{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,6]],"date-time":"2026-06-06T16:57:27Z","timestamp":1780765047609,"version":"3.54.1"},"reference-count":59,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"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. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2022]]},"DOI":"10.1109\/tpami.2022.3208922","type":"journal-article","created":{"date-parts":[[2022,9,26]],"date-time":"2022-09-26T20:45:58Z","timestamp":1664225158000},"page":"1-9","source":"Crossref","is-referenced-by-count":12,"title":["Token Selection is a Simple Booster for Vision Transformers"],"prefix":"10.1109","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-4771-1796","authenticated-orcid":false,"given":"Daquan","family":"Zhou","sequence":"first","affiliation":[{"name":"Bytedance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8388-8708","authenticated-orcid":false,"given":"Qibin","family":"Hou","sequence":"additional","affiliation":[{"name":"School of Computer Science, Nankai University, Tianjin, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjie","family":"Yang","sequence":"additional","affiliation":[{"name":"ByteDance, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7850-1353","authenticated-orcid":false,"given":"Xiaojie","family":"Jin","sequence":"additional","affiliation":[{"name":"ByteDance, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6843-0064","authenticated-orcid":false,"given":"Jiashi","family":"Feng","sequence":"additional","affiliation":[{"name":"ByteDance, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref13","article-title":"Improving language understanding by generative pre-training","author":"radford","year":"2018"},{"key":"ref57","first-page":"801","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref12","article-title":"Language models are few-shot learners","author":"brown","year":"2020"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00406"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2014-80"},{"key":"ref59","article-title":"Electra: Pre-training text encoders as discriminators rather than generators","author":"clark","year":"2020"},{"key":"ref14","article-title":"Recurrent neural network for text classification with multi-task learning","author":"liu","year":"2016"},{"key":"ref58","article-title":"Stand-alone self-attention in vision models","author":"ramachandran","year":"2019"},{"key":"ref53","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","author":"touvron","year":"2021"},{"key":"ref52","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"yang","year":"2021"},{"key":"ref11","article-title":"A survey on visual transformer","author":"han","year":"2020"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.660"},{"key":"ref10","article-title":"Transformers in vision: A survey","author":"khan","year":"2021"},{"key":"ref54","first-page":"418","article-title":"Unified perceptual parsing for scene understanding","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00583"},{"key":"ref16","article-title":"Pre-trained image processing transformer","author":"chen","year":"2020"},{"key":"ref19","first-page":"213","article-title":"End-to-end object detection with transformers","author":"carion","year":"2020","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref18","article-title":"DeepViT: Towards deeper vision transformer","author":"zhou","year":"2021"},{"key":"ref51","article-title":"Cswin transformer: A general vision transformer backbone with cross-shaped windows","author":"dong","year":"2021"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref46","article-title":"Are we done with imagenet?","author":"beyer","year":"2020"},{"key":"ref45","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":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref47","article-title":"Imagenet-21k pretraining for the masses","author":"ridnik","year":"2021"},{"key":"ref42","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016"},{"key":"ref41","article-title":"PyTorch: An imperative style, high-performance deep learning library","author":"paszke","year":"2019"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref43","article-title":"mixup: Beyond empirical risk minimization","author":"zhang","year":"2017"},{"key":"ref49","article-title":"Transformer in transformer","author":"han","year":"2021"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref3","article-title":"Attention is all you need","author":"vaswani","year":"2017"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_38"},{"key":"ref40","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref35","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":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref36","article-title":"Focal modulation networks","author":"yang","year":"2022"},{"key":"ref31","article-title":"MobileNets: Efficient convolutional neural networks for mobile vision applications","author":"howard","year":"2017"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00474"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref2","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2020"},{"key":"ref1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020"},{"key":"ref39","article-title":"GLUE: A multi-task benchmark and analysis platform for natural language understanding","author":"wang","year":"2019","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref38","article-title":"Token labeling: Training a 85.4% top-1 accuracy vision transformer with 56M parameters on imageNet","author":"jiang","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58517-4_31"},{"key":"ref23","article-title":"End-to-end video instance segmentation with transformers","author":"wang","year":"2020"},{"key":"ref26","article-title":"Point transformer","author":"zhao","year":"2020"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00911"},{"key":"ref20","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2020"},{"key":"ref22","article-title":"End-to-end object detection with adaptive clustering transformer","author":"zheng","year":"2020"},{"key":"ref21","article-title":"UP-DETR: Unsupervised pre-training for object detection with transformers","author":"dai","year":"2020"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref27","article-title":"PCT: Point cloud transformer","author":"guo","year":"2020"},{"key":"ref29","article-title":"LocalViT: Bringing locality to vision transformers","author":"li","year":"2021"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/4359286\/09903081.pdf?arnumber=9903081","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,10,4]],"date-time":"2023-10-04T15:24:06Z","timestamp":1696433046000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/9903081\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"references-count":59,"URL":"https:\/\/doi.org\/10.1109\/tpami.2022.3208922","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":[[2022]]}}}