{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,6]],"date-time":"2026-05-06T15:09:21Z","timestamp":1778080161957,"version":"3.51.4"},"reference-count":52,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","issue":"9","license":[{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,9,1]],"date-time":"2025-09-01T00:00:00Z","timestamp":1756684800000},"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":["92470202"],"award-info":[{"award-number":["92470202"]}],"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":["U21A20471"],"award-info":[{"award-number":["U21A20471"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"National Key Research and Development Program of China","award":["2023YFA1008503"],"award-info":[{"award-number":["2023YFA1008503"]}]},{"DOI":"10.13039\/501100001809","name":"Guangdong NSF Project","doi-asserted-by":"publisher","award":["2023B1515040025"],"award-info":[{"award-number":["2023B1515040025"]}],"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":[[2025,9]]},"DOI":"10.1109\/tcsvt.2025.3556868","type":"journal-article","created":{"date-parts":[[2025,4,1]],"date-time":"2025-04-01T18:07:43Z","timestamp":1743530863000},"page":"9205-9217","source":"Crossref","is-referenced-by-count":3,"title":["Progressive Human Motion Generation Based on Text and Few Motion Frames"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-8125-8024","authenticated-orcid":false,"given":"Ling-An","family":"Zeng","sequence":"first","affiliation":[{"name":"School of Artificial Intelligence, Sun Yat-sen University, Zhuhai, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0752-8508","authenticated-orcid":false,"given":"Gaojie","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-7969-3190","authenticated-orcid":false,"given":"Ancong","family":"Wu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-2678-5373","authenticated-orcid":false,"given":"Jian-Fang","family":"Hu","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8327-0003","authenticated-orcid":false,"given":"Wei-Shi","family":"Zheng","sequence":"additional","affiliation":[{"name":"School of Computer Science and Engineering, Sun Yat-sen University, Guangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3351601"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3427488"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_13"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref12","first-page":"20,067","article-title":"MotionGPT: Human motion as a foreign language","volume-title":"Proc. 37th Conf. Neural Inf. Process. Syst.","author":"Jiang"},{"key":"ref13","first-page":"32,939","article-title":"HumanTOMATO: Text-aligned whole-body motion generation","volume-title":"Proc. 41st Int. Conf. Mach. Learn.","author":"Lu"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00135"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00094"},{"key":"ref16","first-page":"6,309","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Den Oord"},{"key":"ref17","first-page":"1","article-title":"Human motion diffusion model","volume-title":"Proc. 11th Int. Conf. Learn. Represent.","author":"Tevet"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33062"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00051"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_2"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73668-1_7"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2020.2973374"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3436900"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72992-8_8"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72661-3_20"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"ref30","first-page":"1","article-title":"Human motion diffusion as a generative prior","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Shafir"},{"key":"ref31","first-page":"1","article-title":"OmniControl: Control any joint at any time for human motion generation","volume-title":"Proc. 12th Int. Conf. Learn. Represent.","author":"Xie"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72913-3_3"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392480"},{"key":"ref35","article-title":"Single-shot motion completion with transformer","author":"Duan","year":"2021","journal-title":"arXiv:2103.00776"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530157"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2018.2867934"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591514"},{"key":"ref39","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Sohl-Dickstein"},{"key":"ref40","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"33","author":"Ho"},{"key":"ref41","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv:2207.12598"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1145\/3610548.3618185"},{"key":"ref45","first-page":"49,842","article-title":"UniPC: A unified predictor-corrector framework for fast sampling of diffusion models","volume-title":"Proc. NeurIPS","author":"Zhao"},{"key":"ref46","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","author":"Radford"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/3DV.2019.00084"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1016\/j.measurement.2020.108253"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1007\/s11432-020-3073-5"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1002\/adc2.63"}],"container-title":["IEEE Transactions on Circuits and Systems for Video Technology"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/76\/11154820\/10947104.pdf?arnumber=10947104","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,1,5]],"date-time":"2026-01-05T18:42:28Z","timestamp":1767638548000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/10947104\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9]]},"references-count":52,"journal-issue":{"issue":"9"},"URL":"https:\/\/doi.org\/10.1109\/tcsvt.2025.3556868","relation":{},"ISSN":["1051-8215","1558-2205"],"issn-type":[{"value":"1051-8215","type":"print"},{"value":"1558-2205","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9]]}}}