{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,12]],"date-time":"2026-05-12T17:04:29Z","timestamp":1778605469148,"version":"3.51.4"},"reference-count":69,"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"}],"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.2023.3268446","type":"journal-article","created":{"date-parts":[[2023,4,19]],"date-time":"2023-04-19T17:27:28Z","timestamp":1681925248000},"page":"10870-10882","source":"Crossref","is-referenced-by-count":143,"title":["Dual Vision Transformer"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7587-101X","authenticated-orcid":false,"given":"Ting","family":"Yao","sequence":"first","affiliation":[{"name":"HiDream.ai, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9603-1113","authenticated-orcid":false,"given":"Yehao","family":"Li","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4344-8898","authenticated-orcid":false,"given":"Yingwei","family":"Pan","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4219-781X","authenticated-orcid":false,"given":"Yu","family":"Wang","sequence":"additional","affiliation":[{"name":"JD.com, Beijing, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5241-0069","authenticated-orcid":false,"given":"Xiao-Ping","family":"Zhang","sequence":"additional","affiliation":[{"name":"Ryerson University, Toronto, ON, Canada"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2497-7732","authenticated-orcid":false,"given":"Tao","family":"Mei","sequence":"additional","affiliation":[{"name":"HiDream.ai, Beijing, China"}]}],"member":"263","reference":[{"key":"ref13","article-title":"PVTv2: Improved baselines with pyramid vision transformer","author":"wang","year":"2021"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref15","article-title":"RegionViT: Regional-to-local attention for vision transformers","author":"chen","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref14","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","author":"chu","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref58","first-page":"2286","article-title":"ConViT: Improving vision transformers with soft convolutional inductive biases","author":"ascoli","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref53","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":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01422"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_28"},{"key":"ref55","first-page":"1633","article-title":"Unified perceptual parsing for scene understanding","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00319"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2844175"},{"key":"ref17","first-page":"84","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref16","article-title":"VOLO: Vision outlooker for visual recognition","author":"yuan","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref18","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2015","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref51","first-page":"21002","article-title":"Generalized focal loss: Learning qualified and distributed bounding boxes for dense object detection","author":"li","year":"2020","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00978"},{"key":"ref46","first-page":"18590","article-title":"All tokens matter: Token labeling for training better vision transformers","author":"jiang","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref47","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2016"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref41","first-page":"740","article-title":"Microsoft COCO: Common objects in context","author":"lin","year":"2014","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref43","article-title":"Decoupled weight decay regularization","author":"loshchilov","year":"2017"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01098"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_19"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01746"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref3","doi-asserted-by":"crossref","first-page":"87","DOI":"10.1109\/TPAMI.2022.3152247","article-title":"A survey on vision transformer","volume":"45","author":"han","year":"2023","journal-title":"IEEE Trans Pattern Anal Mach Intell"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3183612"},{"key":"ref5","first-page":"5998","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref35","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","author":"touvron","year":"2021","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref36","article-title":"CMT: Convolutional neural networks meet vision transformers","author":"guo","year":"2021"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3164083"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00675"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref2","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.3047209"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_29"},{"key":"ref38","article-title":"Non-deep networks","author":"goyal","year":"2021"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2938758"},{"key":"ref68","article-title":"MaxViTT: Multi-axis vision transformer","author":"tu","year":"2022"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00236"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00060"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2020.2983686"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00020"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298594"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref63","article-title":"DeepViT: Towards deeper vision transformer","author":"zhou","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref66","first-page":"833","article-title":"Encoder-decoder with atrous separable convolution for semantic image segmentation","author":"chen","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.308"},{"key":"ref65","first-page":"5389","article-title":"Do imageNet classifiers generalize to imagenet?","author":"recht","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref27","first-page":"6105","article-title":"Efficientnet: Rethinking model scaling for convolutional neural networks","author":"tan","year":"2019","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref29","first-page":"68","article-title":"Stand-alone self-attention in vision models","author":"ramachandran","year":"2019","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref60","first-page":"4438","article-title":"Transformer in transformer","author":"han","year":"2021","journal-title":"Proc Int Conf Neural Inf Process"},{"key":"ref62","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"yang","year":"2021"},{"key":"ref61","article-title":"ResNeSt: Split-attention networks","author":"zhang","year":"2020"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10210213\/10105499.pdf?arnumber=10105499","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,8,28]],"date-time":"2023-08-28T17:55:49Z","timestamp":1693245349000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10105499\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,9,1]]},"references-count":69,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3268446","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]]}}}