{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,3]],"date-time":"2026-07-03T19:06:53Z","timestamp":1783105613348,"version":"3.54.6"},"publisher-location":"Cham","reference-count":65,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031732317","type":"print"},{"value":"9783031732324","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,30]],"date-time":"2024-09-30T00:00:00Z","timestamp":1727654400000},"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\/978-3-031-73232-4_23","type":"book-chapter","created":{"date-parts":[[2024,9,29]],"date-time":"2024-09-29T06:01:53Z","timestamp":1727589713000},"page":"405-421","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":31,"title":["SMooDi: Stylized Motion Diffusion Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0003-1778-9282","authenticated-orcid":false,"given":"Lei","family":"Zhong","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0007-8841-9699","authenticated-orcid":false,"given":"Yiming","family":"Xie","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1508-6498","authenticated-orcid":false,"given":"Varun","family":"Jampani","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0329-0456","authenticated-orcid":false,"given":"Deqing","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2300-4237","authenticated-orcid":false,"given":"Huaizu","family":"Jiang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,9,30]]},"reference":[{"key":"23_CR1","doi-asserted-by":"crossref","unstructured":"Aberman, K., Weng, Y., Lischinski, D., Cohen-Or, D., Chen, B.: Unpaired motion style transfer from video to animation. TOG 39(4), 64\u20131 (2020)","DOI":"10.1145\/3386569.3392469"},{"key":"23_CR2","doi-asserted-by":"crossref","unstructured":"Alexanderson, S., Nagy, R., Beskow, J., Henter, G.E.: Listen, denoise, action! audio-driven motion synthesis with diffusion models. TOG 42(4), 1\u201320 (2023)","DOI":"10.1145\/3592458"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Ao, T., Zhang, Z., Liu, L.: Gesturediffuclip: gesture diffusion model with clip latents. TOG 42(4), 1\u201318 (2023)","DOI":"10.1145\/3592097"},{"key":"23_CR4","doi-asserted-by":"crossref","unstructured":"Cen, Z., et al.: Generating human motion in 3D scenes from text descriptions. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00182"},{"key":"23_CR5","unstructured":"Chen, L.H., et al.: MotionLLM: Understanding human behaviors from human motions and videos. ArXiv (2024)"},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Executing your commands via motion diffusion in latent space. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Cohan, S., Tevet, G., Reda, D., Peng, X.B., van\u00a0de Panne, M.: Flexible motion in-betweening with diffusion models. ArXiv (2024)","DOI":"10.1145\/3641519.3657414"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Dabral, R., Mughal, M.H., Golyanik, V., Theobalt, C.: Mofusion: a framework for denoising-diffusion-based motion synthesis. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"23_CR9","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":"23_CR10","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. NeurIPS (2021)"},{"key":"23_CR11","doi-asserted-by":"crossref","unstructured":"Du, H., Herrmann, E., Sprenger, J., Fischer, K., Slusallek, P.: Stylistic locomotion modeling and synthesis using variational generative models. In: Proceedings of the 12th ACM SIGGRAPH Conference on Motion, Interaction and Games (2019)","DOI":"10.1145\/3359566.3360083"},{"key":"23_CR12","doi-asserted-by":"crossref","unstructured":"Everaert, M.N., Bocchio, M., Arpa, S., S\u00fcsstrunk, S., Achanta, R.: Diffusion in style. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00214"},{"key":"23_CR13","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":"23_CR14","doi-asserted-by":"crossref","unstructured":"Guo, C., Mu, Y., Javed, M.G., Wang, S., Cheng, L.: MoMask: generative masked modeling of 3D human motions. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"23_CR15","unstructured":"Guo, C., et al.: Generative human motion stylization in latent space. arXiv preprint arXiv:2401.13505 (2024)"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3D human motions from text. In: CVPR (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"23_CR17","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Diffusion-based generation, optimization, and planning in 3D scenes. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Jang, D.K., Park, S., Lee, S.H.: Motion puzzle: arbitrary motion style transfer by body part. TOG 41(3), 1\u201316 (2022)","DOI":"10.1145\/3516429"},{"key":"23_CR20","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: MotionGPT: human motion as a foreign language. ArXiv preprint arXiv:2306.14795 (2023)"},{"key":"23_CR21","unstructured":"Jones, M., Wang, S.Y., Kumari, N., Bau, D., Zhu, J.Y.: Customizing text-to-image models with a single image pair. arXiv preprint arXiv:2405.01536 (2024)"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Karunratanakul, K., Preechakul, K., Aksan, E., Beeler, T., Suwajanakorn, S., Tang, S.: Optimizing diffusion noise can serve as universal motion priors. Arxiv preprint arXiv:2312.11994 (2023)","DOI":"10.1109\/CVPR52733.2024.00133"},{"key":"23_CR23","unstructured":"Karunratanakul, K., Preechakul, K., Suwajanakorn, S., Tang, S.: GMD: controllable human motion synthesis via guided diffusion models. In: ICCV (2023)"},{"key":"23_CR24","unstructured":"Kim, H.J., Lee, S.H.: Perceptual characteristics by motion style category. In: Eurographics (Short Papers) (2019)"},{"key":"23_CR25","doi-asserted-by":"crossref","unstructured":"Kulkarni, N., et al.: Nifty: neural object interaction fields for guided human motion synthesis. arXiv preprint arXiv:2307.07511 (2023)","DOI":"10.1109\/CVPR52733.2024.00096"},{"key":"23_CR26","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"23_CR27","doi-asserted-by":"crossref","unstructured":"Mason, I., Starke, S., Komura, T.: Real-time style modelling of human locomotion via feature-wise transformations and local motion phases. Proc. ACM on Comput. Graph. Interactive Techniques 5(1), 1\u201318 (2022)","DOI":"10.1145\/3522618"},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Park, S., Jang, D.K., Lee, S.H.: Diverse motion stylization for multiple style domains via spatial-temporal graph-based generative model. Proc. ACM on Comput. Graph. Interactive Techniques 4(3), 1\u201317 (2021)","DOI":"10.1145\/3480145"},{"key":"23_CR29","unstructured":"Peng, X., Xie, Y., Wu, Z., Jampani, V., Sun, D., Jiang, H.: HOI-diff: text-driven synthesis of 3D human-object interactions using diffusion models. ArXiv preprint arXiv:2312.06553 (2023)"},{"key":"23_CR30","doi-asserted-by":"crossref","unstructured":"Peng, X.B., Ma, Z., Abbeel, P., Levine, S., Kanazawa, A.: Amp: adversarial motion priors for stylized physics-based character control. TOG (2021)","DOI":"10.1145\/3476576.3476723"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: TEMOS: generating diverse human motions from textual descriptions. In: ECCV (2022)","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"23_CR32","doi-asserted-by":"crossref","unstructured":"Petrovich, M., et al.: Multi-track timeline control for text-driven 3D human motion generation. In: CVPR (2024)","DOI":"10.1109\/CVPRW63382.2024.00197"},{"key":"23_CR33","doi-asserted-by":"crossref","unstructured":"Pi, H., Peng, S., Yang, M., Zhou, X., Bao, H.: Hierarchical generation of human-object interactions with diffusion probabilistic models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01383"},{"key":"23_CR34","doi-asserted-by":"crossref","unstructured":"Pinyoanuntapong, E., Saleem, M.U., Wang, P., Lee, M., Das, S., Chen, C.: BAMM: bidirectional autoregressive motion model. ArXiv preprint arXiv:2403.19435 (2024)","DOI":"10.1007\/978-3-031-72633-0_10"},{"key":"23_CR35","doi-asserted-by":"crossref","unstructured":"Pinyoanuntapong, E., Wang, P., Lee, M., Chen, C.: MMM: generative masked motion model. In: CVPR (2024)","DOI":"10.1109\/CVPR52733.2024.00153"},{"key":"23_CR36","unstructured":"Raab, S., et al.: Monkey see, monkey do: harnessing self-attention in motion diffusion for zero-shot motion transfer. ArXiv preprint arXiv:2406.06508 (2024)"},{"key":"23_CR37","unstructured":"Raab, S., Leibovitch, I., Tevet, G., Arar, M., Bermano, A.H., Cohen-Or, D.: Single motion diffusion. ArXiv preprint arXiv:2302.05905 (2023)"},{"key":"23_CR38","unstructured":"Radford, A., et\u00a0al.: Learning transferable visual models from natural language supervision. In: ICML (2021)"},{"key":"23_CR39","doi-asserted-by":"crossref","unstructured":"Rempe, D., et al.: Trace and pace: controllable pedestrian animation via guided trajectory diffusion. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.01322"},{"key":"23_CR40","doi-asserted-by":"crossref","unstructured":"Ruiz, N., Li, Y., Jampani, V., Pritch, Y., Rubinstein, M., Aberman, K.: DreamBooth: fine tuning text-to-image diffusion models for subject-driven generation. In: CVPR (2023)","DOI":"10.1109\/CVPR52729.2023.02155"},{"key":"23_CR41","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior. ArXiv preprint arXiv:2303.01418 (2023)"},{"key":"23_CR42","doi-asserted-by":"crossref","unstructured":"Shah, V., Ruiz, N., Cole, F., Lu, E., Lazebnik, S., Li, Y., Jampani, V.: Ziplora: any subject in any style by effectively merging loras. ArXiv preprint arXiv:2311.13600 (2023)","DOI":"10.1007\/978-3-031-73232-4_24"},{"key":"23_CR43","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. ArXiv preprint arXiv:2010.02502 (2020)"},{"key":"23_CR44","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. ArXiv preprint arXiv:2303.01469 (2023)"},{"key":"23_CR45","doi-asserted-by":"crossref","unstructured":"Tao, T., Zhan, X., Chen, Z., van\u00a0de Panne, M.: Style-ERD: responsive and coherent online motion style transfer. Arxiv preprint arXiv:2203.02574 (2022)","DOI":"10.1109\/CVPR52688.2022.00648"},{"key":"23_CR46","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., Bermano, A.H.: Human motion diffusion model. In: ICLR (2023)"},{"key":"23_CR47","unstructured":"Wan, W., Dou, Z., Komura, T., Wang, W., Jayaraman, D., Liu, L.: TLcontrol: trajectory and language control for human motion synthesis. ArXiv preprint arXiv:2311.17135 (2023)"},{"key":"23_CR48","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":"23_CR49","doi-asserted-by":"crossref","unstructured":"Wen, Y.H., Yang, Z., Fu, H., Gao, L., Sun, Y., Liu, Y.J.: Autoregressive stylized motion synthesis with generative flow. In: CVPR (2021)","DOI":"10.1109\/CVPR46437.2021.01340"},{"key":"23_CR50","unstructured":"Wu, Q., Zhao, Y., Wang, Y., Tai, Y.W., Tang, C.K.: MotionLLM: multimodal motion-language learning with large language models. ArXiv preprint arXiv:2405170 (2024)"},{"key":"23_CR51","unstructured":"Wu, Q., Shi, Y., Huang, X., Yu, J., Xu, L., Wang, J.: Thor: text to human-object interaction diffusion via relation intervention. ArXiv preprint arXiv:2403.11208 (2024)"},{"key":"23_CR52","doi-asserted-by":"crossref","unstructured":"Xia, S., Wang, C., Chai, J., Hodgins, J.: Realtime style transfer for unlabeled heterogeneous human motion. TOG (2015)","DOI":"10.1145\/2766999"},{"key":"23_CR53","unstructured":"Xie, Y., Jampani, V., Zhong, L., Sun, D., Jiang, H.: OmniControl: control any joint at any time for human motion generation. In: ICLR (2024)"},{"key":"23_CR54","doi-asserted-by":"crossref","unstructured":"Xu, P., et al.: Adaptnet: policy adaptation for physics-based character control. TOG (2023)","DOI":"10.1145\/3618375"},{"key":"23_CR55","unstructured":"Xu, S., Ma, Z., Huang, Y., Lee, H., Chai, J.: CycleNet: rethinking cycle consistency in text-guided diffusion for image manipulation. NeurIPS (2024)"},{"key":"23_CR56","doi-asserted-by":"crossref","unstructured":"Xu, S., Li, Z., Wang, Y.X., Gui, L.Y.: InterDiff: Generating 3D human-object interactions with physics-informed diffusion. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01371"},{"key":"23_CR57","unstructured":"Xu, S., Wang, Z., Wang, Y.X., Gui, L.Y.: InterDreamer: zero-shot text to 3D dynamic human-object interaction. ArXiv preprint arXiv:2403.19652 (2024)"},{"key":"23_CR58","doi-asserted-by":"crossref","unstructured":"Yi, H., Thies, J., Black, M.J., Peng, X.B., Rempe, D.: Generating human interaction motions in scenes with text control. ArXiv preprint arXiv:2404.1068 (2024)","DOI":"10.1007\/978-3-031-73235-5_14"},{"key":"23_CR59","doi-asserted-by":"crossref","unstructured":"Yu, J., Wang, Y., Zhao, C., Ghanem, B., Zhang, J.: FreeDom: training-free energy-guided conditional diffusion model. ArXiv preprint arXiv:2303.0983 (2023)","DOI":"10.1109\/ICCV51070.2023.02118"},{"key":"23_CR60","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Song, J., Iqbal, U., Vahdat, A., Kautz, J.: PhysDiff: physics-guided human motion diffusion model. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"23_CR61","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"23_CR62","doi-asserted-by":"crossref","unstructured":"Zhang, M., Cai, Z., Pan, L., Hong, F., Guo, X., Yang, L., Liu, Z.: MotionDiffuse: text-driven human motion generation with diffusion model. PAMI (2024)","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"23_CR63","unstructured":"Zhang, Y., et al.: MotionGPT: finetuned LLMs are general-purpose motion generators. ArXiv preprint arXiv:2306.10900 (2023)"},{"key":"23_CR64","doi-asserted-by":"crossref","unstructured":"Zhou, W., et al.: EMDM: efficient motion diffusion model for fast, high-quality motion generation. Arxiv preprint arXiv:2312.02256 (2023)","DOI":"10.1007\/978-3-031-72627-9_2"},{"key":"23_CR65","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Barnes, C., Lu, J., Yang, J., Li, H.: On the continuity of rotation representations in neural networks. In: CVPR (2019)","DOI":"10.1109\/CVPR.2019.00589"}],"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\/978-3-031-73232-4_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,28]],"date-time":"2024-11-28T21:15:32Z","timestamp":1732828532000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73232-4_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,30]]},"ISBN":["9783031732317","9783031732324"],"references-count":65,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73232-4_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,9,30]]},"assertion":[{"value":"30 September 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"}}]}}