{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,5]],"date-time":"2026-03-05T15:37:44Z","timestamp":1772725064553,"version":"3.50.1"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"10","license":[{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2023,10,1]],"date-time":"2023-10-01T00:00:00Z","timestamp":1696118400000},"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":[[2023,10]]},"DOI":"10.1109\/tpami.2023.3285569","type":"journal-article","created":{"date-parts":[[2023,6,13]],"date-time":"2023-06-13T17:17:45Z","timestamp":1686676665000},"page":"12635-12649","source":"Crossref","is-referenced-by-count":30,"title":["Vicinity Vision Transformer"],"prefix":"10.1109","volume":"45","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-5409-1097","authenticated-orcid":false,"given":"Weixuan","family":"Sun","sequence":"first","affiliation":[{"name":"School of Computing, Australian National University, Canberra, ACT, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9856-0843","authenticated-orcid":false,"given":"Zhen","family":"Qin","sequence":"additional","affiliation":[{"name":"SenseTime research, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-5985-3976","authenticated-orcid":false,"given":"Hui","family":"Deng","sequence":"additional","affiliation":[{"name":"School of Electronics and Information, Northwestern Polytechnical University, Xi’an, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6467-4018","authenticated-orcid":false,"given":"Jianyuan","family":"Wang","sequence":"additional","affiliation":[{"name":"Visual Geometry Group, University of Oxford, Oxford, U.K."}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-7303-7594","authenticated-orcid":false,"given":"Yi","family":"Zhang","sequence":"additional","affiliation":[{"name":"SenseTime research, Shanghai, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4317-660X","authenticated-orcid":false,"given":"Kaihao","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computing, Australian National University, Canberra, ACT, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9343-9535","authenticated-orcid":false,"given":"Nick","family":"Barnes","sequence":"additional","affiliation":[{"name":"School of Computing, Australian National University, Canberra, ACT, Australia"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7366-2441","authenticated-orcid":false,"given":"Stan","family":"Birchfield","sequence":"additional","affiliation":[{"name":"Nvidia, Redmond, WA, USA"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9033-2724","authenticated-orcid":false,"given":"Lingpeng","family":"Kong","sequence":"additional","affiliation":[{"name":"University of Hong Kong, Hong Kong, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1404-3610","authenticated-orcid":false,"given":"Yiran","family":"Zhong","sequence":"additional","affiliation":[{"name":"Shanghai AI Lab, Shanghai, China"}]}],"member":"263","reference":[{"key":"ref13","first-page":"21297","article-title":"SOFT: Softmax-free transformer with linear complexity","author":"lu","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref57","article-title":"Focal self-attention for local-global interactions in vision transformers","author":"yang","year":"2021"},{"key":"ref12","article-title":"cosFormer: Rethinking softmax in attention","author":"zhen","year":"2022","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref56","article-title":"RegNet: Self-regulated network for image classification","author":"xu","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref59","article-title":"Learning multiple layers of features from tiny images","author":"krizhevsky","year":"2009"},{"key":"ref14","article-title":"Very deep convolutional networks for large-scale image recognition","author":"simonyan","year":"2014"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.74"},{"key":"ref11","first-page":"5156","article-title":"Transformers are RNNs: Fast autoregressive transformers with linear attention","author":"katharopoulos","year":"2020","journal-title":"Proc Int Conf Mach Learn"},{"key":"ref55","article-title":"Training data-efficient image transformers and distillation through attention","author":"touvron","year":"2021"},{"key":"ref10","article-title":"Rethinking attention with performers","author":"choromanski","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref16","article-title":"Imagenet classification with deep convolutional neural networks","author":"krizhevsky","year":"2012","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref18","first-page":"15908","article-title":"Transformer in transformer","author":"han","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref51","first-page":"1","article-title":"PVT V2: Improved baselines with pyramid vision transformer","volume":"8","author":"wang","year":"2022","journal-title":"Comput Vis Media"},{"key":"ref50","article-title":"Neighborhood attention transformer","author":"hassani","year":"2022"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/D19-1445"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/W19-4828"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW.2019.00246"},{"key":"ref47","volume":"40","author":"minkowski","year":"1910","journal-title":"Geometrie der Zahlen"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00884"},{"key":"ref41","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","author":"ali","year":"2021","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref44","article-title":"Do we really need explicit position encodings for vision transformers?","author":"chu","year":"2021"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00650"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00745"},{"key":"ref8","first-page":"14138","article-title":"Nyströmformer: A nystöm-based algorithm for approximating self-attention","author":"xiong","year":"2021","journal-title":"Proc AAAI Conf Artif Intell"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3530811"},{"key":"ref9","article-title":"Random feature attention","author":"peng","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref4","first-page":"14138","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","author":"dosovitskiy","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref3","article-title":"BERT: Pre-training of deep bidirectional transformers for language understanding","author":"devlin","year":"2018"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01196"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref40","first-page":"3531","article-title":"Efficient attention: Attention with linear complexities","author":"shen","year":"2021","journal-title":"Proc IEEE\/CVF Winter Conf Appl Comput Vis"},{"key":"ref35","article-title":"Generating long sequences with sparse transformers","author":"child","year":"2019"},{"key":"ref34","article-title":"Quadtree attention for vision transformers","author":"tang","year":"2022"},{"key":"ref37","article-title":"Reformer: The efficient transformer","author":"kitaev","year":"2020","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref36","article-title":"Longformer: The long-document transformer","author":"beltagy","year":"2020"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00813"},{"key":"ref33","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":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref2","first-page":"1877","article-title":"Language models are few-shot learners","author":"brown","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref1","article-title":"Attention is all you need","author":"vaswani","year":"2017","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref39","article-title":"Linformer: Self-attention with linear complexity","author":"wang","year":"2020"},{"key":"ref38","first-page":"6476","article-title":"SMYRF: Efficient attention using asymmetric clustering","author":"daras","year":"2020","journal-title":"Proc Adv Neural Inf Process Syst"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01270"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref25","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"zhu","year":"2021","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref20","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":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01044"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref65","first-page":"418","article-title":"Unified perceptual parsing for scene understanding","author":"xiao","year":"2018","journal-title":"Proc Eur Conf Comput Vis"},{"key":"ref28","first-page":"68","article-title":"Stand-alone self-attention in vision models","author":"ramachandran","year":"2019","journal-title":"Proc 33rd Int Conf Neural Inf Process Syst"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00356"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01009"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref62","article-title":"SGDR: Stochastic gradient descent with warm restarts","author":"loshchilov","year":"2017","journal-title":"Proc Int Conf Learn Representations"},{"key":"ref61","article-title":"Adam: A method for stochastic optimization","author":"kingma","year":"2015","journal-title":"Proc Int Conf Learn Representations"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10241246\/10149455.pdf?arnumber=10149455","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,6,6]],"date-time":"2024-06-06T17:13:13Z","timestamp":1717693993000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10149455\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10]]},"references-count":65,"journal-issue":{"issue":"10"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3285569","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":[[2023,10]]}}}