{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T12:55:49Z","timestamp":1761396949867,"version":"3.40.3"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031730320"},{"type":"electronic","value":"9783031730337"}],"license":[{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:00:00Z","timestamp":1730332800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2025]]},"DOI":"10.1007\/978-3-031-73033-7_1","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:03:55Z","timestamp":1730333035000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":3,"title":["Generating Physically Realistic and\u00a0Directable Human Motions from\u00a0Multi-modal Inputs"],"prefix":"10.1007","author":[{"given":"Aayam","family":"Shrestha","sequence":"first","affiliation":[]},{"given":"Pan","family":"Liu","sequence":"additional","affiliation":[]},{"given":"German","family":"Ros","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Yuan","sequence":"additional","affiliation":[]},{"given":"Alan","family":"Fern","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,10,31]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Bae, J., Won, J., Lim, D., Min, C.H., Kim, Y.: PMP: learning to physically interact with environments using part-wise motion priors. In: ACM SIGGRAPH 2023 Conference Proceedings (2023)","DOI":"10.1145\/3588432.3591487"},{"key":"1_CR2","doi-asserted-by":"publisher","first-page":"461","DOI":"10.3390\/mi14020461","volume":"14","author":"JC Cer\u00f3n","year":"2023","unstructured":"Cer\u00f3n, J.C., et al.: A novel multi-modal teleoperation of a humanoid assistive robot with real-time motion mimic. Micromachines 14, 461 (2023)","journal-title":"Micromachines"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Executing your commands via motion diffusion in latent space. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 18000\u201318010 (2022)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Chentanez, N., M\u00fcller, M., Macklin, M., Makoviychuk, V., Jeschke, S.: Physics-based motion capture imitation with deep reinforcement learning. In: Proceedings of the 11th ACM SIGGRAPH Conference on Motion, Interaction and Games (2018)","DOI":"10.1145\/3274247.3274506"},{"key":"1_CR5","doi-asserted-by":"crossref","unstructured":"Dou, Z., Chen, X., Fan, Q., Komura, T., Wang, W.: CASE: learning conditional adversarial skill embeddings for physics-based characters. arXiv arXiv:2309.11351 (2023)","DOI":"10.1145\/3610548.3618205"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Du, Y., Kips, R., Pumarola, A., Starke, S., Thabet, A.K., Sanakoyeu, A.: Avatars grow legs: generating smooth human motion from sparse tracking inputs with diffusion model. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 481\u2013490 (2023)","DOI":"10.1109\/CVPR52729.2023.00054"},{"key":"1_CR7","unstructured":"Ho, J., Ermon, S.: Generative adversarial imitation learning. In: Neural Information Processing Systems (2016)"},{"key":"1_CR8","doi-asserted-by":"crossref","unstructured":"Huang, Z., Zhou, Z., Chuang, Y.Y., Wu, J., Liu, C.K.: Physically plausible animation of human upper body from a single image. In: 2023 IEEE\/CVF Winter Conference on Applications of Computer Vision (WACV), pp. 930\u2013939 (2022)","DOI":"10.1109\/WACV56688.2023.00099"},{"key":"1_CR9","unstructured":"Jiang, Z., et al.: H-GAP: humanoid control with a generalist planner. In: NeurIPS 2023 Foundation Models for Decision Making Workshop (2023)"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Juravsky, J., Guo, Y., Fidler, S., Peng, X.B.: PADL: language-directed physics-based character control. In: SIGGRAPH Asia 2022 Conference Papers (2022)","DOI":"10.1145\/3550469.3555391"},{"key":"1_CR11","doi-asserted-by":"crossref","unstructured":"Lee, C.H., Yueh, N.C.L., Woo, K.T.: Human-inspired video imitation learning on humanoid model. In: 2022 Sixth IEEE International Conference on Robotic Computing (IRC), pp. 345\u2013352 (2022)","DOI":"10.1109\/IRC55401.2022.00068"},{"key":"1_CR12","first-page":"1","volume":"41","author":"S Lee","year":"2022","unstructured":"Lee, S., Lee, J., Lee, J.: Learning virtual chimeras by dynamic motion reassembly. ACM Trans. Graph. (TOG) 41, 1\u201313 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR13","unstructured":"Luo, Z.G., et al.: Universal humanoid motion representations for physics-based control. arXiv arXiv:2310.04582 (2023)"},{"key":"1_CR14","doi-asserted-by":"publisher","unstructured":"Luo, Z., Cao, J., Winkler, A., Kitani, K., Xu, W.: Perpetual humanoid control for real-time simulated avatars. https:\/\/doi.org\/10.48550\/arXiv.2305.06456","DOI":"10.48550\/arXiv.2305.06456"},{"key":"1_CR15","unstructured":"Luo, Z., Yuan, Y., Kitani, K.M.: From universal humanoid control to automatic physically valid character creation. arXiv arXiv:2206.09286 (2022)"},{"key":"1_CR16","unstructured":"Merel, J., et al.: Neural probabilistic motor primitives for humanoid control. arXiv arXiv:1811.11711 (2018)"},{"key":"1_CR17","unstructured":"Merel, J., et al.: Learning human behaviors from motion capture by adversarial imitation. arXiv arXiv:1707.02201 (2017)"},{"key":"1_CR18","doi-asserted-by":"crossref","unstructured":"Merel, J., et al.: Catch & carry: reusable neural controllers for vision-guided whole-body tasks (2019)","DOI":"10.1145\/3386569.3392474"},{"issue":"4","key":"1_CR19","first-page":"1","volume":"37","author":"XB Peng","year":"2018","unstructured":"Peng, X.B., Abbeel, P., Levine, S., Van de Panne, M.: DeepMimic: example-guided deep reinforcement learning of physics-based character skills. ACM Trans. Graph. (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"1_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530110","volume":"41","author":"XB Peng","year":"2022","unstructured":"Peng, X.B., Guo, Y., Halper, L., Levine, S., Fidler, S.: ASE: large-scale reusable adversarial skill embeddings for physically simulated characters. ACM Trans. Graph. (TOG) 41(4), 1\u201317 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"issue":"4","key":"1_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3450626.3459670","volume":"40","author":"XB Peng","year":"2021","unstructured":"Peng, X.B., Ma, Z., Abbeel, P., Levine, S., Kanazawa, A.: AMP: adversarial motion priors for stylized physics-based character control. ACM Trans. Graph. (TOG) 40(4), 1\u201320 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR22","unstructured":"Reallusion: 3D animation and 2D cartoons made simple"},{"key":"1_CR23","unstructured":"Ren, J., Yu, C., Chen, S., Ma, X., Pan, L., Liu, Z.: DiffMimic: efficient motion mimicking with differentiable physics (2023)"},{"issue":"1","key":"1_CR24","doi-asserted-by":"publisher","first-page":"16","DOI":"10.1109\/TBIOM.2020.3037257","volume":"3","author":"I S\u00e1r\u00e1ndi","year":"2021","unstructured":"S\u00e1r\u00e1ndi, I., Linder, T., Arras, K.O., Leibe, B.: MeTRAbs: metric-scale truncation-robust heatmaps for absolute 3D human pose estimation. IEEE Trans. Biometrics Behav. Identity Sci. 3(1), 16\u201330 (2021). https:\/\/doi.org\/10.1109\/TBIOM.2020.3037257","journal-title":"IEEE Trans. Biometrics Behav. Identity Sci."},{"key":"1_CR25","unstructured":"Shrestha, A., Lee, S., Tadepalli, P., Fern, A.: DeepAveragers: offline reinforcement learning by solving derived non-parametric MDPs. arXiv arXiv:2010.08891 (2020)"},{"key":"1_CR26","doi-asserted-by":"crossref","unstructured":"Sun, J., Zhang, Q., Duan, Y., Jiang, X., Cheng, C., Xu, R.: Prompt, plan, perform: LLM-based humanoid control via quantized imitation learning. arXiv arXiv:2309.11359 (2023)","DOI":"10.1109\/ICRA57147.2024.10610948"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Tessler, C., Kasten, Y., Guo, Y., Mannor, S., Chechik, G., Peng, X.B.: CALM: conditional adversarial latent models for directable virtual characters. In: ACM SIGGRAPH 2023 Conference Proceedings (2023)","DOI":"10.1145\/3588432.3591541"},{"key":"1_CR28","doi-asserted-by":"publisher","unstructured":"Wagener, N., Kolobov, A., Frujeri, F.V., Loynd, R., Cheng, C.A., Hausknecht, M.: MoCapAct: a multi-task dataset for simulated humanoid control. https:\/\/doi.org\/10.48550\/arXiv.2208.07363","DOI":"10.48550\/arXiv.2208.07363"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Wang, J., Xu, H., Xu, J., Liu, S., Wang, X.: Synthesizing long-term 3D human motion and interaction in 3D scenes. In: 2021 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 9396\u20139406 (2020)","DOI":"10.1109\/CVPR46437.2021.00928"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Won, J., Gopinath, D.E., Hodgins, J.K.: A scalable approach to control diverse behaviors for physically simulated characters. ACM Trans. Graph. (TOG) 39, 1 \u2013 12 (2020)","DOI":"10.1145\/3386569.3392381"},{"key":"1_CR31","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3528223.3530067","volume":"41","author":"J Won","year":"2022","unstructured":"Won, J., Gopinath, D.E., Hodgins, J.K.: Physics-based character controllers using conditional VAEs. ACM Trans. Graph. (TOG) 41, 1\u201312 (2022)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR32","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3480148","volume":"4","author":"P Xu","year":"2021","unstructured":"Xu, P., Karamouzas, I.: A GAN-like approach for physics-based imitation learning and interactive control. Proc. ACM Comput. Graph. Interact. Tech. 4, 1\u201322 (2021)","journal-title":"Proc. ACM Comput. Graph. Interact. Tech."},{"key":"1_CR33","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3618330","volume":"42","author":"P Xu","year":"2023","unstructured":"Xu, P., Shang, X., Zordan, V.B., Karamouzas, I.: Composite motion learning with task control. ACM Trans. Graph. (TOG) 42, 1\u201316 (2023)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"1_CR34","doi-asserted-by":"crossref","unstructured":"Yao, H., Song, Z., Zhou, Y., Ao, T., Chen, B., Liu, L.: MoConVQ: unified physics-based motion control via scalable discrete representations. arXiv arXiv:2310.10198 (2023)","DOI":"10.1145\/3658137"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Generating human motion from textual descriptions with discrete representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14730\u201314740 (2023)","DOI":"10.1109\/CVPR52729.2023.01415"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2024"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-73033-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T00:30:46Z","timestamp":1730334646000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73033-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,31]]},"ISBN":["9783031730320","9783031730337"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73033-7_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,10,31]]},"assertion":[{"value":"31 October 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ECCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"European Conference on Computer Vision","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Milan","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 October 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2024.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}