"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2023.3271312"},{"key":"ref66","first-page":"20054","article-title":"Cross-scale MAE: A tale of multi-scale exploitation in remote sensing","volume-title":"Proc. 37th Int. Conf. Neural Inf. Process. Syst.","author":"Tang","year":"2024"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/tgrs.2025.3541390"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/jstars.2024.3408154"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.01002"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00928"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2025.3602237"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1007\/s44290-024-00049-z"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01553"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref75","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","volume-title":"Proc. 37th Int. Conf. Mach. Learn.Virtual","author":"Katharopoulos","year":"2020"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_3"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-annals-x-1-w1-2023-371-2023"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/icip.2015.7351502"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr.2018.00418"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51070.2023.01549"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/iccv.2019.00972"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/mgrs.2023.3281651"}],"container-title":["IEEE Transactions on Aerospace and Electronic Systems"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/7\/11316225\/11316819.pdf?arnumber=11316819","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,10]],"date-time":"2026-03-10T19:55:26Z","timestamp":1773172526000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11316819\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":84,"URL":"https:\/\/doi.org\/10.1109\/taes.2025.3649185","relation":{},"ISSN":["0018-9251","1557-9603","2371-9877"],"issn-type":[{"value":"0018-9251","type":"print"},{"value":"1557-9603","type":"electronic"},{"value":"2371-9877","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}