{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T02:03:30Z","timestamp":1778810610240,"version":"3.51.4"},"reference-count":62,"publisher":"IEEE","license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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":["92467204,62472249"],"award-info":[{"award-number":["92467204,62472249"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.01338","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"14420-14430","source":"Crossref","is-referenced-by-count":1,"title":["Music-Aligned Holistic 3D Dance Generation via Hierarchical Motion Modeling"],"prefix":"10.1109","author":[{"given":"Xiaojie","family":"Li","sequence":"first","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ronghui","family":"Li","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shukai","family":"Fang","sequence":"additional","affiliation":[{"name":"ByteDance Games"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shuzhao","family":"Xie","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoyang","family":"Guo","sequence":"additional","affiliation":[{"name":"ByteDance Games"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiaqing","family":"Zhou","sequence":"additional","affiliation":[{"name":"ByteDance Games"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Junkun","family":"Peng","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhi","family":"Wang","sequence":"additional","affiliation":[{"name":"Shenzhen International Graduate School, Tsinghua University"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566606"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547797"},{"key":"ref3","volume-title":"Autodesk motionbuilder","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/83.480761"},{"key":"ref5","article-title":"Arkitscenes: A diverse real-world dataset for 3d indoor scene understanding using mobile rgb-d data","author":"Baruch","year":"2021","journal-title":"arXiv preprint"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2023.3288409"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459940"},{"key":"ref8","article-title":"Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arXiv preprint"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1037\/h0030377"},{"key":"ref10","volume-title":"Unreal engine 5","year":"2022"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.256"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1016\/j.evolhumbehav.2021.01.003"},{"key":"ref14","article-title":"Dancemeld: Unraveling dance phrases with hierarchical latent codes for music-to-dance synthesis","author":"Gao","year":"2023","journal-title":"arXiv preprint"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/18.720541"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413635"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref20","article-title":"Residual quantization with implicit neural codebooks","author":"Huijben","year":"2024","journal-title":"arXiv preprint"},{"key":"ref21","article-title":"Categorical reparameterization with gumbel-softmax","author":"Jang","year":"2016","journal-title":"arXiv preprint"},{"key":"ref22","article-title":"Motiongpt: Human motion as a foreign language","author":"Jiang","year":"2023","journal-title":"arXiv preprint"},{"key":"ref23","article-title":"Towards the automatic anime characters creation with generative adversarial networks","author":"Jin","year":"2017","journal-title":"arXiv preprint"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.3390\/inventions3040072"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i7.25996"},{"key":"ref26","article-title":"Making them dance","volume-title":"AAAI Fall Symposium: Aurally Informed Performance","author":"Woo Kim"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1145\/882262.882283"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/3DV50981.2020.00100"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00838"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00939"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818013"},{"key":"ref38","article-title":"Humantomato: Text-aligned whole-body motion generation","author":"Lu","year":"2023","journal-title":"arXiv preprint"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"ref43","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International Conference on Machine Learning","author":"Radford"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.52202\/068431-2643"},{"key":"ref46","first-page":"30119","article-title":"Facial expression recognition with adaptive frame rate based on multiple testing correction","volume-title":"Proceedings of the 40th International Conference on Machine Learning (ICML)","author":"Savchenko"},{"key":"ref47","volume-title":"Chingmu","year":"2022"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1111\/j.1467-8659.2006.00964.x"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.02032"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240526"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480570"},{"key":"ref54","article-title":"Neural discrete representation learning","volume":"30","author":"Van Den Oord","year":"2017","journal-title":"Advances in Neural Information Processing Systems"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2022.3226473"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1145\/3658137"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/TASLP.2021.3129994"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52733.2024.00072"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01415"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"},{"key":"ref62","doi-asserted-by":"publisher","DOI":"10.1145\/3485664"}],"event":{"name":"2025 IEEE\/CVF International Conference on Computer Vision (ICCV)","location":"Honolulu, HI, USA","start":{"date-parts":[[2025,10,19]]},"end":{"date-parts":[[2025,10,25]]}},"container-title":["2025 IEEE\/CVF International Conference on Computer Vision (ICCV)"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/11443115\/11443287\/11445987.pdf?arnumber=11445987","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:56:35Z","timestamp":1777611395000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11445987\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":62,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01338","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}