{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,24]],"date-time":"2026-06-24T16:17:51Z","timestamp":1782317871816,"version":"3.54.5"},"publisher-location":"Cham","reference-count":40,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732416","type":"print"},{"value":"9783031732423","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,10,29]],"date-time":"2024-10-29T00:00:00Z","timestamp":1730160000000},"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\/978-3-031-73242-3_6","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:15:43Z","timestamp":1730106943000},"page":"93-109","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["FreeMotion: A Unified Framework for\u00a0Number-Free Text-to-Motion Synthesis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1404-1335","authenticated-orcid":false,"given":"Ke","family":"Fan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6549-5257","authenticated-orcid":false,"given":"Junshu","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-2554-1294","authenticated-orcid":false,"given":"Weijian","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1858-3358","authenticated-orcid":false,"given":"Ran","family":"Yi","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8149-1117","authenticated-orcid":false,"given":"Moran","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-4536-0953","authenticated-orcid":false,"given":"Jingyu","family":"Gong","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8891-6766","authenticated-orcid":false,"given":"Jiangning","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6592-8411","authenticated-orcid":false,"given":"Yabiao","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4216-8090","authenticated-orcid":false,"given":"Chengjie","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1653-4341","authenticated-orcid":false,"given":"Lizhuang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"6_CR1","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Executing your commands via motion diffusion in latent space. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18000\u201318010 (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Chopin, B., Tang, H., Daoudi, M.: Bipartite graph diffusion model for human interaction generation. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 5333\u20135342 (2024)","DOI":"10.1109\/WACV57701.2024.00525"},{"key":"6_CR3","doi-asserted-by":"crossref","unstructured":"Chopin, B., Tang, H., Otberdout, N., Daoudi, M., Sebe, N.: Interaction transformer for human reaction generation. IEEE Trans. Multimed. (2023)","DOI":"10.1109\/TMM.2023.3242152"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Dai, W., Chen, L.H., Wang, J., Liu, J., Dai, B., Tang, Y.: Motionlcm: real-time controllable motion generation via latent consistency model. arXiv preprint arXiv:2404.19759 (2024)","DOI":"10.1007\/978-3-031-72640-8_22"},{"key":"6_CR5","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Dabral, R., Golyanik, V., Theobalt, C., Slusallek, P.: Remos: reactive 3d motion synthesis for two-person interactions. arXiv preprint arXiv:2311.17057 (2023)","DOI":"10.1007\/978-3-031-72764-1_24"},{"key":"6_CR7","unstructured":"Gong, J., et al.: Demos: dynamic environment motion synthesis in 3D scenes via local spherical-bev perception. arXiv preprint arXiv:2403.01740 (2024)"},{"key":"6_CR8","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3D human motions from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Guo, W., Bie, X., Alameda-Pineda, X., Moreno-Noguer, F.: Multi-person extreme motion prediction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13053\u201313064 (2022)","DOI":"10.1109\/CVPR52688.2022.01271"},{"key":"6_CR10","first-page":"6840","volume":"33","author":"J Ho","year":"2020","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. Adv. Neural Inf. Process. Syst. 33, 6840\u20136851 (2020)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"6_CR11","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"6_CR12","doi-asserted-by":"crossref","unstructured":"Hu, T., Zhu, X., Guo, W., Su, K., et\u00a0al.: Efficient interaction recognition through positive action representation. Math. Probl. Eng. 2013 (2013)","DOI":"10.1155\/2013\/795360"},{"key":"6_CR13","unstructured":"Karunratanakul, K., Preechakul, K., Suwajanakorn, S., Tang, S.: GMD: controllable human motion synthesis via guided diffusion models. arXiv preprint arXiv:2305.12577 (2023)"},{"issue":"3\u20134","key":"6_CR14","doi-asserted-by":"publisher","first-page":"213","DOI":"10.1002\/cav.101","volume":"16","author":"T Komura","year":"2005","unstructured":"Komura, T., Ho, E.S., Lau, R.W.: Animating reactive motion using momentum-based inverse kinematics. Comput. Animat. Virtual Worlds 16(3\u20134), 213\u2013223 (2005)","journal-title":"Comput. Animat. Virtual Worlds"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Kundu, J.N., Buckchash, H., Mandikal, P., Jamkhandi, A., Radhakrishnan, V.B., et\u00a0al.: Cross-conditioned recurrent networks for long-term synthesis of inter-person human motion interactions. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 2724\u20132733 (2020)","DOI":"10.1109\/WACV45572.2020.9093627"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Le, N., Pham, T., Do, T., Tjiputra, E., Tran, Q.D., Nguyen, A.: Music-driven group choreography. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8673\u20138682 (2023)","DOI":"10.1109\/CVPR52729.2023.00838"},{"key":"6_CR17","doi-asserted-by":"crossref","unstructured":"Liang, H., Zhang, W., Li, W., Yu, J., Xu, L.: Intergen: diffusion-based multi-human motion generation under complex interactions. arXiv preprint arXiv:2304.05684 (2023)","DOI":"10.1007\/s11263-024-02042-6"},{"key":"6_CR18","unstructured":"Lin, J., et al.: Motion-x: a large-scale 3d expressive whole-body human motion dataset. arXiv preprint arXiv:2307.00818 (2023)"},{"key":"6_CR19","doi-asserted-by":"crossref","unstructured":"Liu, H., et al.: Emage: towards unified holistic co-speech gesture generation via expressive masked audio gesture modeling. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 1144\u20131154 (2024)","DOI":"10.1109\/CVPR52733.2024.00115"},{"key":"6_CR20","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: International Conference on Machine Learning, pp. 8162\u20138171. PMLR (2021)"},{"key":"6_CR21","unstructured":"OpenAI: https:\/\/openai.com\/blog\/chatgpt"},{"key":"6_CR22","doi-asserted-by":"publisher","unstructured":"Petrovich, M., Black, M.J., Varol, G.: TEMOS: generating diverse human motions from textual descriptions. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Computer Vision \u2013 ECCV 2022. ECCV 2022. LNCS, vol. 13682, pp. 480\u2013497. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_28","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"6_CR23","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: International Conference on Machine Learning, pp. 8748\u20138763. PMLR (2021)"},{"key":"6_CR24","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418 (2023)"},{"key":"6_CR25","doi-asserted-by":"crossref","unstructured":"Shum, H.P., Komura, T., Yamazaki, S.: Simulating competitive interactions using singly captured motions. In: Proceedings of the 2007 ACM Symposium on Virtual Reality Software and Technology, pp. 65\u201372 (2007)","DOI":"10.1145\/1315184.1315194"},{"key":"6_CR26","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. arXiv preprint arXiv:2010.02502 (2020)"},{"key":"6_CR27","doi-asserted-by":"crossref","unstructured":"Tanaka, M., Fujiwara, K.: Role-aware interaction generation from textual description. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 15999\u201316009 (2023)","DOI":"10.1109\/ICCV51070.2023.01466"},{"issue":"1","key":"6_CR28","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1007\/s44267-023-00020-z","volume":"1","author":"J Tang","year":"2023","unstructured":"Tang, J., Wang, J., Hu, J.F.: Predicting human poses via recurrent attention network. Vis. Intell. 1(1), 18 (2023)","journal-title":"Vis. Intell."},{"key":"6_CR29","doi-asserted-by":"crossref","unstructured":"Tang, J., et al: Make-it-vivid: dressing your animatable biped cartoon characters from text. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6243\u20136253 (2024)","DOI":"10.1109\/CVPR52733.2024.00597"},{"key":"6_CR30","doi-asserted-by":"crossref","unstructured":"Tanke, J., et al.: Social diffusion: long-term multiple human motion anticipation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9601\u20139611 (2023)","DOI":"10.1109\/ICCV51070.2023.00880"},{"key":"6_CR31","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. arXiv preprint arXiv:2209.14916 (2022)"},{"key":"6_CR32","unstructured":"Wang, Z., Wang, J., Lin, D., Dai, B.: Intercontrol: generate human motion interactions by controlling every joint. arXiv preprint arXiv:2311.15864 (2023)"},{"key":"6_CR33","unstructured":"Xie, Y., Jampani, V., Zhong, L., Sun, D., Jiang, H.: Omnicontrol: control any joint at any time for human motion generation. arXiv preprint arXiv:2310.08580 (2023)"},{"key":"6_CR34","doi-asserted-by":"crossref","unstructured":"Xie, Z., Wu, Y., Gao, X., Sun, Z., Yang, W., Liang, X.: Towards detailed text-to-motion synthesis via basic-to-advanced hierarchical diffusion model. arXiv preprint arXiv:2312.10960 (2023)","DOI":"10.1609\/aaai.v38i6.28443"},{"key":"6_CR35","doi-asserted-by":"crossref","unstructured":"Xu, J., et al.: Exploring versatile prior for human motion via motion frequency guidance. In: 2021 International Conference on 3D Vision (3DV), pp. 606\u2013616. IEEE (2021)","DOI":"10.1109\/3DV53792.2021.00070"},{"key":"6_CR36","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"6_CR37","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Motiondiffuse: text-driven human motion generation with diffusion model. IEEE Transactions on Pattern Analysis and Machine Intelligence (2024)","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"6_CR38","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Remodiffuse: retrieval-augmented motion diffusion model. arXiv preprint arXiv:2304.01116 (2023)","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"6_CR39","unstructured":"Zhang, M., Li, H., Cai, Z., Ren, J., Yang, L., Liu, Z.: Finemogen: fine-grained spatio-temporal motion generation and editing. arXiv preprint arXiv:2312.15004 (2023)"},{"key":"6_CR40","doi-asserted-by":"crossref","unstructured":"Zheng, T., et al.: Beta-tuned timestep diffusion model. In: European Conference on Computer Vision (2024)","DOI":"10.1007\/978-3-031-72646-0_7"}],"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\/978-3-031-73242-3_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:22:43Z","timestamp":1732962163000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73242-3_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031732416","9783031732423"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73242-3_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,10,29]]},"assertion":[{"value":"29 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"}}]}}