{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,11]],"date-time":"2026-04-11T11:51:47Z","timestamp":1775908307202,"version":"3.50.1"},"reference-count":58,"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\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["62303406"],"award-info":[{"award-number":["62303406"]}],"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":["62273303"],"award-info":[{"award-number":["62273303"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Key R&D Program of Zhejiang Province, China","award":["2023C01135"],"award-info":[{"award-number":["2023C01135"]}]},{"name":"Key R&D Program of Zhejiang Province, China","award":["2021C01012"],"award-info":[{"award-number":["2021C01012"]}]},{"name":"Yongjiang Talent Introduction Programme","award":["2023A-194-G"],"award-info":[{"award-number":["2023A-194-G"]}]}],"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.2023.3341806","type":"journal-article","created":{"date-parts":[[2023,12,19]],"date-time":"2023-12-19T19:26:43Z","timestamp":1703014003000},"page":"3123-3136","source":"Crossref","is-referenced-by-count":208,"title":["CrossFormer++: A Versatile Vision Transformer Hinging on Cross-Scale Attention"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6399-292X","authenticated-orcid":false,"given":"Wenxiao","family":"Wang","sequence":"first","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-3265-3966","authenticated-orcid":false,"given":"Wei","family":"Chen","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2848-6079","authenticated-orcid":false,"given":"Qibo","family":"Qiu","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6148-9709","authenticated-orcid":false,"given":"Long","family":"Chen","sequence":"additional","affiliation":[{"name":"Hong Kong University of Science and Technology, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4494-193X","authenticated-orcid":false,"given":"Boxi","family":"Wu","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0330-6406","authenticated-orcid":false,"given":"Binbin","family":"Lin","sequence":"additional","affiliation":[{"name":"Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0001-9107-2354","authenticated-orcid":false,"given":"Xiaofei","family":"He","sequence":"additional","affiliation":[{"name":"State Key Lab of CAD&CG, Zhejiang University, Hangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3865-8145","authenticated-orcid":false,"given":"Wei","family":"Liu","sequence":"additional","affiliation":[{"name":"Data Platform, Tencent, Shenzhen, China"}]}],"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","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/icme52920.2022.9859720"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/N18-2074"},{"key":"ref7","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":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00060"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3206108"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.2104.10858"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref13","first-page":"1298","article-title":"Data2vec: A general framework for self-supervised learning in speech, vision and language","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Baevski"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01852-4"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00951"},{"key":"ref16","article-title":"DINOv2: Learning robust visual features without supervision","author":"Oquab","year":"2023"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/iccv48922.2021.00043"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref21","article-title":"Conditional positional encodings for vision transformers","author":"Chu","year":"2021"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00028"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01205"},{"key":"ref24","first-page":"8714","article-title":"Searching the search space of vision transformer","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Chen"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00008"},{"key":"ref26","article-title":"Layer normalization","author":"Ba","year":"2016"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.5555\/3104322.3104425"},{"key":"ref28","first-page":"12 116","article-title":"Do vision transformers see like convolutional neural networks?","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Raghu"},{"key":"ref29","article-title":"Transformer in transformer","author":"Han","year":"2021"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref31","article-title":"Twins: Revisiting spatial attention design in vision transformers","author":"Chu","year":"2021"},{"key":"ref32","article-title":"Aggregating nested transformers","author":"Zhang","year":"2021"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref34","article-title":"Rest: An efficient transformer for visual recognition","author":"Zhang","year":"2021"},{"key":"ref35","article-title":"Transformer in convolutional neural networks","author":"Liu","year":"2021"},{"key":"ref36","article-title":"Shuffle transformer: Rethinking spatial shuffle for vision transformer","author":"Huang","year":"2021"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01625"},{"key":"ref38","article-title":"RegionViT: Regional-to-local attention for vision transformers","author":"Chen","year":"2021"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref43","first-page":"3965","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","volume-title":"Proc. Annu. Conf. Neural Inf. Process. Syst.","author":"Dai"},{"key":"ref44","article-title":"Adam: A method for stochastic optimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Kingma"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref46","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v34i07.7000"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref51","article-title":"MMDetection: OpenMMLab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2018.2858826"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref55","first-page":"5122","article-title":"Scene parsing through ADE20 K dataset","volume-title":"Proc. Conf. Comput. Vis. Pattern Recognit.","author":"Zhou"},{"key":"ref56","article-title":"MMSegmentation: OpenMMLab semantic segmentation toolbox and benchmark","author":"Contributors","year":"2020"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10490207\/10366193.pdf?arnumber=10366193","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:47:07Z","timestamp":1725904027000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10366193\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,5]]},"references-count":58,"journal-issue":{"issue":"5"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3341806","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]]}}}