{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,25]],"date-time":"2026-03-25T16:06:25Z","timestamp":1774454785683,"version":"3.50.1"},"reference-count":60,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by-nc-nd\/4.0\/"}],"funder":[{"DOI":"10.13039\/501100003052","name":"Ministry of Trade, Industry and Energy","doi-asserted-by":"publisher","award":["20018906"],"award-info":[{"award-number":["20018906"]}],"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":[[2025]]},"DOI":"10.1109\/access.2025.3534117","type":"journal-article","created":{"date-parts":[[2025,1,24]],"date-time":"2025-01-24T18:32:52Z","timestamp":1737743572000},"page":"18239-18252","source":"Crossref","is-referenced-by-count":3,"title":["EMSFomer: Efficient Multi-Scale Transformer for Real-Time Semantic Segmentation"],"prefix":"10.1109","volume":"13","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":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2016.2644615"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24574-4_28"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"key":"ref6","article-title":"Rethinking Atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3228042"},{"key":"ref8","article-title":"PP-LiteSeg: A superior real-time semantic segmentation model","author":"Peng","year":"2022","journal-title":"arXiv:2204.02681"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01871"},{"key":"ref10","first-page":"1","article-title":"An image is worth 16 \u00d7 16 words: Transformers for image recognition at scale","volume-title":"Proc. ICLR","author":"Dosovitskiy"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref12","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. NeurIPS","author":"Xie"},{"key":"ref13","first-page":"1","article-title":"MaskFormer: Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. NeurIPS","author":"Cheng"},{"key":"ref14","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3211006"},{"key":"ref16","first-page":"1","article-title":"RTFormer: Efficient design for real-time semantic segmentation with transformer","volume-title":"Proc. NeurIPS","author":"Wang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref18","article-title":"DBAT: Dynamic backward attention transformer for material segmentation with cross-resolution patches","author":"Heng","year":"2023","journal-title":"arXiv:2305.03919"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-27066-6_23"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/j.patrec.2008.04.005"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref24","first-page":"1","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. ICLR","author":"Yu"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2022.3157128"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01465-9"},{"key":"ref27","first-page":"30394","article-title":"SegNeXt: Rethinking convolutional attention design for semantic segmentation","volume-title":"Proc. NeurIPS","author":"Guo"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref30","article-title":"SeMask: Semantically masked transformers for semantic segmentation","author":"Jain","year":"2021","journal-title":"arXiv:2112.12782"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01493"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01219-9_25"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_20"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00959"},{"key":"ref35","first-page":"11","article-title":"FasterSeg: Searching for faster real-time semantic segmentation","volume-title":"Proc. ICLR","author":"Chen"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref37","first-page":"1","article-title":"Rethinking attention with performers","volume-title":"Proc. ICLR","author":"Choroma\u0144ski"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.5040\/9781501365072.13350"},{"key":"ref39","article-title":"Longformer: The long-document transformer","author":"Beltagy","year":"2020","journal-title":"arXiv:2004.05150"},{"key":"ref40","first-page":"1","article-title":"Lightweight vision transformer with cross feature attention","volume-title":"Proc. ICIP","author":"Zhao"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICME52920.2022.9859720"},{"key":"ref42","article-title":"CSWin transformer: A general vision transformer backbone with cross-shaped windows","author":"Dong","year":"2021","journal-title":"arXiv:2107.00652"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref47","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. ICLR","author":"Loshchilov"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref49","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. ICML","author":"Tan"},{"key":"ref50","article-title":"PaddleSeg: A high-efficient development toolkit for image segmentation","author":"Liu","year":"2021","journal-title":"arXiv:2101.06175"},{"key":"ref51","article-title":"Fast-SCNN: Fast semantic segmentation network","author":"Poudel","year":"2019","journal-title":"arXiv:1902.04502"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2017.2750080"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01191"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00426"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00936"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01515-2"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01289"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00929"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"}],"container-title":["IEEE Access"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/6287639\/10820123\/10852306.pdf?arnumber=10852306","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,1,30]],"date-time":"2025-01-30T19:25:09Z","timestamp":1738265109000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10852306\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":60,"URL":"https:\/\/doi.org\/10.1109\/access.2025.3534117","relation":{},"ISSN":["2169-3536"],"issn-type":[{"value":"2169-3536","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]}}}