{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T14:25:25Z","timestamp":1774621525527,"version":"3.50.1"},"reference-count":35,"publisher":"Wiley","license":[{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/onlinelibrary.wiley.com\/termsAndConditions#vor"},{"start":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T00:00:00Z","timestamp":1774569600000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/doi.wiley.com\/10.1002\/tdm_license_1.1"}],"content-domain":{"domain":["onlinelibrary.wiley.com"],"crossmark-restriction":true},"short-container-title":["Computer Graphics Forum"],"abstract":"<jats:title>Abstract<\/jats:title>\n                  <jats:p>Motion tracking has been an important technique for imitating human\u2010like movement from large\u2010scale datasets in physics\u2010based motion synthesis. However, existing approaches focus on tracking either single character or a particular type of interaction, limiting their ability to handle contact\u2010rich interactions. Extending single\u2010character tracking approaches suffers from the instability due to the challenge of forces transferred through contacts. Contact\u2010rich interactions requires levels of control, which places much greater demands on model capacity. To this end, we propose a robust tracking method based on progressive neural network (PNN) where multiple experts are specialized in learning skills of various difficulties. Our method learns to assign training samples to experts automatically without requiring manually scheduling. Both qualitative and quantitative results show that our method delivers more stable motion tracking in densely interactive movements while enabling more efficient model training.<\/jats:p>","DOI":"10.1111\/cgf.70336","type":"journal-article","created":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T13:30:31Z","timestamp":1774618231000},"update-policy":"https:\/\/doi.org\/10.1002\/crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Physics\u2010Based Motion Tracking of Contact\u2010Rich Interacting Characters"],"prefix":"10.1111","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-0822-9064","authenticated-orcid":false,"given":"Xiaotang","family":"Zhang","sequence":"first","affiliation":[{"name":"Durham University  United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0746-6826","authenticated-orcid":false,"given":"Ziyi","family":"Chang","sequence":"additional","affiliation":[{"name":"Durham University  United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0059-5484","authenticated-orcid":false,"given":"Qianhui","family":"Men","sequence":"additional","affiliation":[{"name":"University of Bristol  United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5651-6039","authenticated-orcid":false,"given":"Hubert P. H.","family":"Shum","sequence":"additional","affiliation":[{"name":"Durham University  United Kingdom"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"311","published-online":{"date-parts":[[2026,3,27]]},"reference":[{"key":"e_1_2_6_2_2","doi-asserted-by":"crossref","DOI":"10.1016\/j.patcog.2025.111934","article-title":"On the design fundamentals of diffusion models: A survey","volume":"169","author":"Chang Ziyi","year":"2026","journal-title":"Pattern Recognition"},{"key":"e_1_2_6_3_2","doi-asserted-by":"crossref","unstructured":"Chentanez Nuttapong M\u00fcller Matthias Macklin Miles et al. \u201cPhysics-based motion capture imitation with deep reinforcement learning\u201d.Proceedings of the 11th ACM SIGGRAPH Conference on Motion Interaction and Games.2018 1\u2013102.","DOI":"10.1145\/3274247.3274506"},{"key":"e_1_2_6_4_2","doi-asserted-by":"publisher","DOI":"10.1145\/3721238.3730750"},{"key":"e_1_2_6_4_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3721238.37307503."},{"issue":"6","key":"e_1_2_6_5_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3478513.3480527","article-title":"Supertrack: Motion tracking for physically simulated characters using supervised learning","volume":"40","author":"Fussell Levi","year":"2021","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_6_6_2","doi-asserted-by":"crossref","unstructured":"Juravsky Jordan Guo Yunrong Fidler Sanja andPeng Xue Bin. \u201cSuperpadl: Scaling language-directed physics-based control with progressive supervised distillation\u201d.ACM SIGGRAPH 2024 Conference Papers.2024 1\u2013112.","DOI":"10.1145\/3641519.3657492"},{"key":"e_1_2_6_7_2","first-page":"2161","article-title":"Omnigrasp: Grasping diverse objects with simulated humanoids","volume":"37","author":"Luo Zhengyi","year":"2024","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_2_6_8_2","doi-asserted-by":"crossref","unstructured":"Liu Yunze Chen Changxi Ding Chenjing andYi Li. \u201cPhysReaction: Physically plausible real-time humanoid reaction synthesis via forward dynamics guided 4d imitation\u201d.Proceedings of the 32nd ACM International Conference on Multimedia.2024 3771\u201337803.","DOI":"10.1145\/3664647.3680636"},{"key":"e_1_2_6_9_2","doi-asserted-by":"crossref","unstructured":"Luo Zhengyi Cao Jinkun Khirodkar Rawal et al. \u201cReal-time simulated avatar from head-mounted sensors\u201d.Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition.2024 571\u20135812.","DOI":"10.1109\/CVPR52733.2024.00061"},{"key":"e_1_2_6_10_2","unstructured":"Luo Zhengyi Cao Jinkun Kitani Kris Xu Weipeng et al. \u201cPerpetual humanoid control for real-time simulated avatars\u201d.Proceedings of the IEEE\/CVF International Conference on Computer Vision.2023 10895\u2013109041\u20133 5."},{"key":"e_1_2_6_11_2","unstructured":"Luo Zhengyi Cao Jinkun Merel Josh et al. \u201cUniversal humanoid motion representations for physics-based control\u201d.arXiv preprint arXiv:2310.04582(2023) 2."},{"key":"e_1_2_6_12_2","doi-asserted-by":"crossref","unstructured":"Loper Matthew Mahmood Naureen Romero Javier et al. \u201cSMPL: A skinned multi-person linear model\u201d.Seminal Graphics Papers: Pushing the Boundaries Volume 2.2023 851\u20138665.","DOI":"10.1145\/3596711.3596800"},{"key":"e_1_2_6_13_2","unstructured":"Luo Zhengyi Wang Jiashun Liu Kangni et al. \u201cSmplolympics: Sports environments for physically simulated humanoids\u201d.arXiv preprint arXiv:2407.00187(2024) 1\u20133."},{"key":"e_1_2_6_14_2","unstructured":"Luo Zhengyi Yuan Ye Wang Tingwu et al. \u201cSonic: Supersizing motion tracking for natural humanoid whole-body control\u201d.arXiv preprint arXiv:2511.07820(2025) 5."},{"key":"e_1_2_6_15_2","unstructured":"Liang Han Zhang Wenqian Li Wenxuan et al. \u201cIntergen: Diffusion-based multi-human motion generation under complex interactions\u201d.International Journal of Computer Vision(2024) 1\u2013212 5."},{"key":"e_1_2_6_16_2","doi-asserted-by":"publisher","DOI":"10.1109\/LRA.2023.3270034"},{"issue":"4","key":"e_1_2_6_17_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201311","article-title":"Deepmimic: Example-guided deep reinforcement learning of physics-based character skills","volume":"37","author":"Peng Xue Bin","year":"2018","journal-title":"ACM Transactions On Graphics (TOG)"},{"issue":"4","key":"e_1_2_6_18_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3528223.3530110","article-title":"Ase: Large-scale reusable adversarial skill embeddings for physically simulated characters","volume":"41","author":"Peng Xue Bin","year":"2022","journal-title":"ACM Transactions On Graphics (TOG)"},{"issue":"6","key":"e_1_2_6_19_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3355089.3356501","article-title":"Learning predict-and-simulate policies from unorganized human motion data","volume":"38","author":"Park Soohwan","year":"2019","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_6_20_2","unstructured":"Rusu Andrei A Rabinowitz Neil C Desjardins Guillaume et al. \u201cProgressive Neural Networks\u201d. (2016) 2 4 5."},{"key":"e_1_2_6_21_2","unstructured":"Ren Jiawei Yu Cunjun Chen Siwei et al. \u201cDiffmimic: Efficient motion mimicking with differentiable physics\u201d.arXiv preprint arXiv:2304.03274(2023) 2."},{"issue":"6","key":"e_1_2_6_22_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3687951","article-title":"Maskedmimic: Unified physics-based character control through masked motion inpainting","volume":"43","author":"Tessler Chen","year":"2024","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_6_23_2","unstructured":"Tevet Guy Raab Sigal Cohan Setareh et al. \u201cCLoSD: Closing the Loop between Simulation and Diffusion for multitask character control\u201d.The Thirteenth International Conference on Learning Representations.20252."},{"issue":"4","key":"e_1_2_6_24_2","first-page":"33","article-title":"A scalable approach to control diverse behaviors for physically simulated characters","volume":"39","author":"Won Jungdam","year":"2020","journal-title":"ACM Transactions on Graphics (TOG)"},{"issue":"4","key":"e_1_2_6_25_2","first-page":"1","article-title":"Control strategies for physically simulated characters performing two-player competitive sports","volume":"40","author":"Won Jungdam","year":"2021","journal-title":"ACM Transactions on Graphics (TOG)"},{"key":"e_1_2_6_26_2","unstructured":"Wang Tingwu Guo Yunrong Shugrina Maria andFidler Sanja. \u201cUnicon: Universal neural controller for physics-based character motion\u201d.arXiv preprint arXiv:2011.15119(2020) 2."},{"key":"e_1_2_6_27_2","doi-asserted-by":"crossref","unstructured":"Xie Zhaoming Starke Sebastian Ling Hung Yu andvan dePanne Michiel. \u201cLearning Soccer Juggling Skills with Layer-wise Mixture-of-Experts.(2022)\u201d. (2022) 3.","DOI":"10.1145\/3528233.3530735"},{"key":"e_1_2_6_28_2","doi-asserted-by":"crossref","unstructured":"Xu Michael Shi Yi Yin KangKang andPeng Xue Bin. \u201cParc: Physics-based augmentation with reinforcement learning for character controllers\u201d.Proceedings of the Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Papers.2025 1\u2013112.","DOI":"10.1145\/3721238.3730616"},{"key":"e_1_2_6_29_2","first-page":"21763","article-title":"Residual force control for agile human behavior imitation and extended motion synthesis","volume":"33","author":"Yuan Ye","year":"2020","journal-title":"Advances in Neural Information Processing Systems"},{"issue":"3","key":"e_1_2_6_30_2","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3606926","article-title":"MAAIP: Multi-Agent Adversarial Interaction Priors for imitation from fighting demonstrations for physics-based characters","volume":"6","author":"Younes Mohamed","year":"2023","journal-title":"Proceedings of the ACM on Computer Graphics and Interactive Techniques"},{"key":"e_1_2_6_31_2","doi-asserted-by":"publisher","DOI":"10.1145\/3757377.3763950"},{"key":"e_1_2_6_31_3","unstructured":"url:https:\/\/doi.org\/10.1145\/3757377.37639503."},{"key":"e_1_2_6_32_2","first-page":"6","volume-title":"Computer Graphics Forum","author":"Zhang Xiaotang","year":"2025"},{"key":"e_1_2_6_33_2","doi-asserted-by":"crossref","unstructured":"Zhang Yunbo Gopinath Deepak Ye Yuting et al. \u201cSimulation and retargeting of complex multi-character interactions\u201d.ACM SIGGRAPH 2023 Conference Proceedings.2023 1\u2013112.","DOI":"10.1145\/3588432.3591491"},{"issue":"6","key":"e_1_2_6_34_2","first-page":"1","article-title":"Neural categorical priors for physics-based character control","volume":"42","author":"Zhu Qingxu","year":"2023","journal-title":"ACM Transactions on Graphics (TOG)"}],"container-title":["Computer Graphics Forum"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70336","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/full-xml\/10.1111\/cgf.70336","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/pdf\/10.1111\/cgf.70336","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,3,27]],"date-time":"2026-03-27T13:30:44Z","timestamp":1774618244000},"score":1,"resource":{"primary":{"URL":"https:\/\/onlinelibrary.wiley.com\/doi\/10.1111\/cgf.70336"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,3,27]]},"references-count":35,"alternative-id":["10.1111\/cgf.70336"],"URL":"https:\/\/doi.org\/10.1111\/cgf.70336","archive":["Portico"],"relation":{},"ISSN":["0167-7055","1467-8659"],"issn-type":[{"value":"0167-7055","type":"print"},{"value":"1467-8659","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,3,27]]},"assertion":[{"value":"2026-03-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}],"article-number":"e70336"}}