{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T19:32:40Z","timestamp":1786563160094,"version":"3.56.0"},"reference-count":61,"publisher":"Institute of Electrical and Electronics Engineers (IEEE)","license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/ieeexplore.ieee.org\/Xplorehelp\/downloads\/license-information\/IEEE.html"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"stm-asf","delay-in-days":0,"URL":"https:\/\/doi.org\/10.15223\/policy-029"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":"crossref","award":["62322608"],"award-info":[{"award-number":["62322608"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]},{"name":"PCL Major Key Project","award":["PCL2025A17-2"],"award-info":[{"award-number":["PCL2025A17-2"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["IEEE Trans. on Image Process."],"published-print":{"date-parts":[[2026]]},"DOI":"10.1109\/tip.2026.3708043","type":"journal-article","created":{"date-parts":[[2026,7,20]],"date-time":"2026-07-20T20:22:21Z","timestamp":1784578941000},"page":"7799-7812","source":"Crossref","is-referenced-by-count":0,"title":["In-Context Model Predictive Generation: Open-Vocabulary Motion Synthesis From Language Models to Physics"],"prefix":"10.1109","volume":"35","author":[{"ORCID":"https:\/\/orcid.org\/0009-0005-2818-2373","authenticated-orcid":false,"given":"Xiaomeng","family":"Fu","sequence":"first","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8717-8351","authenticated-orcid":false,"given":"Junfan","family":"Lin","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory","place":["Shenzhen, China"],"department":["Department of Networked Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-9423-9252","authenticated-orcid":false,"given":"Yang","family":"Liu","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2197-9038","authenticated-orcid":false,"given":"Yaowei","family":"Wang","sequence":"additional","affiliation":[{"name":"Harbin Institute of Technology","place":["Shenzhen, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4805-0926","authenticated-orcid":false,"given":"Guanbin","family":"Li","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2248-3755","authenticated-orcid":false,"given":"Liang","family":"Lin","sequence":"additional","affiliation":[{"name":"Sun Yat-sen University","place":["Guangzhou, China"]}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2026-6028","authenticated-orcid":false,"given":"Ziliang","family":"Chen","sequence":"additional","affiliation":[{"name":"Peng Cheng Laboratory","place":["Shenzhen, China"],"department":["Department of Networked Intelligence"]}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"263","reference":[{"key":"ref1","article-title":"Human motion diffusion model","author":"Tevet","year":"2022","journal-title":"arXiv:2209.14916"},{"key":"ref2","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"ref3","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"ref4","article-title":"MotionDiffuse: Text-driven human motion generation with diffusion model","author":"Zhang","year":"2022","journal-title":"arXiv:2208.15001"},{"key":"ref5","doi-asserted-by":"publisher","DOI":"10.52202\/075280-0880"},{"key":"ref6","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00053"},{"key":"ref7","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32877"},{"key":"ref8","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i2.32183"},{"key":"ref9","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW67362.2025.00271"},{"key":"ref10","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"ref11","doi-asserted-by":"publisher","DOI":"10.1145\/3528223.3530094"},{"key":"ref12","first-page":"8748","article-title":"Learning transferable visual models from natural language supervision","volume-title":"Proc. Int. Conf. Mach. Learn.","volume":"139","author":"Radford"},{"key":"ref13","article-title":"LaMDA: Language models for dialog applications","author":"Thoppilan","year":"2022","journal-title":"arXiv:2201.08239"},{"key":"ref14","article-title":"GPT-4 technical report","volume-title":"arXiv:2303.08774","author":"Achiam","year":"2023"},{"key":"ref15","doi-asserted-by":"publisher","DOI":"10.52202\/068431-1800"},{"key":"ref16","doi-asserted-by":"publisher","DOI":"10.1109\/ICRA57147.2024.10610948"},{"key":"ref17","article-title":"Plan, posture and go: Towards open-world text-to-motion generation","author":"Liu","year":"2023","journal-title":"arXiv:2312.14828"},{"key":"ref18","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"ref19","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00087"},{"key":"ref20","doi-asserted-by":"publisher","DOI":"10.1007\/BF00992698"},{"key":"ref21","doi-asserted-by":"publisher","DOI":"10.1007\/BF00115009"},{"key":"ref22","doi-asserted-by":"publisher","DOI":"10.1016\/0005-1098(78)90001-8"},{"key":"ref23","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-24853-0"},{"key":"ref24","first-page":"1","article-title":"Neural discrete representation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"30","author":"Van Den Oord"},{"key":"ref25","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i9.33062"},{"key":"ref26","article-title":"Human motion diffusion as a generative prior","author":"Shafir","year":"2023","journal-title":"arXiv:2303.01418"},{"key":"ref27","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-72627-9_2"},{"key":"ref28","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"ref29","doi-asserted-by":"publisher","DOI":"10.1089\/big.2016.0028"},{"key":"ref30","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02117"},{"key":"ref31","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00554"},{"key":"ref32","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1099"},{"key":"ref33","article-title":"Motion-X++: A large-scale multimodal 3D whole-body human motion dataset","author":"Zhang","year":"2025","journal-title":"arXiv:2501.05098"},{"key":"ref34","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02224"},{"key":"ref35","doi-asserted-by":"publisher","DOI":"10.1109\/ICME55011.2023.00014"},{"key":"ref36","doi-asserted-by":"publisher","DOI":"10.1145\/3658137"},{"key":"ref37","article-title":"An image is worth $16\\times 16$\n words: Transformers for image recognition at scale","author":"Dosovitskiy","year":"2020","journal-title":"arXiv:2010.11929"},{"key":"ref38","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01228"},{"key":"ref39","article-title":"Physics-based character controllers with reinforcement learning","volume-title":"Ph.D. dissertation, Univ. British Columbia","author":"Reda","year":"2025"},{"key":"ref40","doi-asserted-by":"publisher","DOI":"10.1145\/3732285"},{"key":"ref41","doi-asserted-by":"publisher","DOI":"10.1145\/3731425"},{"key":"ref42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"ref43","doi-asserted-by":"publisher","DOI":"10.52202\/075280-1799"},{"key":"ref44","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00859"},{"key":"ref45","doi-asserted-by":"publisher","DOI":"10.1145\/3680528.3687683"},{"key":"ref46","article-title":"CLoSD: Closing the loop between simulation and diffusion for multi-task character control","author":"Tevet","year":"2024","journal-title":"arXiv:2410.03441"},{"key":"ref47","first-page":"1","article-title":"Generative adversarial imitation learning","volume-title":"Proc. Adv. Neural Inf. Process. Syst.","volume":"29","author":"Ho"},{"key":"ref48","doi-asserted-by":"publisher","DOI":"10.1145\/3386569.3392474"},{"key":"ref49","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555391"},{"key":"ref50","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01000"},{"key":"ref51","article-title":"Isaac gym: High performance GPU-based physics simulation for robot learning","author":"Makoviychuk","year":"2021","journal-title":"arXiv:2108.10470"},{"key":"ref52","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596800"},{"key":"ref53","first-page":"1","article-title":"LoRA: Low-rank adaptation of large language models","volume-title":"Proc. Int. Conf. Learn. Represent.","author":"Hu"},{"key":"ref54","article-title":"Decoupled weight decay regularization","author":"Loshchilov","year":"2017","journal-title":"arXiv:1711.05101"},{"key":"ref55","article-title":"The llama 3 herd of models","author":"Grattafiori","year":"2024","journal-title":"arXiv:2407.21783"},{"key":"ref56","volume-title":"CMU Graphics Lab Motion Capture Database","author":"Hodgins","year":"2015"},{"key":"ref57","article-title":"ActionCLIP: A new paradigm for video action recognition","author":"Wang","year":"2021","journal-title":"arXiv:2109.08472"},{"key":"ref58","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51701.2025.01239"},{"key":"ref59","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3754940"},{"key":"ref60","article-title":"Llama 2: Open foundation and fine-tuned chat models","author":"Touvron","year":"2023","journal-title":"arXiv:2307.09288"},{"key":"ref61","article-title":"Phi-4 technical report","volume-title":"arXiv:2412.08905","author":"Abdin","year":"2024"}],"container-title":["IEEE Transactions on Image Processing"],"original-title":[],"link":[{"URL":"http:\/\/xplorestaging.ieee.org\/ielx8\/83\/11355710\/11614712.pdf?arnumber=11614712","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,8,12]],"date-time":"2026-08-12T19:05:14Z","timestamp":1786561514000},"score":1,"resource":{"primary":{"URL":"https:\/\/ieeexplore.ieee.org\/document\/11614712\/"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"references-count":61,"URL":"https:\/\/doi.org\/10.1109\/tip.2026.3708043","relation":{},"ISSN":["1057-7149","1941-0042"],"issn-type":[{"value":"1057-7149","type":"print"},{"value":"1941-0042","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]}}}