{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:11:18Z","timestamp":1784268678230,"version":"3.55.0"},"reference-count":61,"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"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025,10,19]]},"DOI":"10.1109\/iccv51701.2025.00987","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10602-10611","source":"Crossref","is-referenced-by-count":3,"title":["X-Dancer: Expressive Music to Human Dance Video Generation"],"prefix":"10.1109","author":[{"given":"Zeyuan","family":"Chen","sequence":"first","affiliation":[{"name":"UC San Diego"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongyi","family":"Xu","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Guoxian","family":"Song","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"You","family":"Xie","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chenxu","family":"Zhang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xin","family":"Chen","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Chao","family":"Wang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Di","family":"Chang","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjie","family":"Luo","sequence":"additional","affiliation":[{"name":"ByteDance"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.1145\/3592458"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1145\/3550454.3555435"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2019\/276"},{"key":"ref4","article-title":"Stable video diffusion: Scaling latent video diffusion models to large datasets","author":"Blattmann","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02062"},{"key":"ref6","article-title":"Magicpose: Realistic human poses and facial expressions retargeting with identity-aware diffusion","author":"Chang","year":"2023","journal-title":"ICML"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00517"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00482"},{"key":"ref10","article-title":"Jong Wook Kim, Alec Radford, and Ilya Sutskever. Jukebox: A generative model for music","author":"Dhariwal","year":"2020","journal-title":"arxiv preprint arxiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00695"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00361"},{"key":"ref13","article-title":"Animatediff: Animate your personalized text-to-image diffusion models without specific tuning","author":"Guo","year":"2023","journal-title":"arxiv preprint arxiv"},{"key":"ref14","article-title":"Denoising diffusion probabilistic models","author":"Ho","year":"2020","journal-title":"arxiv preprint arxiv"},{"key":"ref15","article-title":"Fleet. Video diffusion models","volume":"35","author":"Ho","year":"2022","journal-title":"NeurIPS"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00779"},{"key":"ref17","article-title":"Animate anyone: Consistent and controllable image-to-video synthesis for character animation","volume-title":"arxiv preprint arxiv","author":"Hu","year":"2023"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.167"},{"key":"ref19","article-title":"Motiongpt: Human motion as a foreign language","author":"Jiang","year":"2023","journal-title":"NeurIPS"},{"key":"ref20","article-title":"Loopy: Taming audio-driven portrait avatar with long-term motion dependency","author":"Jiang","year":"2024","journal-title":"arxiv preprint arxiv"},{"key":"ref21","article-title":"Towards the automatic anime characters creation with generative adversarial networks","author":"Jin","year":"2017","journal-title":"arxiv preprint arxiv"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00838"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"ref24","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00939"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/icassp48485.2024.10447825"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"ref27","article-title":"Learning hierarchical cross-modal association for cospeech gesture generation","author":"Liu","year":"2022","journal-title":"CVPR"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20068-7_24"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02548"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01089"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"ref35","article-title":"Stefano Ermon, and Ben Poole. Score-based generative modeling through stochastic differential equations","author":"Song","year":"2020","journal-title":"arxiv preprint arxiv"},{"key":"ref36","article-title":"Human motion diffusion model","author":"Tevet","year":"2023","journal-title":"ICLR"},{"key":"ref37","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73010-8_15"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.00051"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref40","article-title":"Aist dance video database: Multi-genre, multi-dancer, and multi-camera database for dance information processing","author":"Tsuchida","year":"2019","journal-title":"ISMIR"},{"key":"ref41","article-title":"Towards accurate generative models of video: A new metric & challenges","author":"Unterthiner","year":"2018","journal-title":"arxiv preprint arxiv"},{"key":"ref42","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"NeurIPS"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72983-6_19"},{"key":"ref44","article-title":"Holistic-motion2d: Scalable whole-body human motion generation in 2d space","author":"Wang","journal-title":"arxiv preprint arxiv"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00739"},{"key":"ref46","article-title":"Music-todance generation with optimal transport","author":"Wu","year":"2021","journal-title":"arxiv preprint arxiv"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01011"},{"key":"ref48","article-title":"Hallo: Hierarchical audio-driven visual synthesis for portrait image animation","volume-title":"arxiv preprint arxiv","author":"Xu","year":"2024"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00147"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/WACV61041.2025.00502"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v35i12.17275"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00053"},{"key":"ref53","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00072"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/WACV57701.2024.00609"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01902"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73001-6_9"},{"key":"ref61","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\/11446036.pdf?arnumber=11446036","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T04:58:05Z","timestamp":1777611485000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11446036\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00987","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}