{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T00:01:15Z","timestamp":1783641675836,"version":"3.55.0"},"reference-count":90,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"2","license":[{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,2,1]],"date-time":"2026-02-01T00:00:00Z","timestamp":1769904000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"JSPS KAKENHI","award":["25H01133"],"award-info":[{"award-number":["25H01133"]}]},{"name":"JSPS KAKENHI","award":["25K22112"],"award-info":[{"award-number":["25K22112"]}]},{"DOI":"10.13039\/501100001459","name":"Ministry of Education - Singapore","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001459","id-type":"DOI","asserted-by":"publisher"}]},{"name":"MOE AcRF Tier 2","award":["MOET2EP20221-0012"],"award-info":[{"award-number":["MOET2EP20221-0012"]}]},{"name":"MOE AcRF Tier 2","award":["MOE-T2EP20223-0002"],"award-info":[{"award-number":["MOE-T2EP20223-0002"]}]},{"name":"NTU S-Lab"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Pattern Anal. Mach. Intell."],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1109\/tpami.2025.3618174","type":"journal-article","created":{"date-parts":[[2025,10,7]],"date-time":"2025-10-07T17:41:53Z","timestamp":1759858913000},"page":"1778-1794","source":"Crossref","is-referenced-by-count":14,"title":["SMPLest-X: Ultimate Scaling for Expressive Human Pose and Shape Estimation"],"prefix":"10.1109","volume":"48","author":[{"ORCID":"https:\/\/orcid.org\/0009-0003-1914-7715","authenticated-orcid":false,"given":"Wanqi","family":"Yin","sequence":"first","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1810-3855","authenticated-orcid":false,"given":"Zhongang","family":"Cai","sequence":"additional","affiliation":[{"name":"SenseTime Research, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruisi","family":"Wang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3783-0679","authenticated-orcid":false,"given":"Ailing","family":"Zeng","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chen","family":"Wei","sequence":"additional","affiliation":[{"name":"SenseTime Research, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3998-5356","authenticated-orcid":false,"given":"Qingping","family":"Sun","sequence":"additional","affiliation":[{"name":"SenseTime Research, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Haiyi","family":"Mei","sequence":"additional","affiliation":[{"name":"SenseTime Research, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanjun","family":"Wang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hui En","family":"Pang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8212-715X","authenticated-orcid":false,"given":"Mingyuan","family":"Zhang","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6926-0538","authenticated-orcid":false,"given":"Lei","family":"Zhang","sequence":"additional","affiliation":[{"name":"International Digital Economy Academy (IDEA), Shenzhen, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5345-1591","authenticated-orcid":false,"given":"Chen Change","family":"Loy","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1280-069X","authenticated-orcid":false,"given":"Atsushi","family":"Yamashita","sequence":"additional","affiliation":[{"name":"The University of Tokyo, Tokyo, Japan"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0571-5924","authenticated-orcid":false,"given":"Lei","family":"Yang","sequence":"additional","affiliation":[{"name":"SenseTime Research, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4220-5958","authenticated-orcid":false,"given":"Ziwei","family":"Liu","sequence":"additional","affiliation":[{"name":"S-Lab, Nanyang Technological University, Singapore"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00843"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3450537"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01855"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_11"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02027"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01547"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01244"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00724"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01829"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01326"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_37"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2025.3528979"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/3dv53792.2021.00015"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00256"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.500"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00576"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-10602-1_48"},{"key":"ref21","first-page":"25268","article-title":"Motion-X: A large-scale 3D expressive whole-body human motion dataset","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Lin","year":"2023"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72754-2_2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01292"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2014.471"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2018.00024"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01345"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00237"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01085"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01112"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i2.16223"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00542"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00735"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01632"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00073"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72652-1_1"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00979"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00986"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00098"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2011.5995318"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00457"},{"key":"ref43","doi-asserted-by":"crossref","DOI":"10.5244\/C.34.20","article-title":"Synthetic training for accurate 3D human pose and shape estimation in the wild","volume-title":"Proc. Brit. Mach. Vis. Conf.","author":"Sengupta","year":"2020"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01122"},{"key":"ref45","first-page":"20","article-title":"Monocular expressive body regression through body-driven attention","volume-title":"Proc. Eur. Conf. Comput. Vis.","author":"Pavlakos","year":"2020"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00201"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00478"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00088"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747426"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3271691"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00257"},{"key":"ref52","article-title":"An image is worth 16x16 words: Transformers for image recognition at scale","volume-title":"Proc. Int. Conf. Learn. Representations","author":"Dosovitskiy","year":"2021"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00180"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73337-6_12"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.emnlp-main.256"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.15607\/rss.2025.xxi.010"},{"key":"ref57","article-title":"$\\pi$\u03c00. 5: A vision-language-action model with open-world generalization","author":"Black","year":"2025"},{"key":"ref58","first-page":"2165","article-title":"RT-2: Vision-language-action models transfer web knowledge to robotic control","volume-title":"Proc. Conf. Robot Learn.","author":"Zitkovich","year":"2023"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00499"},{"key":"ref60","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford","year":"2021"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.1810.04805"},{"key":"ref62","article-title":"Florence: A new foundation model for computer vision","author":"Yuan","year":"2021"},{"key":"ref63","article-title":"GPT-5 system card","year":"2025"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00371"},{"key":"ref65","article-title":"SAM 2: Segment anything in images and videos","volume-title":"Proc. 13th Int. Conf. Learn. Representations","author":"Ravi","year":"2025"},{"key":"ref66","article-title":"DINO: DETR with improved denoising anchor boxes for end-to-end object detection","volume-title":"Proc. 11th Int. Conf. Learn. Representations","author":"Zhang","year":"2023"},{"key":"ref67","article-title":"Dinov2: Learning robust visual features without supervision","author":"Oquab","year":"2024","journal-title":"Trans. Mach. Learn. Res."},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00987"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0688"},{"key":"ref70","article-title":"Dinov 3","author":"Sim\u00e9oni","year":"2025"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72970-6_3"},{"key":"ref72","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02104"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01711"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73235-5_12"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00297"},{"key":"ref76","first-page":"26034","article-title":"Benchmarking and analyzing 3D human pose and shape estimation beyond algorithms","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Pang","year":"2022"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00938"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.52202\/079017-4444"},{"key":"ref79","doi-asserted-by":"publisher","DOI":"10.1109\/3DV53792.2021.00015"},{"key":"ref80","doi-asserted-by":"publisher","DOI":"10.21105\/joss.00861"},{"key":"ref81","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00544"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3271691"},{"key":"ref83","article-title":"Openxrlab synthetic data rendering toolbox","author":"Contributors","year":"2023"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58565-5_33"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00363"},{"key":"ref88","article-title":"Openmmlab 3D human parametric model toolbox and benchmark","author":"Contributors","year":"2021"},{"key":"ref89","article-title":"EMO-X: Efficient multi-person pose and shape estimation in one-stage","author":"Jian","year":"2025"},{"key":"ref90","first-page":"38571","article-title":"Vitpose: Simple vision transformer baselines for human pose estimation","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","author":"Xu","year":"2022"}],"container-title":["IEEE Transactions on Pattern Analysis and Machine Intelligence"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/34\/11345188\/11195771.pdf?arnumber=11195771","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,12]],"date-time":"2026-01-12T22:00:59Z","timestamp":1768255259000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11195771\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,2]]},"references-count":90,"journal-issue":{"issue":"2"},"URL":"https:\/\/doi.org\/10.1109\/tpami.2025.3618174","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":[[2026,2]]}}}