{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,18]],"date-time":"2026-07-18T18:30:35Z","timestamp":1784399435003,"version":"3.55.0"},"reference-count":84,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2024,2,1]],"date-time":"2024-02-01T00:00:00Z","timestamp":1706745600000},"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":[[2024,2]]},"DOI":"10.1109\/tpami.2023.3330016","type":"journal-article","created":{"date-parts":[[2023,11,3]],"date-time":"2023-11-03T18:01:07Z","timestamp":1699034467000},"page":"1212-1230","source":"Crossref","is-referenced-by-count":131,"title":["ViTPose++: Vision Transformer for Generic Body Pose Estimation"],"prefix":"10.1109","volume":"46","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9931-5138","authenticated-orcid":false,"given":"Yufei","family":"Xu","sequence":"first","affiliation":[{"name":"Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, 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":"Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0060-0543","authenticated-orcid":false,"given":"Qiming","family":"Zhang","sequence":"additional","affiliation":[{"name":"Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, 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":"Sydney AI Centre and the School of Computer Science, Faculty of Engineering, University of Sydney, Darlington, NSW, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/JIOT.2020.3039359"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-023-01842-6"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.214"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01231-1_29"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_3"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58520-4_36"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00198"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01112"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01159"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_5"},{"key":"ref16","article-title":"HRFormer: High-resolution transformer for dense prediction","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Yuan"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref20","article-title":"AP-10K: A benchmark for animal pose estimation in the wild","volume-title":"Proc. 35th Conf. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Yu"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.5244\/C.30.109"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-022-01739-w"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.395"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46484-8_29"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00584"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01153"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2022.3222784"},{"key":"ref30","first-page":"4971","article-title":"SegViT: Semantic segmentation with plain vision transformers","volume-title":"Proc. Int. Conf. Neural Inf. Process. Sys.","author":"Zhang"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20077-9_17"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.533"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46466-4_3"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2929257"},{"key":"ref35","first-page":"2274","article-title":"Associative embedding: End-to-end learning for joint detection and grouping","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Newell"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01225"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00705"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00543"},{"key":"ref39","first-page":"28522","article-title":"ViTAE: Vision transformer advanced by exploring intrinsic inductive bias","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref40","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":"ref41","article-title":"ELSA: Enhanced local self-attention for vision transformer","author":"Zhou","year":"2021"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00061"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i3.20150"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19806-9_27"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2009.5206848"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00950"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19827-4_28"},{"key":"ref48","article-title":"BEit: BERT pre-training of image transformers","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Bao"},{"key":"ref49","article-title":"On the opportunities and risks of foundation models","author":"Bommasani","year":"2021"},{"key":"ref50","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref51","first-page":"23716","article-title":"Flamingo: A visual language model for few-shot learning","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Alayrac"},{"key":"ref52","article-title":"Outrageously large neural networks: The sparsely-gated mixture-of-experts layer","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Shazeer"},{"key":"ref53","first-page":"2664","article-title":"Uni-perceiver-MoE: Learning sparse generalist models with conditional MoEs","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Zhu"},{"key":"ref54","first-page":"38571","article-title":"ViTPose: Simple vision transformer baselines for human pose estimation","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Xu"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00098"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/icme.2019.00256"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_12"},{"key":"ref58","first-page":"17301","article-title":"APT-36K: A large-scale benchmark for animal pose estimation and tracking","volume-title":"Proc. Neural Inf. Process. Syst. Datasets Benchmarks Track","author":"Yang"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.5555\/3045118.3045167"},{"key":"ref60","article-title":"Deep learning using rectified linear units (ReLU)","author":"Agarap","year":"2018"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01482-8"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.207"},{"key":"ref63","first-page":"24261","article-title":"MLP-mixer: An all-MLP architecture for vision","volume-title":"Proc. Int. Conf. Neural Inf. Process. Syst.","author":"Tolstikhin"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00476"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1145\/3560815"},{"key":"ref66","article-title":"Distilling the knowledge in a neural network","author":"Hinton","year":"2015"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-021-01453-z"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.acl-short.8"},{"key":"ref69","article-title":"Towards impartial multi-task learning","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Liu"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-63416-2_584"},{"key":"ref72","article-title":"Open MMLab pose estimation toolbox and benchmark","year":"2020"},{"key":"ref73","article-title":"On the convergence of adam and beyond","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Reddi"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00574"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.90"},{"key":"ref76","first-page":"10 347","article-title":"Training data-efficient image transformers & distillation through attention","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Touvron"},{"key":"ref77","article-title":"Rethinking on multi-stage networks for human pose estimation","author":"Li","year":"2019"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01391"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00712"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58580-8_27"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00524"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00311"},{"key":"ref83","article-title":"Cascade feature aggregation for human pose estimation","author":"Su","year":"2019"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58529-7_36"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx7\/34\/10384454\/10308645.pdf?arnumber=10308645","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,9]],"date-time":"2024-09-09T17:46:21Z","timestamp":1725903981000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10308645\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,2]]},"references-count":84,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2023.3330016","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":[[2024,2]]}}}