{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T15:40:16Z","timestamp":1784389216879,"version":"3.55.0"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":["62225113"],"award-info":[{"award-number":["62225113"]}],"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":["41871243"],"award-info":[{"award-number":["41871243"]}],"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":["62141112"],"award-info":[{"award-number":["62141112"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Science and Technology Major Project of Hubei Province","award":["2019AEA170"],"award-info":[{"award-number":["2019AEA170"]}]},{"DOI":"10.13039\/501100000923","name":"ARC","doi-asserted-by":"publisher","award":["FL-170100117"],"award-info":[{"award-number":["FL-170100117"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/tgrs.2022.3222818","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T21:06:14Z","timestamp":1669064774000},"page":"1-15","source":"Crossref","is-referenced-by-count":236,"title":["Advancing Plain Vision Transformer Toward Remote Sensing Foundation Model"],"prefix":"10.1109","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6360-4360","authenticated-orcid":false,"given":"Di","family":"Wang","sequence":"first","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Qiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9931-5138","authenticated-orcid":false,"given":"Yufei","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-7661","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-8458","authenticated-orcid":false,"given":"Bo","family":"Du","sequence":"additional","affiliation":[{"name":"School of Computer Science, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6890-3650","authenticated-orcid":false,"given":"Liangpei","family":"Zhang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping and Remote Sensing, Wuhan University, Wuhan, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2016.2577339"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3039359"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3123080"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3109872"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3114404"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2022.3185795"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3097148"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2925070"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3046756"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2020.3037893"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071369"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00415"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3056416"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3062048"},{"key":"ref15","first-page":"1","article-title":"Understanding the effective receptive field in deep convolutional neural networks","volume-title":"Proc. NeurIPS","volume":"29","author":"Luo"},{"key":"ref16","first-page":"1","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. NeurIPS","volume":"34","author":"Xie"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref18","first-page":"1","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref20","article-title":"ViTAEv2: Vision transformer advanced by exploring inductive bias for image recognition and beyond","author":"Zhang","year":"2022","journal-title":"arXiv:2202.10108"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3176603"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3070368"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref25","article-title":"ViTPose: Simple vision transformer baselines for human pose estimation","author":"Xu","year":"2022","journal-title":"arXiv:2204.12484"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00928"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01002"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_27"},{"key":"ref29","article-title":"CoCa: Contrastive captioners are image-text foundation models","author":"Yu","year":"2022","journal-title":"arXiv:2205.01917"},{"key":"ref30","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021","journal-title":"arXiv:2111.11432"},{"key":"ref31","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021","journal-title":"arXiv:2108.07258"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3194732"},{"key":"ref33","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"Devlin","year":"2018","journal-title":"arXiv:1810.04805"},{"key":"ref34","article-title":"Switch transformers: Scaling to trillion parameter models with simple and efficient sparsity","author":"Fedus","year":"2021"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01179"},{"key":"ref36","first-page":"8583","article-title":"Scaling vision with sparse mixture of experts","volume-title":"Proc. NeurIPS","volume":"34","author":"Riquelme"},{"key":"ref37","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. NeurIPS","volume":"34","author":"Dai"},{"key":"ref38","first-page":"12009","article-title":"Swin transformer V2: Scaling up capacity and resolution","volume-title":"Proc. CVPR","author":"Liu"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20176"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3092816"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00296"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3115569"},{"key":"ref45","first-page":"1597","article-title":"A simple framework for contrastive learning of visual representations","volume-title":"Proc. ICML","author":"Chen"},{"key":"ref46","article-title":"Improved baselines with momentum contrastive learning","author":"Chen","year":"2020","journal-title":"arXiv:2003.04297"},{"key":"ref47","article-title":"RegionCL: Can simple region swapping contribute to contrastive learning?","author":"Xu","year":"2021","journal-title":"arXiv:2111.12309"},{"key":"ref48","article-title":"SimMIM: A simple framework for masked image modeling","author":"Xie","year":"2021","journal-title":"arXiv:2111.09886"},{"key":"ref49","first-page":"1","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. NeurIPS","volume":"34","author":"Xu"},{"key":"ref50","article-title":"Searching for activation functions","author":"Ramachandran","year":"2017","journal-title":"arXiv:1710.05941"},{"key":"ref51","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref52","article-title":"BEiT: BERT pre-training of image transformers","author":"Bao","year":"2021","journal-title":"arXiv:2106.08254"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/1869790.1869829"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2017.2685945"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/JPROC.2017.2675998"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00418"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3183022"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.11.023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00350"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i4.16426"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2974745"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3149780"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00281"},{"key":"ref64","first-page":"1","article-title":"Learning high-precision bounding box for rotated object detection via Kullback-Leibler divergence","volume-title":"Proc. NeurIPS","author":"Yang"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00187"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2022.3222906"},{"key":"ref67","first-page":"1","article-title":"Rethinking rotated object detection with Gaussian Wasserstein distance loss","volume-title":"Proc. ICML","author":"Yang"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3136350"},{"key":"ref69","article-title":"The KFIoU loss for rotated object detection","author":"Yang","year":"2022","journal-title":"arXiv:2201.12558"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2021.3127851"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093914"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3011405"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3109661"},{"key":"ref76","article-title":"Aerial scene parsing: From tile-level scene classification to pixel-wise semantic labeling","author":"Long","year":"2022","journal-title":"arXiv:2201.01953"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3106391"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP42928.2021.9506524"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.3390\/rs14225675"},{"key":"ref81","first-page":"28","article-title":"iSAID: A large-scale dataset for instance segmentation in aerial images","volume-title":"Proc. CVPRW","author":"Waqas Zamir"},{"key":"ref82","first-page":"1","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","volume-title":"NeurIPS","volume":"1","author":"Wang"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2572683"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref90","first-page":"1877","article-title":"Language models are few-shot learners","volume-title":"Proc. NeurIPS","volume":"33","author":"Brown"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10006360\/09956816.pdf?arnumber=9956816","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T03:12:00Z","timestamp":1706757120000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9956816\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":90,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2022.3222818","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}