{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,28]],"date-time":"2026-02-28T18:20:51Z","timestamp":1772302851636,"version":"3.50.1"},"reference-count":55,"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:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Technology Innovation Program of the Ministry of Trade, Industry and Energy (MOTIE), Republic of Korea","doi-asserted-by":"publisher","award":["1415181272"],"award-info":[{"award-number":["1415181272"]}],"id":[{"id":"10.13039\/501100003052","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Access"],"published-print":{"date-parts":[[2023]]},"DOI":"10.1109\/access.2023.3329435","type":"journal-article","created":{"date-parts":[[2023,11,1]],"date-time":"2023-11-01T18:23:36Z","timestamp":1698863016000},"page":"122345-122356","source":"Crossref","is-referenced-by-count":6,"title":["Enhancing Semantically Masked Transformer With Local Attention for Semantic Segmentation"],"prefix":"10.1109","volume":"11","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5225-5580","authenticated-orcid":false,"given":"Zhengyu","family":"Xia","sequence":"first","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8833-0319","authenticated-orcid":false,"given":"Joohee","family":"Kim","sequence":"additional","affiliation":[{"name":"Illinois Institute of Technology, Chicago, IL, USA"}]}],"member":"263","reference":[{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref12","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","author":"xie","year":"2021","journal-title":"Proc NIPS"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref14","first-page":"17864","article-title":"Per-pixel classification is not all you need for semantic segmentation","author":"cheng","year":"2021","journal-title":"Proc NIPS"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ACCESS.2018.2880877"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00388"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-014-0733-5"},{"key":"ref54","first-page":"1140","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","author":"guo","year":"2021","journal-title":"Proc NIPS"},{"key":"ref17","first-page":"1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc NIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref18","article-title":"SeMask: Semantically masked transformers for semantic segmentation","author":"jain","year":"2021","journal-title":"arXiv 2112 12782"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01240-3_17"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00294"},{"key":"ref45","first-page":"1","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2019","journal-title":"Proc ICLR"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref42","article-title":"Layer normalization","author":"lei ba","year":"2016","journal-title":"arXiv 1607 06450"},{"key":"ref41","article-title":"Gaussian error linear units (GELUs)","author":"hendrycks","year":"2016","journal-title":"arXiv 1606 08415"},{"key":"ref44","author":"wu","year":"2019","journal-title":"Detectron2"},{"key":"ref43","first-page":"1","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc NIPS"},{"key":"ref49","article-title":"Swin transformer v2: Scaling up capacity and resolution","author":"liu","year":"2021","journal-title":"arXiv 2111 09883"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref9","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc ECCV"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref6","first-page":"833","article-title":"Encoder–decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc 15th Eur Conf Comput Vis (ECCV)"},{"key":"ref5","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"chen","year":"2017","journal-title":"arXiv 1706 05587"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.169"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.81"},{"key":"ref37","first-page":"1","article-title":"P2T: Pyramid pooling transformer for scene understanding","volume":"99","author":"wu","year":"2022","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2577031"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref33","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc MLRE"},{"key":"ref32","first-page":"1","article-title":"An image is worth 16×16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Proc ICLR"},{"key":"ref2","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref38","article-title":"Deep residual learning for image recognition","author":"he","year":"2015","journal-title":"arXiv 1512 03385"},{"key":"ref24","first-page":"30392","article-title":"Early convolutions help transformers see better","author":"xiao","year":"2021","journal-title":"Proc NIPS"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00063"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref28","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2016","journal-title":"Proc ILCR"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2389824"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/6287639\/10005208\/10304180.pdf?arnumber=10304180","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,11]],"date-time":"2023-12-11T20:43:41Z","timestamp":1702327421000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10304180\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"references-count":55,"URL":"https:\/\/doi.org\/10.1109\/access.2023.3329435","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]}}}