{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,16]],"date-time":"2026-04-16T21:27:57Z","timestamp":1776374877154,"version":"3.51.2"},"reference-count":50,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"National Key Research and Development Program of China","award":["2018AAA0100400"],"award-info":[{"award-number":["2018AAA0100400"]}]},{"name":"CAAI-Huawei Open Fund"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,1,1]]},"DOI":"10.1109\/tpami.2022.3145427","type":"journal-article","created":{"date-parts":[[2022,1,25]],"date-time":"2022-01-25T20:38:22Z","timestamp":1643143102000},"page":"1328-1334","source":"Crossref","is-referenced-by-count":157,"title":["Vision Permutator: A Permutable MLP-Like Architecture for Visual Recognition"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8388-8708","authenticated-orcid":false,"given":"Qibin","family":"Hou","sequence":"first","affiliation":[{"name":"School of Computer Science, Nankai University, Tianjin, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8096-842X","authenticated-orcid":false,"given":"Zihang","family":"Jiang","sequence":"additional","affiliation":[{"name":"Department of Electrical and Computer Engineering, National University of Singapore, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2120-5588","authenticated-orcid":false,"given":"Li","family":"Yuan","sequence":"additional","affiliation":[{"name":"School of Electronic and Computer Engineering, Peking University, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5550-8758","authenticated-orcid":false,"given":"Ming-Ming","family":"Cheng","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nankai University, Tianjin, China"}]},{"given":"Shuicheng","family":"Yan","sequence":"additional","affiliation":[{"name":"Sea AI Lab, Singapore"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-0064","authenticated-orcid":false,"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"Sea AI Lab, Singapore"}]}],"member":"263","reference":[{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref38","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref33","article-title":"Beyond self-attention: External attention using two linear layers for visual tasks","author":"guo","year":"2021"},{"key":"ref32","article-title":"Pay attention to MLPs","author":"liu","year":"2021"},{"key":"ref31","article-title":"Axial attention in multidimensional transformers","author":"ho","year":"2019"},{"key":"ref30","article-title":"DeepViT: Towards deeper vision transformer","author":"zhou","year":"2021"},{"key":"ref37","article-title":"Pytorch image models","author":"wightman","year":"2019"},{"key":"ref36","first-page":"8026","article-title":"Pytorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019","journal-title":"Proc Adv Neural Informat Process Syst"},{"key":"ref35","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2020"},{"key":"ref34","first-page":"5998","article-title":"Attention is all you need","volume":"30","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Informat Process Syst"},{"key":"ref28","article-title":"Transformer in transformer","author":"han","year":"2021"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref2","article-title":"ResMLP: Feedforward networks for image classification with data-efficient training","author":"touvron","year":"2021"},{"key":"ref1","article-title":"MLP-Mixer: An all-MLP architecture for vision","author":"tolstikhin","year":"2021"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00338"},{"key":"ref22","first-page":"352","article-title":"A2-Nets: Double attention networks","author":"chen","year":"2018","journal-title":"Proc Adv Neural Informat Process Syst"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01011"},{"key":"ref24","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_7"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref25","article-title":"Refiner: Refining self-attention for vision transformers","author":"zhou","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref10","first-page":"1097","article-title":"ImageNet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref11","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref14","doi-asserted-by":"crossref","DOI":"10.5244\/C.30.87","article-title":"Wide residual networks","author":"zagoruyko","year":"2016"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref4","article-title":"EfficientNet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref6","article-title":"ResNeSt: Split-attention networks","author":"zhang","year":"2020"},{"key":"ref5","article-title":"High-performance large-scale image recognition without normalization","author":"brock","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref7","article-title":"Token labeling: Training a 85.4% top-1 accuracy vision transformer with 56m parameters on ImageNet","author":"jiang","year":"2021"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00914"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref46","article-title":"VOLO: Vision outlooker for visual recognition","author":"yuan","year":"2021"},{"key":"ref45","first-page":"5389","article-title":"Do ImageNet classifiers generalize to imagenet?","author":"recht","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00065"},{"key":"ref42","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref44","article-title":"Are we done with imagenet?","author":"beyer","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/9970415\/09693166.pdf?arnumber=9693166","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,12,26]],"date-time":"2022-12-26T19:15:29Z","timestamp":1672082129000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9693166\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,1,1]]},"references-count":50,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3145427","relation":{},"ISSN":["0162-8828","2160-9292","1939-3539"],"issn-type":[{"value":"0162-8828","type":"print"},{"value":"2160-9292","type":"electronic"},{"value":"1939-3539","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,1,1]]}}}