{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T16:42:08Z","timestamp":1780418528324,"version":"3.54.1"},"publisher-location":"Cham","reference-count":86,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031726392","type":"print"},{"value":"9783031726408","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\/978-3-031-72640-8_22","type":"book-chapter","created":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T09:34:20Z","timestamp":1730108060000},"page":"390-408","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":61,"title":["MotionLCM: Real-Time Controllable Motion Generation via Latent Consistency Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0004-1465-3739","authenticated-orcid":false,"given":"Wenxun","family":"Dai","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2528-6178","authenticated-orcid":false,"given":"Ling-Hao","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-0740-8548","authenticated-orcid":false,"given":"Jingbo","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-8689-8248","authenticated-orcid":false,"given":"Jinpeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0777-9232","authenticated-orcid":false,"given":"Bo","family":"Dai","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-1534-4549","authenticated-orcid":false,"given":"Yansong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,10,29]]},"reference":[{"key":"22_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, H., Ha, T., Choi, Y., Yoo, H., Oh, S.: Text2action: generative adversarial synthesis from language to action. In: ICRA, pp. 5915\u20135920 (2018)","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"22_CR2","doi-asserted-by":"crossref","unstructured":"Ahuja, C., Morency, L.P.: Language2pose: natural language grounded pose forecasting. In: 3DV, pp. 719\u2013728 (2019)","DOI":"10.1109\/3DV.2019.00084"},{"key":"22_CR3","doi-asserted-by":"crossref","unstructured":"Athanasiou, N., Petrovich, M., Black, M.J., Varol, G.: Teach: temporal action composition for 3D humans. In: 3DV, pp. 414\u2013423 (2022)","DOI":"10.1109\/3DV57658.2022.00053"},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Barquero, G., Escalera, S., Palmero, C.: Seamless human motion composition with blended positional encodings. In: CVPR, pp. 457\u2013469 (2024)","DOI":"10.1109\/CVPR52733.2024.00051"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Bhattacharya, U., Rewkowski, N., Banerjee, A., Guhan, P., Bera, A., Manocha, D.: Text2gestures: a transformer-based network for generating emotive body gestures for virtual agents. In: VR, pp. 1\u201310 (2021)","DOI":"10.1109\/VR50410.2021.00037"},{"key":"22_CR6","doi-asserted-by":"publisher","unstructured":"Cervantes, P., Sekikawa, Y., Sato, I., Shinoda, K.: Implicit neural representations for variable length human motion generation. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds) ECCV 2022. LNCS, vol. 13677, pp. 356\u2013372. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19790-1_22","DOI":"10.1007\/978-3-031-19790-1_22"},{"key":"22_CR7","unstructured":"Chen, L.H., et al.: Motionllm: understanding human behaviors from human motions and videos. arXiv preprint arXiv:2405.20340 (2024)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Chen, L.H., Zhang, J., Li, Y., Pang, Y., Xia, X., Liu, T.: HumanMAC: masked motion completion for human motion prediction. In: ICCV, pp. 9544\u20139555 (2023)","DOI":"10.1109\/ICCV51070.2023.00875"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Chen, X., et al.: Executing your commands via motion diffusion in latent space. In: CVPR, pp. 18000\u201318010 (2023)","DOI":"10.1109\/CVPR52729.2023.01726"},{"key":"22_CR10","unstructured":"Cong, P., et al.: Laserhuman: language-guided scene-aware human motion generation in free environment. arXiv preprint arXiv:2403.13307 (2024)"},{"key":"22_CR11","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, pp. 9760\u20139770 (2023)","DOI":"10.1109\/CVPR52729.2023.00941"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Dou, Z., Chen, X., Fan, Q., Komura, T., Wang, W.: C\u00b7 ase: learning conditional adversarial skill embeddings for physics-based characters. In: SIGGRAPH Asia, pp. 1\u201311 (2023)","DOI":"10.1145\/3610548.3618205"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Fan, K., et al.: Freemotion: a unified framework for number-free text-to-motion synthesis. arXiv preprint arXiv:2405.15763 (2024)","DOI":"10.1007\/978-3-031-73242-3_6"},{"key":"22_CR14","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Cheema, N., Oguz, C., Theobalt, C., Slusallek, P.: Synthesis of compositional animations from textual descriptions. In: ICCV, pp. 1396\u20131406 (2021)","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"22_CR15","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, pp. 1900\u20131910 (2024)","DOI":"10.1109\/CVPR52733.2024.00186"},{"key":"22_CR16","unstructured":"Guo, C., et al.: Generative human motion stylization in latent space. arXiv preprint arXiv:2401.13505 (2024)"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Generating diverse and natural 3D human motions from text. In: CVPR, pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"22_CR18","series-title":"LNCS","doi-asserted-by":"publisher","first-page":"580","DOI":"10.1007\/978-3-031-19833-5_34","volume-title":"ECCV 2022","author":"C Guo","year":"2022","unstructured":"Guo, C., Zuo, X., Wang, S., Cheng, L.: TM2T: stochastic and tokenized modeling for the reciprocal generation of 3D human motions and texts. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13695, pp. 580\u2013597. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19833-5_34"},{"key":"22_CR19","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Action2motion: conditioned generation of 3D human motions. In: ACMMM, pp. 2021\u20132029 (2020)","DOI":"10.1145\/3394171.3413635"},{"key":"22_CR20","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: NeurIPS, pp. 6840\u20136851 (2020)"},{"key":"22_CR21","unstructured":"Ho, J., Salimans, T.: Classifier-free diffusion guidance. arXiv preprint arXiv:2207.12598 (2022)"},{"issue":"4","key":"22_CR22","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073663","volume":"36","author":"D Holden","year":"2017","unstructured":"Holden, D., Komura, T., Saito, J.: Phase-functioned neural networks for character control. TOG 36(4), 1\u201313 (2017)","journal-title":"TOG"},{"issue":"4","key":"22_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925975","volume":"35","author":"D Holden","year":"2016","unstructured":"Holden, D., Saito, J., Komura, T.: A deep learning framework for character motion synthesis and editing. TOG 35(4), 1\u201311 (2016)","journal-title":"TOG"},{"key":"22_CR24","doi-asserted-by":"crossref","unstructured":"Huang, Y., et al.: Stablemofusion: towards robust and efficient diffusion-based motion generation framework. arXiv preprint arXiv:2405.05691 (2024)","DOI":"10.1145\/3664647.3681657"},{"issue":"1","key":"22_CR25","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1214\/aoms\/1177703732","volume":"35","author":"PJ Huber","year":"1964","unstructured":"Huber, P.J.: Robust estimation of a location parameter. Ann. Math. Stat. 35(1), 73\u2013101 (1964)","journal-title":"Ann. Math. Stat."},{"key":"22_CR26","doi-asserted-by":"crossref","unstructured":"Ji, Y., Xu, F., Yang, Y., Shen, F., Shen, H.T., Zheng, W.S.: a large-scale RGB-D database for arbitrary-view human action recognition. In: ACMMM, pp. 1510\u20131518 (2018)","DOI":"10.1145\/3240508.3240675"},{"key":"22_CR27","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: MotionGPT: human motion as a foreign language. In: NeurIPS (2024)"},{"key":"22_CR28","unstructured":"Karras, T., Aittala, M., Aila, T., Laine, S.: Elucidating the design space of diffusion-based generative models. In: NeurIPS, pp. 26565\u201326577 (2022)"},{"key":"22_CR29","doi-asserted-by":"crossref","unstructured":"Karunratanakul, K., Preechakul, K., Suwajanakorn, S., Tang, S.: Guided motion diffusion for controllable human motion synthesis. In: CVPR, pp. 2151\u20132162 (2023)","DOI":"10.1109\/ICCV51070.2023.00205"},{"key":"22_CR30","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"22_CR31","doi-asserted-by":"crossref","unstructured":"Lee, T., Moon, G., Lee, K.M.: Multiact: long-term 3D human motion generation from multiple action labels. In: AAAI, pp. 1231\u20131239 (2023)","DOI":"10.1609\/aaai.v37i1.25206"},{"key":"22_CR32","doi-asserted-by":"crossref","unstructured":"Li, B., Zhao, Y., Zhelun, S., Sheng, L.: Danceformer: music conditioned 3D dance generation with parametric motion transformer. In: AAAI, pp. 1272\u20131279 (2022)","DOI":"10.1609\/aaai.v36i2.20014"},{"key":"22_CR33","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Lodge: a coarse to fine diffusion network for long dance generation guided by the characteristic dance primitives. In: CVPR, pp. 1524\u20131534 (2024)","DOI":"10.1109\/CVPR52733.2024.00151"},{"key":"22_CR34","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Finedance: a fine-grained choreography dataset for 3D full body dance generation. In: ICCV, pp. 10234\u201310243 (2023)","DOI":"10.1109\/ICCV51070.2023.00939"},{"key":"22_CR35","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with aist++. In: ICCV, pp. 13401\u201313412 (2021)","DOI":"10.1109\/ICCV48922.2021.01315"},{"key":"22_CR36","doi-asserted-by":"crossref","unstructured":"Li, T., Qiao, C., Ren, G., Yin, K., Ha, S.: AAMDM: accelerated auto-regressive motion diffusion model. In: CVPR, pp. 1813\u20131823 (2024)","DOI":"10.1109\/CVPR52733.2024.00178"},{"issue":"2018","key":"22_CR37","first-page":"1","volume":"1","author":"AS Lin","year":"2018","unstructured":"Lin, A.S., Wu, L., Corona, R., Tai, K., Huang, Q., Mooney, R.J.: Generating animated videos of human activities from natural language descriptions. Learning 1(2018), 1 (2018)","journal-title":"Learning"},{"key":"22_CR38","unstructured":"Lin, X., Amer, M.R.: Human motion modeling using DVGANs. arXiv preprint arXiv:1804.10652 (2018)"},{"key":"22_CR39","doi-asserted-by":"crossref","unstructured":"Liu, J., Dai, W., Wang, C., Cheng, Y., Tang, Y., Tong, X.: Plan, posture and go: towards open-world text-to-motion generation. arXiv preprint arXiv:2312.14828 (2023)","DOI":"10.1007\/978-3-031-73383-3_26"},{"key":"22_CR40","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"22_CR41","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver: a fast ode solver for diffusion probabilistic model sampling in around 10 steps. In: NeurIPS, pp. 5775\u20135787 (2022)"},{"key":"22_CR42","unstructured":"Lu, C., Zhou, Y., Bao, F., Chen, J., Li, C., Zhu, J.: DPM-solver++: fast solver for guided sampling of diffusion probabilistic models. arXiv preprint arXiv:2211.01095 (2022)"},{"key":"22_CR43","unstructured":"Lu, S., et al.: Humantomato: text-aligned whole-body motion generation. arXiv preprint arXiv:2310.12978 (2023)"},{"key":"22_CR44","unstructured":"Luo, S., Tan, Y., Huang, L., Li, J., Zhao, H.: Latent consistency models: synthesizing high-resolution images with few-step inference. arXiv preprint arXiv:2310.04378 (2023)"},{"key":"22_CR45","doi-asserted-by":"crossref","unstructured":"Mahmood, N., Ghorbani, N., Troje, N.F., Pons-Moll, G., Black, M.J.: Amass: archive of motion capture as surface shapes. In: ICCV, pp. 5442\u20135451 (2019)","DOI":"10.1109\/ICCV.2019.00554"},{"key":"22_CR46","unstructured":"Nichol, A.Q., Dhariwal, P.: Improved denoising diffusion probabilistic models. In: ICML, pp. 8162\u20138171 (2021)"},{"key":"22_CR47","unstructured":"Paszke, A, et\u00a0al.: Pytorch: an imperative style, high-performance deep learning library. In: NeurIPS (2019)"},{"key":"22_CR48","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: ICCV, pp. 10985\u201310995 (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"22_CR49","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.) 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":"22_CR50","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: TMR: text-to-motion retrieval using contrastive 3D human motion synthesis. In: ICCV, pp. 9488\u20139497 (2023)","DOI":"10.1109\/ICCV51070.2023.00870"},{"key":"22_CR51","doi-asserted-by":"crossref","unstructured":"Petrovich, M., et al.: Multi-track timeline control for text-driven 3D human motion generation. In: CVPRW, pp. 1911\u20131921 (2024)","DOI":"10.1109\/CVPRW63382.2024.00197"},{"issue":"4","key":"22_CR52","doi-asserted-by":"publisher","first-page":"236","DOI":"10.1089\/big.2016.0028","volume":"4","author":"M Plappert","year":"2016","unstructured":"Plappert, M., Mandery, C., Asfour, T.: The kit motion-language dataset. Big Data 4(4), 236\u2013252 (2016)","journal-title":"Big Data"},{"key":"22_CR53","doi-asserted-by":"crossref","unstructured":"Punnakkal, A.R., Chandrasekaran, A., Athanasiou, N., Quiros-Ramirez, A., Black, M.J.: Babel: bodies, action and behavior with English labels. In: CVPR, pp. 722\u2013731 (2021)","DOI":"10.1109\/CVPR46437.2021.00078"},{"key":"22_CR54","doi-asserted-by":"crossref","unstructured":"Raab, S., Leibovitch, I., Li, P., Aberman, K., Sorkine-Hornung, O., Cohen-Or, D.: Modi: unconditional motion synthesis from diverse data. In: CVPR, pp. 13873\u201313883 (2023)","DOI":"10.1109\/CVPR52729.2023.01333"},{"key":"22_CR55","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: CVPR, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"22_CR56","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior. In: ICLR (2024)"},{"key":"22_CR57","doi-asserted-by":"crossref","unstructured":"Shahroudy, A., Liu, J., Ng, T.T., Wang, G.: NTU RGB+ D: a large scale dataset for 3D human activity analysis. In: CVPR, pp. 1010\u20131019 (2016)","DOI":"10.1109\/CVPR.2016.115"},{"key":"22_CR58","unstructured":"Shi, Y., Wang, J., Jiang, X., Dai, B.: Controllable motion diffusion model. arXiv preprint arXiv:2306.00416 (2023)"},{"key":"22_CR59","doi-asserted-by":"crossref","unstructured":"Siyao, L., et al.: Bailando: 3D dance generation by actor-critic GPT with choreographic memory. In: CVPR, pp. 11050\u201311059 (2022)","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"22_CR60","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: ICML, pp. 2256\u20132265 (2015)"},{"key":"22_CR61","unstructured":"Song, J., Meng, C., Ermon, S.: Denoising diffusion implicit models. In: ICLR (2021)"},{"key":"22_CR62","unstructured":"Song, Y., Dhariwal, P., Chen, M., Sutskever, I.: Consistency models. In: ICML (2023)"},{"key":"22_CR63","doi-asserted-by":"crossref","unstructured":"Tang, Y., et al.: Flag3D: a 3D fitness activity dataset with language instruction. In: CVPR, pp. 22106\u201322117 (2023)","DOI":"10.1109\/CVPR52729.2023.02117"},{"key":"22_CR64","doi-asserted-by":"publisher","unstructured":"Tevet, G., Gordon, B., Hertz, A., Bermano, A.H., Cohen-Or, D.: Motionclip: exposing human motion generation to clip space. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13682, pp. 358\u2013374. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20047-2_21","DOI":"10.1007\/978-3-031-20047-2_21"},{"key":"22_CR65","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human motion diffusion model. In: ICLR (2022)"},{"key":"22_CR66","doi-asserted-by":"crossref","unstructured":"Tseng, J., Castellon, R., Liu, K.: Edge: editable dance generation from music. In: CVPR, pp. 448\u2013458 (2023)","DOI":"10.1109\/CVPR52729.2023.00051"},{"key":"22_CR67","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NeurIPS (2017)"},{"key":"22_CR68","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":"22_CR69","doi-asserted-by":"crossref","unstructured":"Wang, Z., et al.: Move as you say interact as you can: language-guided human motion generation with scene affordance. In: CVPR, pp. 433\u2013444 (2024)","DOI":"10.1109\/CVPR52733.2024.00049"},{"key":"22_CR70","unstructured":"Wang, Z., Chen, Y., Liu, T., Zhu, Y., Liang, W., Huang, S.: Humanise: language-conditioned human motion generation in 3D scenes. In: NeurIPS, pp. 14959\u201314971 (2022)"},{"key":"22_CR71","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":"22_CR72","unstructured":"Xiao, Z., et al.: Unified human-scene interaction via prompted chain-of-contacts. In: ICLR (2024)"},{"key":"22_CR73","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":"22_CR74","doi-asserted-by":"crossref","unstructured":"Xu, L., et\u00a0al.: Inter-x: towards versatile human-human interaction analysis. In: CVPR, pp. 22260\u201322271 (2024)","DOI":"10.1109\/CVPR52733.2024.02101"},{"key":"22_CR75","doi-asserted-by":"crossref","unstructured":"Xu, L., et\u00a0al.: Actformer: a GAN-based transformer towards general action-conditioned 3D human motion generation. In: ICCV, pp. 2228\u20132238 (2023)","DOI":"10.1109\/ICCV51070.2023.00212"},{"key":"22_CR76","doi-asserted-by":"crossref","unstructured":"Xu, L., et al.: RegenNet: towards human action-reaction synthesis. In: CVPR, pp. 1759\u20131769 (2024)","DOI":"10.1109\/CVPR52733.2024.00173"},{"key":"22_CR77","doi-asserted-by":"crossref","unstructured":"Yan, S., Li, Z., Xiong, Y., Yan, H., Lin, D.: Convolutional sequence generation for skeleton-based action synthesis. In: ICCV, pp. 4394\u20134402 (2019)","DOI":"10.1109\/ICCV.2019.00449"},{"key":"22_CR78","doi-asserted-by":"crossref","unstructured":"Yuan, Y., Song, J., Iqbal, U., Vahdat, A., Kautz, J.: PhysDiff: physics-guided human motion diffusion model. In: ICCV, pp. 16010\u201316021 (2023)","DOI":"10.1109\/ICCV51070.2023.01467"},{"key":"22_CR79","unstructured":"Zhang, B., et al.: RodinHD: high-fidelity 3D avatar generation with diffusion models. arXiv preprint arXiv:2407.06938 (2024)"},{"key":"22_CR80","unstructured":"Zhang, B., et al.: Gaussiancube: structuring gaussian splatting using optimal transport for 3D generative modeling. arXiv preprint arXiv:2403.19655 (2024)"},{"key":"22_CR81","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: Generating human motion from textual descriptions with discrete representations. In: CVPR, pp. 14730\u201314740 (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"22_CR82","doi-asserted-by":"crossref","unstructured":"Zhang, L., Rao, A., Agrawala, M.: Adding conditional control to text-to-image diffusion models. In: ICCV, pp. 3836\u20133847 (2023)","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"22_CR83","unstructured":"Zhang, M., et al.: Motiondiffuse: text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001 (2022)"},{"key":"22_CR84","doi-asserted-by":"crossref","unstructured":"Zhao, R., Su, H., Ji, Q.: Bayesian adversarial human motion synthesis. In: CVPR, pp. 6225\u20136234 (2020)","DOI":"10.1109\/CVPR42600.2020.00626"},{"key":"22_CR85","doi-asserted-by":"crossref","unstructured":"Zhong, L., Xie, Y., Jampani, V., Sun, D., Jiang, H.: Smoodi: stylized motion diffusion model. arXiv preprint arXiv:2407.12783 (2024)","DOI":"10.1007\/978-3-031-73232-4_23"},{"key":"22_CR86","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"}],"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\/978-3-031-72640-8_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,30]],"date-time":"2024-11-30T10:30:49Z","timestamp":1732962649000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-72640-8_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,29]]},"ISBN":["9783031726392","9783031726408"],"references-count":86,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-72640-8_22","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"}}]}}