{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T06:14:11Z","timestamp":1778566451916,"version":"3.51.4"},"reference-count":73,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100019642","name":"Foundation of the State Key Laboratory of Integrated Services Networks of Xidian University","doi-asserted-by":"publisher","award":["ISN27-4"],"award-info":[{"award-number":["ISN27-4"]}],"id":[{"id":"10.13039\/501100019642","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3688157","type":"journal-article","created":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T19:43:00Z","timestamp":1778096580000},"page":"4847-4860","source":"Crossref","is-referenced-by-count":0,"title":["SCASeg: Strip Cross-Attention for Efficient Semantic Segmentation"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0181-4140","authenticated-orcid":false,"given":"Guoan","family":"Xu","sequence":"first","affiliation":[{"name":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2235-4101","authenticated-orcid":false,"given":"Jiaming","family":"Chen","sequence":"additional","affiliation":[{"name":"Department of Computer Science, The University of Manchester, Manchester, U.K."}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9373-1720","authenticated-orcid":false,"given":"Wenfeng","family":"Huang","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0940-3338","authenticated-orcid":false,"given":"Wenjing","family":"Jia","sequence":"additional","affiliation":[{"name":"Faculty of Engineering and Information Technology, University of Technology Sydney, Sydney, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3950-1844","authenticated-orcid":false,"given":"Guangwei","family":"Gao","sequence":"additional","affiliation":[{"name":"State Key Laboratory of Integrated Services Networks, Xidian University, Xi’an, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3508-1851","authenticated-orcid":false,"given":"Guo-Jun","family":"Qi","sequence":"additional","affiliation":[{"name":"Research Center for Industries of the Future and the School of Engineering, Westlake University, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0084"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1909.11065"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19815-1_36"},{"key":"ref5","article-title":"Efficient modulation for vision networks","author":"Ma","year":"2024","journal-title":"arXiv:2403.19963"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2023.3248089"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3435571"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0385"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00915"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298965"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00326"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref14","article-title":"An image is worth $16 \\times 16$\n words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref15","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":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00050"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i2.25321"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00750"},{"key":"ref19","article-title":"MacFormer: Semantic segmentation with fine object boundaries","author":"Xu","year":"2024","journal-title":"arXiv:2408.05699"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"ref23","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Ali"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.350"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00132"},{"issue":"1","key":"ref26","first-page":"1","article-title":"Pascal VOC 2008 challenge","volume":"24","author":"Hoiem","year":"2009","journal-title":"World Literature Today"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00017"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00681"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i6.28457"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00525"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1802.02611"},{"key":"ref33","article-title":"Rethinking atrous convolution for semantic image segmentation","author":"Chen","year":"2017","journal-title":"arXiv:1706.05587"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00747"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01243"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01368"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00110"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01308"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01496"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00721"},{"key":"ref42","article-title":"CLUSTSEG: Clustering for universal segmentation","author":"Liang","year":"2023","journal-title":"arXiv:2305.02187"},{"key":"ref43","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref48","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref52","article-title":"SwiftNet: Using graph propagation as meta-knowledge to search highly representative neural architectures","author":"Cheng","year":"2019","journal-title":"arXiv:1906.08305"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00671"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/icip55913.2025.11084523"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00086"},{"key":"ref56","article-title":"ContextFormer: Redefining efficiency in semantic segmentation","author":"Abid","year":"2025","journal-title":"arXiv:2501.19255"},{"key":"ref57","first-page":"5974","article-title":"SeaFormer: Squeeze-enhanced axial transformer for mobile semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wan"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TITS.2024.3417813"},{"key":"ref59","first-page":"667","article-title":"Multi-scale representations by varying window attention for semantic segmentation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Yan"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3596776"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00918"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72946-1_6"},{"key":"ref63","first-page":"61381","article-title":"Vision-RWKV: Efficient and scalable visual perception with rwkv-like architectures","volume-title":"Proc. 13th Int. Conf. Learn. Represent.","author":"Duan"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2025.3534532"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.02076"},{"key":"ref66","first-page":"17","article-title":"Per-pixel classification is not all you need for semantic segmentation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Cheng"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01777"},{"key":"ref68","first-page":"667","article-title":"Multi-scale representations by varing window attention for semantic segmentation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Yan"},{"key":"ref69","volume-title":"MMSegmentation: OpenMMLab Semantic Segmentation Toolbox and Benchmark","year":"2020"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01155"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01350"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11511404.pdf?arnumber=11511404","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T05:40:24Z","timestamp":1778564424000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11511404\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":73,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3688157","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}