{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,12]],"date-time":"2026-07-12T02:40:23Z","timestamp":1783824023253,"version":"3.55.0"},"reference-count":65,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"5","license":[{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,5,1]],"date-time":"2024-05-01T00:00:00Z","timestamp":1714521600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"DOI":"10.13039\/501100000923","name":"Australian Research Council","doi-asserted-by":"publisher","award":["FL-170100117"],"award-info":[{"award-number":["FL-170100117"]}],"id":[{"id":"10.13039\/501100000923","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2024,5]]},"DOI":"10.1109\/tpami.2023.3347693","type":"journal-article","created":{"date-parts":[[2024,1,8]],"date-time":"2024-01-08T19:42:04Z","timestamp":1704742924000},"page":"3608-3624","source":"Crossref","is-referenced-by-count":73,"title":["Vision Transformer With Quadrangle Attention"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0060-0543","authenticated-orcid":false,"given":"Qiming","family":"Zhang","sequence":"first","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6595-7661","authenticated-orcid":false,"given":"Jing","family":"Zhang","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9931-5138","authenticated-orcid":false,"given":"Yufei","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7225-5449","authenticated-orcid":false,"given":"Dacheng","family":"Tao","sequence":"additional","affiliation":[{"name":"School of Computer Science, Faculty of Engineering, The University of Sydney, Sydney, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref4","first-page":"30008","article-title":"Focal attention for long-range interactions in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00761"},{"key":"ref8","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref9","first-page":"38571","article-title":"ViTPose: Simple vision transformer baselines for human pose estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_17"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20176"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref14","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"Huang","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i04.5862"},{"key":"ref16","first-page":"10347","article-title":"Training data-efficient image transformers; distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref17","first-page":"3965","article-title":"Coatnet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref18","article-title":"ConTNet: Why not use convolution and transformer at the same time?","author":"Yan","year":"2021"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-022-0274-8"},{"key":"ref21","doi-asserted-by":"crossref","DOI":"10.1109\/TPAMI.2023.3341806","article-title":"CrossFormer: A versatile vision transformer hinging on cross-scale attention","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Wang"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01175"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.89"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00953"},{"key":"ref25","article-title":"Deformable DETR: Deformable transformers for end-to-end object detection","author":"Zhu","year":"2021","journal-title":"Int. Conf. Learn. Representations"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475467"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_27"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref29","article-title":"Empirical evaluation of rectified activations in convolutional network","author":"Xu","year":"2015"},{"key":"ref30","article-title":"Conditional positional encodings for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chu"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-018-1140-0"},{"key":"ref36","article-title":"BEiT: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref39","article-title":"MMSegmentation: Openmmlab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00574"},{"key":"ref42","article-title":"Are we done with imageNet?","author":"Beyer","year":"2020"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01172"},{"key":"ref45","first-page":"15908","article-title":"Transformer in transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Han"},{"key":"ref46","first-page":"9355","article-title":"Twins: Revisiting the design of spatial attention in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chu"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01168"},{"key":"ref49","first-page":"7281","article-title":"HRFormer: High-resolution vision transformer for dense predict","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref50","article-title":"Multi-scale context aggregation by dilated convolutions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yu"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref52","article-title":"RegionViT: Regional-to-local attention for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref53","first-page":"20014","article-title":"XCiT: Cross-covariance image transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Ali"},{"key":"ref54","first-page":"15475","article-title":"ResT: An efficient transformer for visual recognition","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Zhang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref57","article-title":"Decoupled weight decay regularization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Loshchilov"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00668"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref60","article-title":"mixup: Beyond empirical risk minimization","author":"Zhang","year":"2017"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2956516"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.634"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref64","article-title":"Mmdetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref65","first-page":"30392","article-title":"Early convolutions help transformers see better","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xiao"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10384565.pdf?arnumber=10384565","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:46:35Z","timestamp":1725903995000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10384565\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":65,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3347693","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":[[2024,5]]}}}