{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T21:02:12Z","timestamp":1766437332139,"version":"3.48.0"},"reference-count":91,"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:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Foundation of Key Laboratory of Artificial Intelligence of Ministry of Education","award":["AI202404"],"award-info":[{"award-number":["AI202404"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2025]]},"DOI":"10.1109\/tip.2025.3639919","type":"journal-article","created":{"date-parts":[[2025,12,11]],"date-time":"2025-12-11T18:48:12Z","timestamp":1765478892000},"page":"8243-8256","source":"Crossref","is-referenced-by-count":0,"title":["S2AFormer: Strip Self-Attention for Efficient Vision Transformer"],"prefix":"10.1109","volume":"34","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, NSW, Australia"}],"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, NSW, 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, NSW, Australia"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7478-4544","authenticated-orcid":false,"given":"Jiamao","family":"Li","sequence":"additional","affiliation":[{"name":"Bionic Vision System Laboratory and the State Key Laboratory of Transducer Technology, Shanghai Institute of Microsystem and Information Technology, Chinese Academy of Sciences, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3950-1844","authenticated-orcid":false,"given":"Guangwei","family":"Gao","sequence":"additional","affiliation":[{"name":"PCA Laboratory, the Key Laboratory of Intelligent Perception and Systems for High-Dimensional Information of Ministry of Education, and the School of Computer Science and Engineering, Nanjing University of Science and Technology, Nanjing, 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":"10.1007\/978-3-030-58452-8_13"},{"key":"ref2","article-title":"An image is worth 16\u00d716 words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20080-9_30"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00135"},{"key":"ref7","first-page":"12077","article-title":"SegFormer: Simple and efficient design for semantic segmentation with transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xie"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3596776"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"ref10","article-title":"IFormer: Integrating ConvNet and transformer for mobile application","author":"Zheng","year":"2025","journal-title":"arXiv:2501.15369"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref13","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","author":"Rao","year":"Jun. 2021","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref14","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","author":"Liang","year":"2022","journal-title":"arXiv:2202.07800"},{"key":"ref15","article-title":"Not all images are worth 16\u00d716 words: Dynamic transformers for efficient image recognition","author":"Wang","year":"2021","journal-title":"arXiv:2105.15075"},{"key":"ref16","first-page":"69328","article-title":"MG-ViT: A multi-granularity method for compact and efficient vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"36","author":"Zhang"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00552"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1145\/3582649.3582676"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00050"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2913372"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.01506"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00550"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3425048"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00141"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00078"},{"key":"ref31","first-page":"12934","article-title":"EfficientFormer: Vision transformers at MobileNet speed","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02353"},{"key":"ref34","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"El-Nouby"},{"key":"ref35","article-title":"Efficient modulation for vision networks","author":"Ma","year":"2024","journal-title":"arXiv:2403.19963"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01062"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00208"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19211-1_33"},{"key":"ref39","article-title":"Reformer: The efficient transformer","author":"Kitaev","year":"2020","journal-title":"arXiv:2001.04451"},{"key":"ref40","article-title":"Linformer: Self-attention with linear complexity","author":"Wang","year":"2020","journal-title":"arXiv:2006.04768"},{"key":"ref41","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00520"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-1-4842-6168-2_11"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref46","article-title":"RepNeXt: A fast multi-scale CNN using structural reparameterization","author":"Zhao","year":"2024","journal-title":"arXiv:2406.16004"},{"key":"ref47","article-title":"CAS-ViT: Convolutional additive self-attention vision transformers for efficient mobile applications","author":"Zhang","year":"2024","journal-title":"arXiv:2408.03703"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref49","article-title":"Separable self-attention for mobile vision transformers","author":"Mehta","year":"2022","journal-title":"arXiv:2206.02680"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3065386"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01157"},{"key":"ref56","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"Howard","year":"2017","journal-title":"arXiv:1704.04861"},{"key":"ref57","article-title":"Vision mamba: Efficient visual representation learning with bidirectional state space model","author":"Zhu","year":"2024","journal-title":"arXiv:2401.09417"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00424"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00908"},{"key":"ref60","article-title":"Vision-RWKV: Efficient and scalable visual perception with RWKV-like architectures","author":"Duan","year":"2024","journal-title":"arXiv:2403.02308"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"ref62","first-page":"5762","article-title":"FastViT: A fast hybrid vision transformer using structural reparameterization","volume-title":"Proc. IEEE\/CVF Int. Conf. Comput. Vis.","author":"Vasu"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"ref64","first-page":"15234","article-title":"Lightweight vision transformer with bidirectional interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00215"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00544"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00539"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"ref69","article-title":"MambaOut: Do we really need mamba for vision?","author":"Yu","year":"2024","journal-title":"arXiv:2405.07992"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00531"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref72","article-title":"PlainMamba: Improving non-hierarchical mamba in visual recognition","author":"Yang","year":"2024","journal-title":"arXiv:2403.17695"},{"key":"ref73","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Yang"},{"key":"ref74","article-title":"Advancing vision transformers with group-mix attention","author":"Ge","year":"2023","journal-title":"arXiv:2311.15157"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3329173"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3401450"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01390"},{"key":"ref81","article-title":"Mobilemamba: Lightweight multi-receptive visual Mamba network","author":"He","year":"2024","journal-title":"arXiv:2411.15941"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref84","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2017.2699184"},{"volume-title":"MMSegmentation: Openmmlab Semantic Segmentation Toolbox and Benchmark","year":"2020","key":"ref87"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.07155"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/10795784\/11298398.pdf?arnumber=11298398","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,22]],"date-time":"2025-12-22T18:44:33Z","timestamp":1766429073000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11298398\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/tip.2025.3639919","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"type":"print","value":"1057-7149"},{"type":"electronic","value":"1941-0042"}],"subject":[],"published":{"date-parts":[[2025]]}}}