{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,30]],"date-time":"2026-06-30T15:50:56Z","timestamp":1782834656254,"version":"3.54.5"},"reference-count":48,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Science Foundation (NSF) of China","doi-asserted-by":"publisher","award":["62071131"],"award-info":[{"award-number":["62071131"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100021171","name":"Basic and Applied Basic Research Foundation of Guangdong Province","doi-asserted-by":"publisher","award":["2022B1515020086"],"award-info":[{"award-number":["2022B1515020086"]}],"id":[{"id":"10.13039\/501100021171","id-type":"DOI","asserted-by":"publisher"}]},{"name":"International Collaborative Research Program of Guangdong Science and Technology Department","award":["2022A0505050070"],"award-info":[{"award-number":["2022A0505050070"]}]},{"name":"Industrial Research and Development Project of Haoyang Electronic Company Ltd","award":["2022440002001494"],"award-info":[{"award-number":["2022440002001494"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Geosci. Remote Sensing"],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tgrs.2022.3223416","type":"journal-article","created":{"date-parts":[[2022,11,21]],"date-time":"2022-11-21T21:06:14Z","timestamp":1669064774000},"page":"1-13","source":"Crossref","is-referenced-by-count":14,"title":["2DSegFormer: 2-D Transformer Model for Semantic Segmentation on Aerial Images"],"prefix":"10.1109","volume":"60","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-2317-4110","authenticated-orcid":false,"given":"Xinyu","family":"Li","sequence":"first","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6717-5727","authenticated-orcid":false,"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1538-249X","authenticated-orcid":false,"given":"Yi","family":"Fang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8628-3483","authenticated-orcid":false,"given":"Hongmei","family":"Liang","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Shaoqiu","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Information Engineering, Guangdong University of Technology, Guangzhou, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.3390\/rs13163065"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3050824"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.3390\/rs14061498"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.3390\/rs13132524"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3065112"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144894"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144165"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3003425"},{"key":"ref40","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume":"34","author":"xie","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3034011"},{"key":"ref12","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":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref14","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015","journal-title":"arXiv 1511 07122"},{"key":"ref15","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"arXiv 2010 11929"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref17","first-page":"1","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref18","first-page":"1243","article-title":"Convolutional sequence to sequence learning","author":"gehring","year":"2017","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.09.005"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3076664"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1016\/j.jag.2021.102667"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3053062"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref29","article-title":"Multiattention network for semantic segmentation of fine-resolution remote sensing images","volume":"60","author":"li","year":"2021","journal-title":"EEE Trans Geosci Remote Sens"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2018.2878510"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2017.11.024"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2015.2451002"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3146296"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/IGARSS.2018.8519049"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3046321"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref20","first-page":"1","article-title":"Stand-alone self-attention in vision models","volume":"32","author":"ramachandran","year":"2019","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00988"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/WACV.2018.00168"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2979552"},{"key":"ref41","first-page":"448","article-title":"Batch normalization: Accelerating deep network training by reducing internal covariate shift","author":"ioffe","year":"2015","journal-title":"Proc 32nd Int Conf Mach Learn"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2016.01.004"},{"key":"ref44","author":"contributors","year":"2021","journal-title":"MMSegmentation Openmmlab semantic segmentation toolbox and benchmark"},{"key":"ref26","article-title":"Cascaded multiscale structure with self-smoothing atrous convolution for semantic segmentation","volume":"60","author":"li","year":"2021","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.05.009"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.3390\/rs13245015"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/9633014\/09955997.pdf?arnumber=9955997","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,2]],"date-time":"2022-12-02T20:58:03Z","timestamp":1670014683000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9955997\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":48,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2022.3223416","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]}}}