{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,8]],"date-time":"2026-05-08T16:09:05Z","timestamp":1778256545271,"version":"3.51.4"},"reference-count":77,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["423377341"],"award-info":[{"award-number":["423377341"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100013317","name":"Shanxi Provincial Key Research and Development Project","doi-asserted-by":"publisher","award":["2023-ZDLNY-69"],"award-info":[{"award-number":["2023-ZDLNY-69"]}],"id":[{"id":"10.13039\/501100013317","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing"],"published-print":{"date-parts":[[2024]]},"DOI":"10.1109\/jstars.2024.3397488","type":"journal-article","created":{"date-parts":[[2024,5,7]],"date-time":"2024-05-07T17:31:38Z","timestamp":1715103098000},"page":"9745-9758","source":"Crossref","is-referenced-by-count":29,"title":["MCAT-UNet: Convolutional and Cross-Shaped Window Attention Enhanced UNet for Efficient High-Resolution Remote Sensing Image Segmentation"],"prefix":"10.1109","volume":"17","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-5277-8985","authenticated-orcid":false,"given":"Tao","family":"Wang","sequence":"first","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2793-0350","authenticated-orcid":false,"given":"Chao","family":"Xu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9388-0198","authenticated-orcid":false,"given":"Bin","family":"Liu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-9023-3306","authenticated-orcid":false,"given":"Guang","family":"Yang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3408-1932","authenticated-orcid":false,"given":"Erlei","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1576-1657","authenticated-orcid":false,"given":"Dangdang","family":"Niu","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4605-8577","authenticated-orcid":false,"given":"Hongming","family":"Zhang","sequence":"additional","affiliation":[{"name":"College of Information Engineering, Northwest A&F University, Yangling, China"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1016\/j.rse.2019.111402"},{"key":"ref2","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","author":"Wang","year":"2021"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/s11356-020-08984-x"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.gloenvcha.2012.11.006"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.3390\/rs10081230"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.5194\/isprs-archives-XLIII-B3-2020-1497-2020"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw53098.2021.00121"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00415"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2016.90"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2024.3367765"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2021.3071369"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102383"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3231870"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2020.01.013"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3063381"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.3011151"},{"key":"ref19","article-title":"Semantic image segmentation with deep convolutional nets and fully connected crfs","author":"Chen","year":"2014"},{"key":"ref20","article-title":"Multi-scale context aggregation by dilated convolutions","author":"Yu","year":"2015"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00064"},{"key":"ref25","article-title":"Ocnet: Object context network for scene parsing","author":"Yuan","year":"2018"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref27","first-page":"10326","article-title":"K-net: Towards unified image segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref29","article-title":"VIT: An image is worth 16x16 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3222818"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144165"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3215200"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2022.3144894"},{"key":"ref37","first-page":"1140","article-title":"Segnext: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"35","author":"Guo"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3256064"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2022.06.008"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2020.107404"},{"key":"ref43","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00309"},{"key":"ref45","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Xie"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref47","article-title":"Transunet: Transformers make strong encoders for medical image segmentation","author":"Chen","year":"2021"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25066-8_9"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01894-8"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.5555\/3298023.3298188"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref54","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Tan"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref59","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref60","article-title":"Deformable detr: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2020"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01075"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP46576.2022.9897766"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25412"},{"key":"ref65","first-page":"15475","article-title":"Rest: An efficient transformer for visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Zhang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref67","article-title":"Beit: Bert pre-training of image transformers","author":"Bao","year":"2021"},{"key":"ref68","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Chu"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.3390\/rs13163065"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2021.09.005"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3093977"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3289408"},{"key":"ref73","article-title":"AerialFormer: Multi-resolution transformer for aerial image segmentation","author":"Yamazaki","year":"2023"},{"key":"ref74","article-title":"OpenMMLab semantic segmentation toolbox and benchmark","year":"2023"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.16.014515"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2023.3268159"}],"container-title":["IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/4609443\/10330207\/10521698.pdf?arnumber=10521698","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,5,20]],"date-time":"2024-05-20T17:26:14Z","timestamp":1716225974000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10521698\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"references-count":77,"URL":"https:\/\/doi.org\/10.1109\/jstars.2024.3397488","relation":{},"ISSN":["1939-1404","2151-1535"],"issn-type":[{"value":"1939-1404","type":"print"},{"value":"2151-1535","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]}}}