{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T03:31:25Z","timestamp":1777865485117,"version":"3.51.4"},"reference-count":74,"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\/501100012166","name":"National Key R&D Program of China","doi-asserted-by":"publisher","award":["2024YFB2809102,2022ZD0160201"],"award-info":[{"award-number":["2024YFB2809102,2022ZD0160201"]}],"id":[{"id":"10.13039\/501100012166","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"NSFC","doi-asserted-by":"publisher","award":["62402427,U24B20154"],"award-info":[{"award-number":["62402427,U24B20154"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"Natural Science Foundation of China","doi-asserted-by":"publisher","award":["LR25F020003"],"award-info":[{"award-number":["LR25F020003"]}],"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\/iccv51701.2025.00940","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"10086-10096","source":"Crossref","is-referenced-by-count":4,"title":["MotionStreamer: Streaming Motion Generation via Diffusion-Based Autoregressive Model in Causal Latent Space"],"prefix":"10.1109","author":[{"given":"Lixing","family":"Xiao","sequence":"first","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunlin","family":"Lu","sequence":"additional","affiliation":[{"name":"The Chinese University of Hong Kong (Shenzhen)"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huaijin","family":"Pi","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ke","family":"Fan","sequence":"additional","affiliation":[{"name":"Shanghai Jiao Tong University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Liang","family":"Pan","sequence":"additional","affiliation":[{"name":"The University of Hong Kong"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yueer","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyong","family":"Feng","sequence":"additional","affiliation":[{"name":"DeepGlint"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaowei","family":"Zhou","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sida","family":"Peng","sequence":"additional","affiliation":[{"name":"Zhejiang University"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jingbo","family":"Wang","sequence":"additional","affiliation":[{"name":"Shanghai AI Laboratory"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2022.findings-acl.58"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"ref3","first-page":"2","volume-title":"Multidiffusion: Fusing diffusion paths for controlled image generation.","author":"Bar-Tal","year":"2023"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00051"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46454-1_34"},{"key":"ref6","first-page":"3","article-title":"Ready-to-react: Online reaction policy for two-character interaction generation","author":"Cen","year":"2025","journal-title":"ICLR"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01103"},{"key":"ref8","first-page":"2","article-title":"Dancetogether! identity-preserving multi-person interactive video generation","author":"Chen","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"ref10","first-page":"2","article-title":"Motionllm: Understanding human behaviors from human motions and videos","author":"Chen","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657440"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref14","doi-asserted-by":"publisher","DOI":"10.18653\/vl\/N19-142"},{"key":"ref15","first-page":"3","article-title":"GitHub discussion","year":"2023","journal-title":"rotation discussion."},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73242-3_6"},{"key":"ref17","first-page":"2","article-title":"Textual decomposition then sub-motion-space scattering for open-vocabulary motion generation","author":"Fan","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01239"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19833-5_34"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/2020.findings-emnlp.379"},{"key":"ref23","first-page":"5","article-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium","volume":"30","author":"Heusel","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref24","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2023.3259183"},{"key":"ref26","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.02113"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2025.3542631"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref29","volume-title":"Auto-encoding variational bayes","author":"Kingma","year":"2013"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01123"},{"key":"ref32","first-page":"2","article-title":"Dispose: Disentangling pose guidance for controllable human image animation","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref33","first-page":"5","article-title":"Autoregressive image generation without vector quantization","author":"Li","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref34","first-page":"851","article-title":"Smpl: A skinned multiperson linear model","volume":"2","author":"Loper","year":"2023","journal-title":"Seminal Graphics Papers: Pushing the Boundaries"},{"key":"ref35","first-page":"2","article-title":"Humantomato: Text-aligned whole-body motion generation","author":"Lu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref36","first-page":"2","article-title":"Scamo: Exploring the scaling law in autoregressive motion generation model","author":"Lu","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref37","first-page":"8","article-title":"Autoregressive speech synthesis without vector quantization","volume":"5","author":"Meng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref38","first-page":"2","article-title":"Rethinking diffusion for text-driven human motion generation","author":"Meng","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref39","first-page":"2","article-title":"Absolute coordinates make motion generation easy","author":"Meng","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00506"},{"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","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01383"},{"key":"ref44","article-title":"Motion-2-to-3: Leveraging 2d motion data to boost 3d motion generation","author":"Pi","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref45","first-page":"2","article-title":"Coda: Coordinated diffusion noise optimization for wholebody manipulation of articulated objects","author":"Pi","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref49","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"International conference on machine learning","volume":"8","author":"Radford"},{"issue":"140","key":"ref50","first-page":"1","article-title":"Exploring the limits of transfer learning with a unified text-to-text transformer","volume":"21","author":"Raffel","year":"2020","journal-title":"Journal of machine learning research"},{"key":"ref51","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref52","first-page":"9179","article-title":"Simple and effective vae training with calibrated decoders","volume-title":"International conference on machine learning","volume":"4","author":"Rybkin"},{"key":"ref53","first-page":"7","article-title":"Human motion diffusion as a generative prior","author":"Shafir","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1145\/3658140"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1145\/3658140"},{"key":"ref56","doi-asserted-by":"publisher","DOI":"10.1145\/3355089.3356505"},{"issue":"3","key":"ref57","first-page":"6","article-title":"Human motion diffusion model","volume-title":"The Eleventh International Conference on Learning Representations","volume":"2","author":"Tevet"},{"key":"ref58","first-page":"3","article-title":"Closd: Closing the loop between simulation and diffusion for multi-task character control","author":"Tevet","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref59","first-page":"3","article-title":"Neural discrete representation learning","volume":"30","author":"Van","year":"2017","journal-title":"Advances in neural information processing systems"},{"key":"ref60","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00672"},{"key":"ref62","article-title":"Mospa: Human motion generation driven by spatial audio","author":"Xu","year":"2025","journal-title":"arXiv preprint arXiv"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00487"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611887"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.00956"},{"key":"ref66","first-page":"4","article-title":"Language model beats diffusion-tokenizer is key to visual generation","author":"Yu","year":"2023","journal-title":"arXiv preprint arXiv"},{"key":"ref67","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730640"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1109\/cvpr52729.2023.01415"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"ref70","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v38i7.28567"},{"key":"ref71","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.00190"},{"key":"ref72","first-page":"3","article-title":"Dart: A diffusionbased autoregressive motion model for real-time text-driven motion control","volume":"2","author":"Zhao","year":"2024","journal-title":"arXiv preprint arXiv"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00135"}],"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\/11449018.pdf?arnumber=11449018","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,30]],"date-time":"2026-04-30T06:40:40Z","timestamp":1777531240000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11449018\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":74,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.00940","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}