{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T15:18:08Z","timestamp":1780413488661,"version":"3.54.1"},"reference-count":88,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,9,1]],"date-time":"2023-09-01T00:00:00Z","timestamp":1693526400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U21A20471"],"award-info":[{"award-number":["U21A20471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1911401"],"award-info":[{"award-number":["U1911401"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["U1811461"],"award-info":[{"award-number":["U1811461"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong NSF","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}]},{"name":"Guangdong NSF","award":["2020B1515120085"],"award-info":[{"award-number":["2020B1515120085"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2023,9,1]]},"DOI":"10.1109\/tpami.2023.3265499","type":"journal-article","created":{"date-parts":[[2023,4,7]],"date-time":"2023-04-07T17:29:11Z","timestamp":1680888551000},"page":"11120-11135","source":"Crossref","is-referenced-by-count":34,"title":["PSLT: A Light-Weight Vision Transformer With Ladder Self-Attention and Progressive Shift"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0752-8508","authenticated-orcid":false,"given":"Gaojie","family":"Wu","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5315-3375","authenticated-orcid":false,"given":"Yutong","family":"Lu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7252-5047","authenticated-orcid":false,"given":"Qi","family":"Tian","sequence":"additional","affiliation":[{"name":"Cloud and AI BU, Huawei, Shenzhen, Guangdong, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"CMT: Convolutional neural networks meet vision transformers","author":"guo","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref12","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00020"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref59","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref53","first-page":"5389","article-title":"Do imagenet classifiers generalize to imagenet?","author":"recht","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.133"},{"key":"ref11","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref55","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017"},{"key":"ref10","first-page":"30 392","article-title":"Early convolutions help transformers see better","author":"xiao","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref17","doi-asserted-by":"crossref","DOI":"10.1007\/978-3-031-20083-0_18","article-title":"EdgeViTs: Competing light-weight CNNs on mobile devices with vision transformers","author":"pan","year":"2022"},{"key":"ref16","article-title":"CrossFormer: A versatile vision transformer based on cross-scale attention","author":"wang","year":"2021"},{"key":"ref19","article-title":"MobileViT: Light-weight, general-purpose, and mobile-friendly vision transformer","author":"mehta","year":"2021"},{"key":"ref18","article-title":"EdgeNeXt: Efficiently amalgamated CNN-transformer architecture for mobile vision applications","author":"maaz","year":"2022"},{"key":"ref51","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref46","first-page":"15 475","article-title":"ResT: An efficient transformer for visual recognition","author":"zhang","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref45","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","author":"chu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref48","article-title":"MPViT: Multi-path vision transformer for dense prediction","author":"lee","year":"2021"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00048"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01225-0_30"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref88","first-page":"8634","article-title":"Evaluating machine accuracy on imageNet","author":"shankar","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref43","first-page":"12992","article-title":"Glance-and-gaze vision transformer","author":"yu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref87","article-title":"In defense of the triplet loss for person re-identification","author":"hermans","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"ref8","doi-asserted-by":"crossref","DOI":"10.5244\/C.30.87","article-title":"Wide residual networks","author":"zagoruyko","year":"2016"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.243"},{"key":"ref9","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","author":"dai","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref6","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00666"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00380"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01474"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00385"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2019.00190"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref79","first-page":"418","article-title":"Unified perceptual parsing for scene understanding","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref34","article-title":"EfficientFormer: Vision transformers at mobilenet speed","author":"li","year":"2022"},{"key":"ref78","article-title":"Multi-scale context aggregation by dilated convolutions","author":"yu","year":"2015"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01204"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref31","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref75","first-page":"249","article-title":"Understanding the difficulty of training deep feedforward neural networks","author":"glorot","year":"2010","journal-title":"Proc 13th Int Conf Artif Intell Statist"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref33","article-title":"Volo: Vision outlooker for visual recognition","author":"yuan","year":"2021"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00044"},{"key":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-015-0816-y"},{"key":"ref1","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":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref38","article-title":"Mobile-former: Bridging mobilenet and transformer","author":"chen","year":"2021"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR56361.2022.9956379"},{"key":"ref70","first-page":"1","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2012","journal-title":"Univ Toronto"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref24","first-page":"1","article-title":"Neural architecture search with reinforcement learning","author":"zoph","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01054"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00716"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01206"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_32"},{"key":"ref69","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref20","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref64","article-title":"Shunted self-attention via multi-scale token aggregation","author":"ren","year":"2021"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00983"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00140"},{"key":"ref66","article-title":"MetaFormer is actually what you need for vision","author":"yu","year":"2021"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref65","article-title":"Global context vision transformers","author":"hatamizadeh","year":"2022"},{"key":"ref28","first-page":"1","article-title":"DARTS: Differentiable architecture search","author":"liu","year":"2019","journal-title":"Proc 7th Int Conf Learn Representations"},{"key":"ref27","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Int Conf Mach Learn"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01214"},{"key":"ref60","article-title":"Hrformer: High-resolution transformer for dense prediction","author":"yuan","year":"2021"},{"key":"ref62","article-title":"ConTNet: Why not use convolution and transformer at the same time?","author":"yan","year":"2021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58555-6_46"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10210213\/10097573.pdf?arnumber=10097573","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T17:55:29Z","timestamp":1693245329000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10097573\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":88,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3265499","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":[[2023,9,1]]}}}