{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T18:08:16Z","timestamp":1775326096840,"version":"3.50.1"},"reference-count":69,"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":["62171381"],"award-info":[{"award-number":["62171381"]}],"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":[[2023]]},"DOI":"10.1109\/tgrs.2023.3302024","type":"journal-article","created":{"date-parts":[[2023,8,4]],"date-time":"2023-08-04T17:23:16Z","timestamp":1691169796000},"page":"1-15","source":"Crossref","is-referenced-by-count":80,"title":["Rethinking Transformers for Semantic Segmentation of Remote Sensing Images"],"prefix":"10.1109","volume":"61","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5007-8533","authenticated-orcid":false,"given":"Yuheng","family":"Liu","sequence":"first","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4533-3880","authenticated-orcid":false,"given":"Yifan","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5689-8271","authenticated-orcid":false,"given":"Ye","family":"Wang","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8018-596X","authenticated-orcid":false,"given":"Shaohui","family":"Mei","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.01.013"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-022-07737-w"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.04.015"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.3390\/rs12040701"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093977"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.01.020"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2020.114532"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.3390\/rs13040808"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s12145-018-00376-7"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.3390\/s18103232"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.3390\/rs11161922"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3103517"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-540-77058-9_42"},{"key":"ref19","first-page":"234","article-title":"U-Net: Convolutional networks for biomedical image segmentation","author":"ronneberger","year":"2015","journal-title":"Proc Int Conf Med Image Comput Comput -Assist Intervent"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref51","first-page":"801","article-title":"Encoder–decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3119654"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183585"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref47","article-title":"BEiT: BERT pre-training of image transformers","author":"bao","year":"2021","journal-title":"arXiv 2106 08254"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144165"},{"key":"ref41","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","author":"wang","year":"2021","journal-title":"arXiv 2110 08733"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144894"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.3390\/en14102960"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.3390\/rs12071130"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/s12665-011-1112-y"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijdrr.2018.11.022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00107"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLII-2-W16-273-2019"},{"key":"ref5","first-page":"1609","article-title":"Remote sensing for natural disaster management","volume":"33","author":"van westen","year":"2000","journal-title":"Int Arch Photogramm Remote Sens"},{"key":"ref40","year":"2018","journal-title":"2d semantic labeling dataset"},{"key":"ref35","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume":"139","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Represent"},{"key":"ref37","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume":"34","author":"chu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119508"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2022.04.006"},{"key":"ref33","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119858"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.90"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1080\/01431160512331316469"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2994150"},{"key":"ref68","article-title":"Swin-UNet: UNet-like pure transformer for medical image segmentation","author":"cao","year":"2021","journal-title":"arXiv 2105 05537"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3015157"},{"key":"ref67","first-page":"325","article-title":"BiSeNet: Bilateral segmentation network for real-time semantic segmentation","author":"yu","year":"2018","journal-title":"Proc Eur Conf Comput Vis (ECCV)"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2795531"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/rs13010071"},{"key":"ref69","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015","journal-title":"arXiv 1511 07122"},{"key":"ref20","first-page":"3","article-title":"UNet++: A nested U-Net architecture for medical image segmentation","author":"zhou","year":"2018","journal-title":"Deep Learning in Medical Image Analysis and Multimodal Learning for Clinical Decision Support"},{"key":"ref64","first-page":"1","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018","journal-title":"Proc North Amer Chapter Assoc Comput Linguistics"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2988294"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref65","first-page":"8821","article-title":"Zero-shot text-to-image generation","author":"ramesh","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3124913"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3016820"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2018.2878958"},{"key":"ref60","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"xie","year":"2021","journal-title":"Proc NIPS"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00398"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10006360\/10209224.pdf?arnumber=10209224","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,9,4]],"date-time":"2023-09-04T18:03:59Z","timestamp":1693850639000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10209224\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2023.3302024","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}