{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,4]],"date-time":"2026-05-04T10:14:24Z","timestamp":1777889664826,"version":"3.51.4"},"reference-count":91,"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\/iccv51701.2025.01182","type":"proceedings-article","created":{"date-parts":[[2026,4,29]],"date-time":"2026-04-29T19:45:49Z","timestamp":1777491949000},"page":"12725-12736","source":"Crossref","is-referenced-by-count":0,"title":["Primal: Physically Reactive and Interactive Motor Model for Avatar Learning"],"prefix":"10.1109","author":[{"given":"Yan","family":"Zhang","sequence":"first","affiliation":[{"name":"Meshcapade"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yao","family":"Feng","sequence":"additional","affiliation":[{"name":"Meshcapade"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Alpar","family":"Cseke","sequence":"additional","affiliation":[{"name":"Meshcapade"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nitin","family":"Saini","sequence":"additional","affiliation":[{"name":"Meshcapade"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nathan","family":"Bajandas","sequence":"additional","affiliation":[{"name":"Meshcapade"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicolas","family":"Heron","sequence":"additional","affiliation":[{"name":"Meshcapade"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Michael J.","family":"Black","sequence":"additional","affiliation":[{"name":"Max Planck Institute for Intelligent Systems,Tübingen"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"263","reference":[{"key":"ref1","volume-title":"SFU motion capture database","year":"2000"},{"key":"ref2","article-title":"Advanced Computing Center for the Arts and Design","journal-title":"ACCAD MoCap Dataset"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298751"},{"key":"ref4","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02032"},{"key":"ref5","article-title":"Scheduled sampling for sequence prediction with recurrent neural networks","volume":"28","author":"Bengio","year":"2015","journal-title":"Advances in neural information processing systems"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1249\/00005768-197901130-00010"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.591"},{"key":"ref8","article-title":"Inertialization: High-performance animation transitions in gears of war","author":"Bollo","year":"2018","journal-title":"GDC 2018"},{"key":"ref9","article-title":"Carnegie Mellon University","journal-title":"CMU MoCap Dataset"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.52202\/079017-0759"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3641519.3657440"},{"key":"ref12","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2005.202"},{"key":"ref13","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"ref14","first-page":"8780","article-title":"Diffusion models beat gans on image synthesis","volume-title":"Advances in neural information processing systems","volume":"34","author":"Dhariwal","year":"2021"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00094"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2017.12.012"},{"key":"ref17","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01093"},{"key":"ref18","article-title":"MoVi: A large multipurpose motion and video dataset","author":"Ghorbani","year":"2020","journal-title":"arXiv preprint"},{"key":"ref19","volume-title":"Meshcapade GmbH. Mocapade3.0","year":"2025"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01118"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1145\/3588432.3591525"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00164"},{"key":"ref24","article-title":"Gaussian error linear units (gelus)","author":"Hendrycks","year":"2016","journal-title":"arXiv preprint"},{"key":"ref25","article-title":"Classifier-free diffusion guidance","author":"Ho","year":"2022","journal-title":"arXiv preprint"},{"key":"ref26","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","author":"Ho","year":"2020","journal-title":"Advances in neural information processing systems"},{"key":"ref27","author":"Holden","year":"2021","journal-title":"Spring-it-on: The game developer\u2019s spring-roll-call"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1145\/2820903.2820918"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392440"},{"issue":"2","key":"ref30","article-title":"Lora: Low-rank adaptation of large language models","volume":"1","author":"Edward","year":"2022","journal-title":"ICLR"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_11"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref33","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687595"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00171"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"ref36","article-title":"Adam: A method for stochastic optimization","author":"Kingma","year":"2014","journal-title":"arXiv preprint"},{"key":"ref37","article-title":"Auto-encoding variational Bayes","author":"Kingma","year":"2014","journal-title":"ICLR"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566605"},{"key":"ref39","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01374"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3618333"},{"key":"ref41","first-page":"54","article-title":"Controllable human-object interaction synthesis","volume-title":"European Conference on Computer Vision","author":"Li"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"ref43","article-title":"Interdance: Reactive 3d dance generation with realistic duet interactions","author":"Li","year":"2024","journal-title":"arXiv preprint"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00053"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392422"},{"key":"ref46","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3680636"},{"key":"ref47","doi-asserted-by":"publisher","DOI":"10.1145\/2661229.2661273"},{"key":"ref48","article-title":"Fixing weight decay regularization in adam","volume":"5","author":"Loshchilov","year":"2017","journal-title":"arXiv preprint"},{"key":"ref49","journal-title":"Eyes JAPAN Co. Ltd. Eyes Japan MoCap Dataset"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref51","article-title":"Documentation mocap database hdm05","volume-title":"Technical Report CG-2007\u20132, Universit\u00e4t Bonn","author":"M\u00fcller","year":"2007"},{"key":"ref52","author":"Agarwal","year":"2025","journal-title":"Cosmos world foundation model platform for physical ai"},{"key":"ref53","article-title":"Chatgpt: Conversational ai model","year":"2024","journal-title":"OpenAI"},{"key":"ref54","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01123"},{"key":"ref55","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00387"},{"key":"ref56","article-title":"Amp: Adversarial motion priors for stylized physics-based character control","author":"Bin Peng","year":"2021","journal-title":"arXiv preprint"},{"key":"ref57","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v32i1.11671"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"ref59","article-title":"Searching for activation functions","volume":"abs\/1710.05941","author":"Ramachandran","year":"2017","journal-title":"CoRR"},{"issue":"2","key":"ref60","first-page":"3","article-title":"Hierarchical text-conditional image generation with CLIP latents","volume":"1","author":"Ramesh","year":"2022","journal-title":"arXiv preprint"},{"key":"ref61","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01322"},{"key":"ref62","article-title":"Insactor: Instruction-driven physicsbased characters","author":"Ren","year":"2023","journal-title":"NeurIPS"},{"key":"ref63","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"ref64","doi-asserted-by":"publisher","DOI":"10.1145\/3658140"},{"key":"ref65","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-009-0273-6"},{"key":"ref66","first-page":"2256","article-title":"Deep unsupervised learning using nonequilibrium thermodynamics","volume-title":"International conference on machine learning","author":"Sohl-Dickstein"},{"key":"ref67","article-title":"Generative modeling by estimating gradients of the data distribution","volume":"32","author":"Song","year":"2019","journal-title":"Advances in neural information processing systems"},{"key":"ref68","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58548-8_34"},{"key":"ref69","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01291"},{"key":"ref70","article-title":"Human motion diffusion model","volume-title":"In The Eleventh International Conference on Learning Representations","author":"Tevet"},{"key":"ref71","article-title":"Closd: Closing the loop between simulation and diffusion for multi-task character control","author":"Tevet","year":"2024","journal-title":"arXiv preprint"},{"key":"ref72","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv preprint"},{"key":"ref73","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72640-8_8"},{"key":"ref74","doi-asserted-by":"publisher","DOI":"10.1167\/2.5.2"},{"key":"ref75","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref76","author":"Valevski","year":"2024","journal-title":"Diffusion models are real-time game engines"},{"key":"ref77","doi-asserted-by":"publisher","DOI":"10.48550\/ARXIV.1706.03762"},{"key":"ref78","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00075"},{"key":"ref79","article-title":"Saga: Stochastic wholebody grasping with contact","author":"Wu","year":"2022","journal-title":"In ECCV"},{"key":"ref80","article-title":"Humanobject interaction from human-level instructions","author":"Wu","year":"2024","journal-title":"arXiv preprint"},{"key":"ref81","article-title":"Omnicontrol: Control any joint at any time for human motion generation","volume-title":"In The Twelfth International Conference on Learning Representations","author":"Xie"},{"key":"ref82","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref83","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"ref84","doi-asserted-by":"publisher","DOI":"10.1109\/tpami.2024.3355414"},{"key":"ref85","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01384"},{"key":"ref86","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01983"},{"key":"ref87","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00338"},{"key":"ref88","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01354"},{"key":"ref89","article-title":"DartControl: A diffusion-based autoregressive motion model for real-time text-driven motion control","volume-title":"The Thirteenth International Conference on Learning Representations (ICLR)","author":"Zhao"},{"key":"ref90","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73232-4_23"},{"key":"ref91","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00589"}],"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\/11443453.pdf?arnumber=11443453","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,1]],"date-time":"2026-05-01T05:14:38Z","timestamp":1777612478000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11443453\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"references-count":91,"URL":"https:\/\/doi.org\/10.1109\/iccv51701.2025.01182","relation":{},"subject":[],"published":{"date-parts":[[2025,10,19]]}}}