{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T20:17:35Z","timestamp":1783455455511,"version":"3.55.0"},"reference-count":103,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"8","license":[{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,8,1]],"date-time":"2026-08-01T00:00:00Z","timestamp":1785542400000},"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":["62576342"],"award-info":[{"award-number":["62576342"]}],"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":["62425606"],"award-info":[{"award-number":["62425606"]}],"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":["62550062"],"award-info":[{"award-number":["62550062"]}],"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":["32341009"],"award-info":[{"award-number":["32341009"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["4252054"],"award-info":[{"award-number":["4252054"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100004826","name":"Beijing Natural Science Foundation","doi-asserted-by":"publisher","award":["L257008"],"award-info":[{"award-number":["L257008"]}],"id":[{"id":"10.13039\/501100004826","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20230484276"],"award-info":[{"award-number":["20230484276"]}],"id":[{"id":"10.13039\/501100005090","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100005090","name":"Beijing Nova Program","doi-asserted-by":"publisher","award":["20240484601"],"award-info":[{"award-number":["20240484601"]}],"id":[{"id":"10.13039\/501100005090","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":[[2026,8]]},"DOI":"10.1109\/tpami.2026.3683127","type":"journal-article","created":{"date-parts":[[2026,4,13]],"date-time":"2026-04-13T19:36:20Z","timestamp":1776108980000},"page":"9711-9729","source":"Crossref","is-referenced-by-count":0,"title":["Advancing Vision Transformer With Enhanced Spatial Priors"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-6115-5503","authenticated-orcid":false,"given":"Qihang","family":"Fan","sequence":"first","affiliation":[{"name":"MAIS & NLPR, Institude of Automation, Chinese Academic of Science, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5866-2283","authenticated-orcid":false,"given":"Huaibo","family":"Huang","sequence":"additional","affiliation":[{"name":"MAIS & NLPR, Institude of Automation, Chinese Academic of Science, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mingrui","family":"Chen","sequence":"additional","affiliation":[{"name":"MAIS & NLPR, Institude of Automation, Chinese Academic of Science, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9834-4087","authenticated-orcid":false,"given":"Hongmin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Artificial Intelligence, University of Science and Technology Beijing, Beijing, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3807-991X","authenticated-orcid":false,"given":"Ran","family":"He","sequence":"additional","affiliation":[{"name":"MAIS & NLPR, Institude of Automation, Chinese Academic of Science, Beijing, China"}],"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","article-title":"UniFormer: Unified transformer for efficient spatiotemporal representation learning","author":"Li","year":"2022"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00010"},{"key":"ref5","article-title":"Rethinking local perception in lightweight vision transformer","author":"Fan","year":"2023"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00009"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01186"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01169"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00599"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00539"},{"key":"ref11","article-title":"Retentive network: A successor to transformer for large language models","author":"Sun","year":"2023"},{"key":"ref12","article-title":"Train short, test long: Attention with linear biases enables input length extrapolation","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Press"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2326"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01181"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00475"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_5"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00995"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01167"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/iccv51701.2025.00383"},{"key":"ref20","article-title":"Vision transformer with sparse scan prior","author":"Fan","year":"2024"},{"key":"ref21","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":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"issue":"3","key":"ref23","first-page":"1","article-title":"PVTV2: Improved baselines with pyramid vision transformer","volume":"8","author":"Wang","year":"2022","journal-title":"Comput. Vis. Media"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0670"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00299"},{"key":"ref26","article-title":"RegionViT: Regional-to-local attention for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref27","article-title":"Visual parser: Representing part-whole hierarchies with transformers","author":"Sun","year":"2021"},{"key":"ref28","first-page":"4651","article-title":"Perceiver: General perception with iterative attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Jaegle"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01175"},{"key":"ref30","first-page":"7281","article-title":"HRFormer: High-resolution transformer for dense prediction","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01178"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_25"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3379457"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01170"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01385"},{"key":"ref36","article-title":"Not all patches are what you need: Expediting vision transformers via token reorganizations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liang"},{"key":"ref37","first-page":"13937","article-title":"DynamicViT: Efficient vision transformers with dynamic token sparsification","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Rao"},{"key":"ref38","article-title":"Token merging: Your ViT but faster","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bolya"},{"key":"ref39","article-title":"Vision transformer with super token sampling","author":"Huang"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00042"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00518"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1707"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1057"},{"key":"ref44","article-title":"CoAtNet: Marrying convolution and attention for all data sizes","author":"Dai","year":"2021"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1061"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref47","article-title":"Conditional positional encodings for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chu"},{"key":"ref48","article-title":"EVA-02: A visual representation for neon genesis","author":"Fang","year":"2023"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00548"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72973-7_8"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.127063"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_27"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0808"},{"key":"ref54","article-title":"MOAT: Alternating mobile convolution and attention brings strong vision models","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Yang"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1007\/s41095-023-0364-2"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3401450"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3600702"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01057"},{"key":"ref59","first-page":"12633","article-title":"Global context vision transformers","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Hatamizadeh"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00553"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01683"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00021"},{"key":"ref63","first-page":"10347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00041"},{"key":"ref65","first-page":"30008","article-title":"Focal self-attention for local-global interactions in vision transformers","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Yang"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00552"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4039"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01007"},{"key":"ref69","article-title":"Quadtree attention for vision transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Tang"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20053-3_28"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3341806"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3164083"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref75","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":"ref76","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00714"},{"key":"ref77","article-title":"Vision transformer adapter for dense predictions","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Chen"},{"key":"ref78","article-title":"Do ImageNet classifiers generalize to ImageNet","author":"Recht","year":"2019"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01501"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00823"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00359"},{"key":"ref83","article-title":"mixup: Beyond empirical risk minimization","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Zhang"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00612"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1137\/0330046"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46493-0_39"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20083-0_18"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0752"},{"key":"ref89","doi-asserted-by":"publisher","DOI":"10.52202\/068431-0304"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref91","article-title":"MMDetection: Open MMLab detection toolbox and benchmark","author":"Chen","year":"2019"},{"key":"ref92","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.322"},{"key":"ref93","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00644"},{"key":"ref94","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.324"},{"key":"ref95","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.544"},{"key":"ref96","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00656"},{"key":"ref97","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01228-1_26"},{"key":"ref98","article-title":"Mmsegmentation, an open source semantic segmentation toolbox","author":"Contributors","year":"2020"},{"key":"ref99","article-title":"Benchmarking neural network robustness to common corruptions and perturbations","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Hendrycks"},{"key":"ref100","first-page":"10506","article-title":"Learning robust global representations by penalizing local predictive power","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Wang"},{"key":"ref101","first-page":"5389","article-title":"Do ImageNet classifiers generalize to ImageNet","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Recht"},{"key":"ref102","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00069"},{"key":"ref103","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.acl-main.385"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11595778\/11479933.pdf?arnumber=11479933","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,7,7]],"date-time":"2026-07-07T19:44:31Z","timestamp":1783453471000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11479933\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8]]},"references-count":103,"journal-issue":{"issue":"8"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2026.3683127","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":[[2026,8]]}}}