{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,4]],"date-time":"2026-07-04T16:41:36Z","timestamp":1783183296797,"version":"3.54.6"},"reference-count":80,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3655121","type":"journal-article","created":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:28Z","timestamp":1769634088000},"page":"1899-1909","source":"Crossref","is-referenced-by-count":8,"title":["CAS-ViT: Convolutional Additive Self-Attention Vision Transformers for Efficient Mobile Applications"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-4183-7053","authenticated-orcid":false,"given":"Tianfang","family":"Zhang","sequence":"first","affiliation":[{"name":"SenseTime Research, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lei","family":"Li","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-1439-7282","authenticated-orcid":false,"given":"Yang","family":"Zhou","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6587-9878","authenticated-orcid":false,"given":"Wentao","family":"Liu","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8761-5563","authenticated-orcid":false,"given":"Chen","family":"Qian","sequence":"additional","affiliation":[{"name":"SenseTime Research, Shanghai, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8877-2421","authenticated-orcid":false,"given":"Jenq-Neng","family":"Hwang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, University of Washington, Seattle, United States"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7333-9975","authenticated-orcid":false,"given":"Xiangyang","family":"Ji","sequence":"additional","affiliation":[{"name":"Department of Automation, Tsinghua University, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref2","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. NIPS","author":"Han"},{"key":"ref3","first-page":"22690","article-title":"Vision transformer with super token sampling","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit. (CVPR)","author":"Huang"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TAES.2023.3238703"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCC56324.2022.10065722"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110963"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3329173"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1016\/j.cag.2023.08.003"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00474"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref14","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"Mehta","year":"2021","journal-title":"arXiv:2110.02178"},{"key":"ref15","article-title":"AGPCNet: Attention-guided pyramid context networks for infrared small target detection","author":"Zhang","year":"2021","journal-title":"arXiv:2111.03580"},{"key":"ref16","article-title":"FasterViT: Fast vision transformers with hierarchical attention","author":"Hatamizadeh","year":"2023","journal-title":"arXiv:2306.06189"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01598"},{"key":"ref21","article-title":"Separable self-attention for mobile vision transformers","author":"Mehta","year":"2022","journal-title":"arXiv:2206.02680"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref23","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref24","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":"ref25","article-title":"Spectral convolutional transformer: Harmonizing real vs. complex multi-view spectral operators for vision transformer","author":"Patro","year":"2024","journal-title":"arXiv:2403.18063"},{"key":"ref26","first-page":"1","article-title":"Spike-driven transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yao"},{"key":"ref27","first-page":"1","article-title":"Lightweight vision transformer with bidirectional interaction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Fan"},{"key":"ref28","first-page":"3531","article-title":"Efficient attention: Attention with linear complexities","volume-title":"Proc. IEEE\/CVF Winter Conf. Appl. Comput. Vis.","author":"Shen"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01386"},{"key":"ref30","first-page":"1","article-title":"Efficient token mixing for transformers via adaptive Fourier neural operators","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Guibas"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"ref34","article-title":"Next-ViT: Next generation vision transformer for efficient deployment in realistic industrial scenarios","author":"Li","year":"2022","journal-title":"arXiv:2207.05501"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00057"},{"key":"ref37","first-page":"1","article-title":"Scattering vision transformer: Spectral mixing matters","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Patro"},{"key":"ref38","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":"ref39","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NIPS)","volume":"34","author":"Ali"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_1"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-25082-8_3"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1807.06521"},{"key":"ref45","first-page":"315","article-title":"Deep sparse rectifier neural networks","volume-title":"Proc. 14th Int. Conf. Artif. Intell. Statist.","author":"Glorot"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.10882"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00764"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref53","volume-title":"Pytorch Image Models","author":"Wightman","year":"2019"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01506"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73661-2_5"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00134"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3596776"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01549"},{"key":"ref59","first-page":"12633","article-title":"Global context vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hatamizadeh"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-024-02034-6"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i6.32690"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00542"},{"key":"ref63","article-title":"Natural adversarial examples","author":"Hendrycks","year":"2019","journal-title":"arXiv:1907.07174"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref65","first-page":"1","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref66","first-page":"12934","article-title":"EfficientFormer: Vision transformers at MobileNet speed","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Li"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref68","first-page":"1","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref69","first-page":"1","article-title":"SGDR: Stochastic gradient descent with warm restarts","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Loshchilov"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref73","first-page":"8026","article-title":"PyTorch: An imperative style, high-performance deep learning library","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"32","author":"Paszke"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1906.07155"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11363151.pdf?arnumber=11363151","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,19]],"date-time":"2026-02-19T21:01:15Z","timestamp":1771534875000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11363151\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":80,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3655121","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}