{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2024,9,7]],"date-time":"2024-09-07T05:55:44Z","timestamp":1725688544705},"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\/501100012166","name":"National Key Research and Development Program of China","doi-asserted-by":"publisher","award":["2018YFB0504800","2018YFB0504801"],"id":[{"id":"10.13039\/501100012166","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.2023.3276172","type":"journal-article","created":{"date-parts":[[2023,5,15]],"date-time":"2023-05-15T18:32:08Z","timestamp":1684175528000},"page":"1-19","source":"Crossref","is-referenced-by-count":3,"title":["Crisscross-Global Vision Transformers Model for Very High Resolution Aerial Image Semantic Segmentation"],"prefix":"10.1109","volume":"61","author":[{"ORCID":"http:\/\/orcid.org\/0000-0001-9529-7852","authenticated-orcid":false,"given":"Guohui","family":"Deng","sequence":"first","affiliation":[{"name":"School of Internet, Anhui University, Anhui, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0003-2435-5538","authenticated-orcid":false,"given":"Zhaocong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Remote Sensing and Information Engineering, Wuhan University, Wuhan, China"}]},{"given":"Miaozhong","family":"Xu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China"}]},{"ORCID":"http:\/\/orcid.org\/0000-0001-8546-9120","authenticated-orcid":false,"given":"Chengjun","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China"}]},{"given":"Zhiye","family":"Wang","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China"}]},{"given":"Zhongyuan","family":"Lu","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing, Wuhan University, Wuhan, China"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2021.3074161"},{"key":"ref12","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":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3063381"},{"key":"ref15","article-title":"CSWin transformer: A general vision transformer backbone with cross-shaped windows","author":"dong","year":"2021","journal-title":"arXiv 2107 00652"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2022.3143368"},{"key":"ref14","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":"ref58","doi-asserted-by":"publisher","DOI":"10.3390\/rs10091429"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2021.3063799"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.3042202"},{"key":"ref11","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":"ref55","first-page":"1","article-title":"Multitask semantic boundary awareness network for remote sensing image segmentation","volume":"60","author":"li","year":"2021","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.319"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2016.2616585"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2016.2569162"},{"key":"ref16","year":"2022","journal-title":"International society for photogrammetry and remote sensing 2d semantic labeling challenge"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref18","article-title":"LoveDA: A remote sensing land-cover dataset for domain adaptive semantic segmentation","author":"wang","year":"2021","journal-title":"arXiv 2110 08733"},{"key":"ref51","article-title":"A review on deep learning techniques applied to semantic segmentation","author":"garcia-garcia","year":"2017","journal-title":"arXiv 1704 06857"},{"key":"ref50","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017","journal-title":"arXiv 1711 05101"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_1"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref48","year":"2015","journal-title":"IEEE GRSS Data Fusion Contest"},{"key":"ref47","year":"2022","journal-title":"International society for photogrammetry and remote sensing 2d semantic labeling challenge"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref49","first-page":"1","article-title":"Automatic differentiation in PyTorch","author":"paszke","year":"2017","journal-title":"Proc NIPS"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/WACV48630.2021.00056"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1080\/01431161.2020.1849852"},{"key":"ref9","article-title":"Object detectors emerge in deep scene CNNs","author":"zhou","year":"2014","journal-title":"arXiv 1412 6856"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2017.12.007"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2019.2913861"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref40","article-title":"How much position information do convolutional neural networks encode?","author":"amirul islam","year":"2020","journal-title":"arXiv 2001 08248"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00863"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.3390\/rs13183585"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/JSTARS.2021.3119654"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/TGRS.2020.2994150"},{"key":"ref33","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2020","journal-title":"arXiv 2012 12877"},{"key":"ref32","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2000.901014"},{"key":"ref1","first-page":"108","article-title":"A novel image segmentation algorithm based on convex polygon edge detection","author":"yishao","year":"2004","journal-title":"Proc IEEE Region 10 Conf (TENCON)"},{"key":"ref39","article-title":"Conditional positional encodings for vision transformers","author":"chu","year":"2021","journal-title":"arXiv 2102 10882"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref24","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00415"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/VCIP.2017.8305148"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2019.07.007"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_49"},{"key":"ref69","first-page":"1","article-title":"FactSeg: Foreground activation-driven small object semantic segmentation in large-scale remote sensing imagery","volume":"60","author":"ma","year":"2021","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2018.2795531"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1117\/1.JRS.13.016501"},{"key":"ref22","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":"ref66","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 4th International Workshop DLMIA 2018 and 8th International Workshop ML-CDS 2018 Held in Conjunction with MICCAI 2018 Granada Spain September 20 2018 Proceedings 4"},{"key":"ref21","article-title":"RiFCN: Recurrent network in fully convolutional network for semantic segmentation of high resolution remote sensing images","author":"mou","year":"2018","journal-title":"arXiv 1805 02091"},{"key":"ref65","article-title":"Pyramid attention network for semantic segmentation","author":"li","year":"2018","journal-title":"arXiv 1805 10180"},{"key":"ref28","first-page":"1","article-title":"Deep multimodal fusion network for semantic segmentation using remote sensing image and LiDAR data","volume":"60","author":"sun","year":"2021","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref27","first-page":"1","article-title":"A gather-to-guide network for remote sensing semantic segmentation of RGB and auxiliary image","volume":"60","author":"zheng","year":"2021","journal-title":"IEEE Trans Geosci Remote Sens"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/LGRS.2020.2988294"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1016\/j.isprsjprs.2018.01.021"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1016\/j.cviu.2019.102809"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"}],"container-title":["IEEE Transactions on Geoscience and Remote Sensing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/36\/10006360\/10124438.pdf?arnumber=10124438","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,19]],"date-time":"2023-06-19T18:03:36Z","timestamp":1687197816000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10124438\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":69,"URL":"https:\/\/doi.org\/10.1109\/tgrs.2023.3276172","relation":{},"ISSN":["0196-2892","1558-0644"],"issn-type":[{"value":"0196-2892","type":"print"},{"value":"1558-0644","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}
