{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,29]],"date-time":"2026-01-29T08:31:48Z","timestamp":1769675508491,"version":"3.49.0"},"reference-count":66,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"1","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-037"}],"funder":[{"name":"Guangdong Provincial Natural Science Foundation for Outstanding Youth Team Project","award":["2024B1515040010"],"award-info":[{"award-number":["2024B1515040010"]}]},{"name":"China National Key Research and Development Program","award":["2023YFE0202700"],"award-info":[{"award-number":["2023YFE0202700"]}]},{"name":"China National Key Research and Development Program","award":["2024YFB4709200"],"award-info":[{"award-number":["2024YFB4709200"]}]},{"name":"Key-Area Research and Development Program of Guangzhou City","award":["2023B01J0022"],"award-info":[{"award-number":["2023B01J0022"]}]},{"name":"NSFC Key Project","award":["U23A20391"],"award-info":[{"award-number":["U23A20391"]}]},{"name":"AI Singapore Programme through the National Research Foundation Singapore","award":["AISG3-GV-1623-011"],"award-info":[{"award-number":["AISG3-GV-1623-011"]}]},{"DOI":"10.13039\/501100001809","name":"Lee Kong Chian Fellowships","doi-asserted-by":"publisher","id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. Circuits Syst. Video Technol."],"published-print":{"date-parts":[[2026,1]]},"DOI":"10.1109\/tcsvt.2025.3595900","type":"journal-article","created":{"date-parts":[[2025,8,5]],"date-time":"2025-08-05T18:08:29Z","timestamp":1754417309000},"page":"817-831","source":"Crossref","is-referenced-by-count":0,"title":["StarPose: 3D Human Pose Estimation via Spatial-Temporal Autoregressive Diffusion"],"prefix":"10.1109","volume":"36","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5988-9816","authenticated-orcid":false,"given":"Haoxin","family":"Yang","sequence":"first","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-5332-7802","authenticated-orcid":false,"given":"Weihong","family":"Chen","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8006-3663","authenticated-orcid":false,"given":"Xuemiao","family":"Xu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4281-6214","authenticated-orcid":false,"given":"Cheng","family":"Xu","sequence":"additional","affiliation":[{"name":"Centre for Smart Health, The Hong Kong Polytechnic University, Hung Hom, Hong Kong"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9494-8948","authenticated-orcid":false,"given":"Peng","family":"Xiao","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, South China University of Technology, Guangzhou, China"}]},{"given":"Cuifeng","family":"Sun","sequence":"additional","affiliation":[{"name":"Cloud Computing Center, Chinese Academy of Sciences, Dongguan, China"}]},{"given":"Shaoyu","family":"Huang","sequence":"additional","affiliation":[{"name":"Guangzhou Yichuang Information Technology Company Ltd., Guangzhou, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3802-4644","authenticated-orcid":false,"given":"Shengfeng","family":"He","sequence":"additional","affiliation":[{"name":"School of Computing and Information Systems, Singapore Management University, Bras Basah, Singapore"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00069"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2024.3372451"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00934"},{"key":"ref4","first-page":"64318","article-title":"Occ3D: A large-scale 3D occupancy prediction benchmark for autonomous driving","volume-title":"Proc. Adv. Neural Inf. Process. Syst. (NeurIPS)","author":"Tian"},{"key":"ref5","first-page":"1114","article-title":"HUM3DIL: Semi-supervised multi-modal 3D human pose estimation for autonomous driving","volume-title":"Proc. Conf. Robot Learn. (CoRL)","volume":"205","author":"Zanfir"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00494"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00916"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3255186"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72649-1_23"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00742"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00060"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00113"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72655-2_18"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01253"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01356"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00464"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2023.3243400"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2024.110654"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/TASE.2023.3279928"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.109497"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2023.110116"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00677"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01145"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICME59968.2025.11210024"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3415348"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/s00371-024-03763-y"},{"key":"ref28","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. NIPS","author":"Ho"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2013.248"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2017.00064"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2010.11929"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2023\/65"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3286402"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01288"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20065-6_27"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01280"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547773"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2022.3141231"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475504"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3057267"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01365"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01464"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1109\/IROS55552.2023.10342204"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW60793.2023.00223"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3369757"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3441713"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2021.3126591"},{"key":"ref48","article-title":"Visual autoregressive modeling: Scalable image generation via next-scale prediction","author":"Tian","year":"2024","journal-title":"arXiv:2404.02905"},{"key":"ref49","volume-title":"Autoregressive model beats diffusion: Llama for scalable image generation","author":"Sun","year":"2024"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/cvprw67362.2025.00628"},{"key":"ref51","article-title":"ViD-GPT: Introducing GPT-style autoregressive generation in video diffusion models","author":"Gao","year":"2024","journal-title":"arXiv:2406.10981"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00723"},{"key":"ref53","article-title":"A tutorial on energy-based learning","author":"Lecun","year":"2006","journal-title":"Predicting Structured Data"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"ref55","first-page":"3609","article-title":"EGSDE: Unpaired image-to-image translation via energy-guided stochastic differential equations","volume-title":"Proc. NIPS","author":"Zhao"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01385"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01098"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01249-6_5"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00794"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00810"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01979"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3474085.3475219"},{"key":"ref63","article-title":"Denoising diffusion implicit models","volume-title":"Proc. Int. Conf. Learn. Represent. (ICLR)","author":"Song"},{"key":"ref64","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv:1412.6980"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/TIFS.2024.3449104"},{"key":"ref66","doi-asserted-by":"publisher","DOI":"10.1109\/WACV56688.2023.00294"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11365019\/11113338.pdf?arnumber=11113338","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,28]],"date-time":"2026-01-28T21:01:15Z","timestamp":1769634075000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11113338\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,1]]},"references-count":66,"journal-issue":{"issue":"1"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3595900","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,1]]}}}