{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,22]],"date-time":"2026-01-22T09:08:05Z","timestamp":1769072885985,"version":"3.49.0"},"reference-count":46,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,10,1]],"date-time":"2024-10-01T00:00:00Z","timestamp":1727740800000},"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. Artif. Intell."],"published-print":{"date-parts":[[2024,10]]},"DOI":"10.1109\/tai.2024.3415551","type":"journal-article","created":{"date-parts":[[2024,6,18]],"date-time":"2024-06-18T14:20:53Z","timestamp":1718720453000},"page":"4915-4927","source":"Crossref","is-referenced-by-count":3,"title":["CS-Mixer: A Cross-Scale Vision Multilayer Perceptron With Spatial\u2013Channel Mixing"],"prefix":"10.1109","volume":"5","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5075-3524","authenticated-orcid":false,"given":"Jonathan","family":"Cui","sequence":"first","affiliation":[{"name":"Pennsylvania State University, University Park, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-3321-9195","authenticated-orcid":false,"given":"David A.","family":"Araujo","sequence":"additional","affiliation":[{"name":"Pennsylvania State University – Harrisburg, Middletown, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9440-6785","authenticated-orcid":false,"given":"Suman","family":"Saha","sequence":"additional","affiliation":[{"name":"School of Electrical Engineering and Computer Science, Pennsylvania State University, University Park, PA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6088-9487","authenticated-orcid":false,"given":"Md Faisal","family":"Kabir","sequence":"additional","affiliation":[{"name":"School of Science, Engineering, and Technology, Pennsylvania State University – Harrisburg, Middletown, PA, USA"}]}],"member":"263","reference":[{"key":"ref1","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"25","author":"Krizhevsky","year":"2012"},{"key":"ref2","first-page":"6105","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","volume-title":"Proc. Int. Conf. Mach. Learn.(PMLR)","author":"Tan","year":"2019"},{"key":"ref3","first-page":"1059","article-title":"High-performance large-scale image recognition without normalization","volume-title":"Proc. Int. Conf. Mach. Learn.(PMLR)","author":"Brock","year":"2021"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref5","first-page":"1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Dosovitskiy","year":"2021"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref10","first-page":"24261","article-title":"MLP-Mixer: An all-MLP architecture for vision","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Tolstikhin","year":"2021"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/WACV51458.2022.00367"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00090"},{"key":"ref13","first-page":"1","article-title":"AS-MLP: An axial shifted MLP architecture for vision","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Lian","year":"2022"},{"key":"ref14","first-page":"9204","article-title":"Pay attention to MLPs","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"34","author":"Liu","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-26351-4_28"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3145427"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206148"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.195"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10096453"},{"key":"ref21","article-title":"Mixing and shifting: Exploiting global and local dependencies in vision MLPs","author":"Zheng","year":"2022"},{"key":"ref22","article-title":"DeepViT: Towards deeper vision transformer","author":"Zhou","year":"2021"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52688.2022.01179"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00043"},{"key":"ref25","first-page":"1","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2021"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/tai.2023.3341879"},{"key":"ref27","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref28","article-title":"Gaussian error linear units (GELUs)","author":"Hendrycks","year":"2016"},{"key":"ref29","article-title":"EINOPS: Clear and reliable tensor manipulations with Einstein-like notation","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Rogozhnikov","year":"2022"},{"key":"ref30","article-title":"CrossFormer: A versatile vision transformer hinging on cross-scale attention","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Wang","year":"2022"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1016\/j.patter.2022.100520"},{"key":"ref32","first-page":"18613","article-title":"Rand-augment: Practical automated data augmentation with a reduced search space","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Cubuk","year":"2020"},{"key":"ref33","first-page":"1","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Zhang","year":"2018"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref37","article-title":"Learning multiple layers of features from tiny images","author":"Krizhevsky","year":"2009"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/219717.219748"},{"key":"ref39","article-title":"Automatic differentiation in pytorch","author":"Paszke","year":"2017"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref41","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"Loshchilov","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00026"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW59228.2023.00671"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01055"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/ICVGIP.2008.47"},{"key":"ref46","article-title":"Exponential moving average of weights in deep learning: Dynamics and benefits","volume-title":"IEEE Trans. Mach. Learn. Res.","author":"Morales-Brotons","year":"2023"}],"container-title":["IEEE Transactions on Artificial Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/9078688\/10720652\/10562192.pdf?arnumber=10562192","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,23]],"date-time":"2025-08-23T01:09:21Z","timestamp":1755911361000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10562192\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10]]},"references-count":46,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tai.2024.3415551","relation":{},"ISSN":["2691-4581"],"issn-type":[{"value":"2691-4581","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10]]}}}