{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,14]],"date-time":"2026-05-14T23:47:41Z","timestamp":1778802461630,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":77,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819636785","type":"print"},{"value":"9789819636792","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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\/978-981-96-3679-2_1","type":"book-chapter","created":{"date-parts":[[2025,4,8]],"date-time":"2025-04-08T21:20:57Z","timestamp":1744147257000},"page":"1-17","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Motion Generation Review: Exploring Deep Learning for\u00a0Lifelike Animation with\u00a0Manifold"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3789-000X","authenticated-orcid":false,"given":"Jiayi","family":"Zhao","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2352-0896","authenticated-orcid":false,"given":"Dongdong","family":"Weng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5991-9482","authenticated-orcid":false,"given":"Qiuxin","family":"Du","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zeyu","family":"Tian","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,3,30]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Ahn, H., Ha, T., Choi, Y., Yoo, H., Oh, S.: Text2Action: Generative Adversarial Synthesis from Language to Action (2017). http:\/\/arxiv.org\/abs\/1710.05298. arXiv:1710.05298","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"1_CR2","doi-asserted-by":"crossref","unstructured":"Ahuja, C., Morency, L.P.: Language2Pose: Natural Language Grounded Pose Forecasting (2019). http:\/\/arxiv.org\/abs\/1907.01108. arXiv:1907.01108","DOI":"10.1109\/3DV.2019.00084"},{"key":"1_CR3","doi-asserted-by":"publisher","unstructured":"Arikan, O., Forsyth, D.A.: Interactive motion generation from examples. ACM Trans. Graph. 21(3), 483\u2013490 (2002). https:\/\/doi.org\/10.1145\/566654.566606","DOI":"10.1145\/566654.566606"},{"key":"1_CR4","unstructured":"Bishop, R.L., Crittenden, R.J.: Geometry of Manifolds: Geometry of Manifolds. Academic Press (2011)"},{"key":"1_CR5","doi-asserted-by":"publisher","unstructured":"Chai, J., Hodgins, J.K.: Performance animation from low-dimensional control signals. ACM Trans. Graph. 24(3), 686\u2013696 (2005). https:\/\/doi.org\/10.1145\/1073204.1073248","DOI":"10.1145\/1073204.1073248"},{"key":"1_CR6","unstructured":"Chopin, B., Otberdout, N., Daoudi, M., Bartolo, A.: Human Motion Prediction Using Manifold-Aware Wasserstein GAN (2021). http:\/\/arxiv.org\/abs\/2105.08715. arXiv:2105.08715"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Degardin, B., Neves, J., Lopes, V., Brito, J., Yaghoubi, E., Proen\u00e7a, H.: Generative adversarial graph convolutional networks for human action synthesis. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp. 1150\u20131159 (2022)","DOI":"10.1109\/WACV51458.2022.00281"},{"key":"1_CR8","doi-asserted-by":"publisher","unstructured":"Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: 2015 IEEE International Conference on Computer Vision (ICCV), pp. 4346\u20134354. IEEE, Santiago, Chile (2015). https:\/\/doi.org\/10.1109\/ICCV.2015.494. http:\/\/ieeexplore.ieee.org\/document\/7410851\/","DOI":"10.1109\/ICCV.2015.494"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Gall, J., Stoll, C., De\u00a0Aguiar, E., Theobalt, C., Rosenhahn, B., Seidel, H.P.: Motion capture using joint skeleton tracking and surface estimation. In: 2009 IEEE Conference on Computer Vision and Pattern Recognition, pp. 1746\u20131753. IEEE (2009)","DOI":"10.1109\/CVPR.2009.5206755"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Ghosh, A., Cheema, N., Oguz, C., Theobalt, C., Slusallek, P.: Synthesis of compositional animations from textual descriptions. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 1396\u20131406 (2021)","DOI":"10.1109\/ICCV48922.2021.00143"},{"key":"1_CR11","doi-asserted-by":"publisher","unstructured":"Goodfellow, I., et al.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020). https:\/\/doi.org\/10.1145\/3422622","DOI":"10.1145\/3422622"},{"key":"1_CR12","doi-asserted-by":"publisher","unstructured":"Grochow, K., Martin, S.L., Hertzmann, A., Popovi\u0107, Z.: Style-based inverse kinematics. In: ACM SIGGRAPH 2004 Papers, pp. 522\u2013531. ACM, Los Angeles California (2004). https:\/\/doi.org\/10.1145\/1186562.1015755. https:\/\/dl.acm.org\/doi\/10.1145\/1186562.1015755","DOI":"10.1145\/1186562.1015755"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Guo, C., Zou, S., Zuo, X., Wang, S., Ji, W., Li, X., Cheng, L.: 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":"1_CR14","doi-asserted-by":"publisher","unstructured":"Habibie, I., Holden, D., Schwarz, J., Yearsley, J., Komura, T.: A recurrent variational autoencoder for human motion synthesis. In: Procedings of the British Machine Vision Conference 2017, p.\u00a0119. British Machine Vision Association, London, UK (2017). https:\/\/doi.org\/10.5244\/C.31.119. http:\/\/www.bmva.org\/bmvc\/2017\/papers\/paper119\/index.html","DOI":"10.5244\/C.31.119"},{"key":"1_CR15","doi-asserted-by":"crossref","unstructured":"Hassan, M., Ghosh, P., Tesch, J., Tzionas, D., Black, M.J.: Populating 3D scenes by learning human-scene interaction. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14708\u201314718 (2021)","DOI":"10.1109\/CVPR46437.2021.01447"},{"key":"1_CR16","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising Diffusion Probabilistic Models (2020). http:\/\/arxiv.org\/abs\/2006.11239. arXiv:2006.11239"},{"key":"1_CR17","unstructured":"Hodgins, C.M.U.: CMU graphics lab motion capture database (2015). http:\/\/mocap.cs.cmu.edu\/"},{"key":"1_CR18","unstructured":"Holden, D.: Reducing animator keyframes. Ph.D. thesis, The University of Edinburgh (2017)"},{"key":"1_CR19","doi-asserted-by":"publisher","unstructured":"Holden, D., Komura, T., Saito, J.: Phase-functioned neural networks for character control. ACM Trans. Graph. 36(4), 1\u201313 (2017). https:\/\/doi.org\/10.1145\/3072959.3073663. https:\/\/dl.acm.org\/doi\/10.1145\/3072959.3073663","DOI":"10.1145\/3072959.3073663"},{"key":"1_CR20","doi-asserted-by":"publisher","unstructured":"Holden, D., Saito, J., Komura, T.: A deep learning framework for character motion synthesis and editing. ACM Trans. Graph. 35(4), 1\u201311 (2016). https:\/\/doi.org\/10.1145\/2897824.2925975. https:\/\/dl.acm.org\/doi\/10.1145\/2897824.2925975","DOI":"10.1145\/2897824.2925975"},{"key":"1_CR21","doi-asserted-by":"publisher","unstructured":"Holden, D., Saito, J., Komura, T., Joyce, T.: Learning motion manifolds with convolutional autoencoders. In: SIGGRAPH Asia 2015 Technical Briefs, pp.\u00a01\u20134. ACM, Kobe Japan (2015). https:\/\/doi.org\/10.1145\/2820903.2820918. https:\/\/dl.acm.org\/doi\/10.1145\/2820903.2820918","DOI":"10.1145\/2820903.2820918"},{"key":"1_CR22","doi-asserted-by":"crossref","unstructured":"Huang, S., et al.: Diffusion-based Generation, Optimization, and Planning in 3D Scenes (2023). http:\/\/arxiv.org\/abs\/2301.06015. arXiv:2301.06015","DOI":"10.1109\/CVPR52729.2023.01607"},{"key":"1_CR23","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Papava, D., Olaru, V., Sminchisescu, C.: Human3.6m: large scale datasets and predictive methods for 3D human sensing in natural environments. IEEE Trans. Pattern Anal. Mach. Intell. 36(7), 1325\u20131339 (2013)","DOI":"10.1109\/TPAMI.2013.248"},{"key":"1_CR24","doi-asserted-by":"publisher","unstructured":"Jang, D.K., Lee, S.H.: Constructing human motion manifold with sequential networks. Comput. Graph. Forum 39(6), 314\u2013324 (2020). https:\/\/doi.org\/10.1111\/cgf.14028. http:\/\/arxiv.org\/abs\/2005.14370. arXiv:2005.14370","DOI":"10.1111\/cgf.14028"},{"key":"1_CR25","unstructured":"Jiang, B., Chen, X., Liu, W., Yu, J., Yu, G., Chen, T.: MotionGPT: Human Motion as a Foreign Language (2023). http:\/\/arxiv.org\/abs\/2306.14795. arXiv:2306.14795"},{"key":"1_CR26","unstructured":"Karras, T., Aila, T., Laine, S., Lehtinen, J.: Progressive Growing of GANs for Improved Quality, Stability, and Variation (2018). http:\/\/arxiv.org\/abs\/1710.10196. arXiv:1710.10196"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aila, T.: A style-based generator architecture for generative adversarial networks. IEEE Trans. Pattern Anal. Mach. Intell. 43(12), 4217\u20134228 (2021). https:\/\/doi.org\/10.1109\/TPAMI.2020.2970919","DOI":"10.1109\/TPAMI.2020.2970919"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Karras, T., Laine, S., Aittala, M., Hellsten, J., Lehtinen, J., Aila, T.: Analyzing and improving the image quality of stylegan. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8110\u20138119 (2020)","DOI":"10.1109\/CVPR42600.2020.00813"},{"key":"1_CR29","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"1_CR30","doi-asserted-by":"publisher","unstructured":"Kovar, L., Gleicher, M.: Automated extraction and parameterization of motions in large data sets. ACM Trans. Graph. 23(3), 559\u2013568 (2004). https:\/\/doi.org\/10.1145\/1015706.1015760","DOI":"10.1145\/1015706.1015760"},{"key":"1_CR31","doi-asserted-by":"publisher","unstructured":"Kovar, L., Gleicher, M., Pighin, F.: Motion graphs. ACM Trans. Graph. 21(3), 473\u2013482 (2002). https:\/\/doi.org\/10.1145\/566654.566605","DOI":"10.1145\/566654.566605"},{"key":"1_CR32","unstructured":"Lawrence, N.: Gaussian process latent variable models for visualisation of high dimensional data. In: Advances in Neural Information Processing Systems, vol.\u00a016. MIT Press (2003). https:\/\/proceedings.neurips.cc\/paper_files\/paper\/2003\/hash\/9657c1fffd38824e5ab0472e022e577e-Abstract.html"},{"key":"1_CR33","doi-asserted-by":"publisher","unstructured":"Le, N., Pham, T., Do, T., Tjiputra, E., Tran, Q.D., Nguyen, A.: Music-driven group choreography. In: 2023 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 8673\u20138682. IEEE, Vancouver, BC, Canada (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00838. https:\/\/ieeexplore.ieee.org\/document\/10205408\/","DOI":"10.1109\/CVPR52729.2023.00838"},{"key":"1_CR34","unstructured":"Lee, J.M.: Manifolds and differential geometry, vol.\u00a0107. American Mathematical Society (2022)"},{"key":"1_CR35","doi-asserted-by":"publisher","unstructured":"Lee, J., Chai, J., Reitsma, P.S., Hodgins, J.K., Pollard, N.S.: Interactive control of avatars animated with human motion data. In: Proceedings of the 29th Annual Conference on Computer Graphics and Interactive Techniques, pp. 491\u2013500 (2002). https:\/\/doi.org\/10.1145\/566570.566607","DOI":"10.1145\/566570.566607"},{"key":"1_CR36","doi-asserted-by":"publisher","unstructured":"Lee, Y., Wampler, K., Bernstein, G., Popovi\u0107, J., Popovi\u0107, Z.: Motion fields for interactive character locomotion. ACM Trans. Graph. 29(6) (2010). https:\/\/doi.org\/10.1145\/1882261.1866160","DOI":"10.1145\/1882261.1866160"},{"key":"1_CR37","doi-asserted-by":"publisher","unstructured":"Levine, S., Lee, Y., Koltun, V., Popovi\u0107, Z.: Space-time planning with parameterized locomotion controllers. ACM Trans. Graph. 30(3), 1\u201311 (2011). https:\/\/doi.org\/10.1145\/1966394.1966402. https:\/\/dl.acm.org\/doi\/10.1145\/1966394.1966402","DOI":"10.1145\/1966394.1966402"},{"key":"1_CR38","doi-asserted-by":"publisher","unstructured":"Levine, S., Wang, J.M., Haraux, A., Popovi\u0107, Z., Koltun, V.: Continuous character control with low-dimensional embeddings. ACM Trans. Graph. 31(4), 1\u201310 (2012). https:\/\/doi.org\/10.1145\/2185520.2185524. https:\/\/dl.acm.org\/doi\/10.1145\/2185520.2185524","DOI":"10.1145\/2185520.2185524"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Li, R., Yang, S., Ross, D.A., Kanazawa, A.: AI choreographer: music conditioned 3D dance generation with AIST++. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 13401\u201313412 (2021)","DOI":"10.1109\/ICCV48922.2021.01315"},{"issue":"10","key":"1_CR40","doi-asserted-by":"crossref","first-page":"2684","DOI":"10.1109\/TPAMI.2019.2916873","volume":"42","author":"J Liu","year":"2019","unstructured":"Liu, J., Shahroudy, A., Perez, M., Wang, G., Duan, L.Y., Kot, A.C.: NTU RGB+D 120: a large-scale benchmark for 3D human activity understanding. IEEE Trans. Pattern Anal. Mach. Intell. 42(10), 2684\u20132701 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1_CR41","doi-asserted-by":"crossref","unstructured":"Liu, Y., Stoll, C., Gall, J., Seidel, H.P., Theobalt, C.: Markerless motion capture of interacting characters using multi-view image segmentation. In: CVPR 2011, pp. 1249\u20131256. IEEE (2011)","DOI":"10.1109\/CVPR.2011.5995424"},{"key":"1_CR42","doi-asserted-by":"publisher","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graph. 34(6) (2015). https:\/\/doi.org\/10.1145\/2816795.2818013","DOI":"10.1145\/2816795.2818013"},{"key":"1_CR43","doi-asserted-by":"crossref","unstructured":"Lucas, T., Baradel, F., Weinzaepfel, P., Rogez, G.: PoseGPT: Quantization-based 3D Human Motion Generation and Forecasting (2022). http:\/\/arxiv.org\/abs\/2210.10542. arXiv:2210.10542","DOI":"10.1007\/978-3-031-20068-7_24"},{"key":"1_CR44","doi-asserted-by":"crossref","unstructured":"Ma, X., Su, J., Wang, C., Zhu, W., Wang, Y.: 3D human mesh estimation from virtual markers. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 534\u2013543 (2023)","DOI":"10.1109\/CVPR52729.2023.00059"},{"key":"1_CR45","doi-asserted-by":"publisher","unstructured":"Min, J., Chai, J.: Motion graphs++: a compact generative model for semantic motion analysis and synthesis. ACM Trans. Graph. 31(6), 1\u201312 (2012). https:\/\/doi.org\/10.1145\/2366145.2366172. https:\/\/dl.acm.org\/doi\/10.1145\/2366145.2366172","DOI":"10.1145\/2366145.2366172"},{"issue":"2\u20133","key":"1_CR46","doi-asserted-by":"crossref","first-page":"90","DOI":"10.1016\/j.cviu.2006.08.002","volume":"104","author":"TB Moeslund","year":"2006","unstructured":"Moeslund, T.B., Hilton, A., Kr\u00fcger, V.: A survey of advances in vision-based human motion capture and analysis. Comput. Vis. Image Underst. 104(2\u20133), 90\u2013126 (2006)","journal-title":"Comput. Vis. Image Underst."},{"key":"1_CR47","doi-asserted-by":"publisher","unstructured":"Osman, A.A.A., Bolkart, T., Black, M.J.: STAR: Sparse Trained Articulated Human Body Regressor (2020). https:\/\/doi.org\/10.1007\/978-3-030-58539-6_36. http:\/\/arxiv.org\/abs\/2008.08535. arXiv:2008.08535","DOI":"10.1007\/978-3-030-58539-6_36"},{"key":"1_CR48","doi-asserted-by":"publisher","unstructured":"Pavlakos, G., et al.: Expressive body capture: 3D hands, face, and body from a single image. In: 2019 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10967\u201310977. IEEE, Long Beach, CA, USA (2019). https:\/\/doi.org\/10.1109\/CVPR.2019.01123. https:\/\/ieeexplore.ieee.org\/document\/8953319\/","DOI":"10.1109\/CVPR.2019.01123"},{"key":"1_CR49","doi-asserted-by":"publisher","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. 41(4), 1\u201317 (2022). https:\/\/doi.org\/10.1145\/3528223.3530110. https:\/\/dl.acm.org\/doi\/10.1145\/3528223.3530110","DOI":"10.1145\/3528223.3530110"},{"key":"1_CR50","doi-asserted-by":"publisher","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. 40(4), 1\u201320 (2021). https:\/\/doi.org\/10.1145\/3450626.3459670. https:\/\/dl.acm.org\/doi\/10.1145\/3450626.3459670","DOI":"10.1145\/3450626.3459670"},{"key":"1_CR51","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-Conditioned 3D Human Motion Synthesis with Transformer VAE (2021). http:\/\/arxiv.org\/abs\/2104.05670. arXiv:2104.05670","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"1_CR52","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: TEMOS: Generating diverse human motions from textual descriptions (2022). http:\/\/arxiv.org\/abs\/2204.14109. arXiv:2204.14109","DOI":"10.1007\/978-3-031-20047-2_28"},{"key":"1_CR53","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13873\u201313883 (2023)","DOI":"10.1109\/CVPR52729.2023.01333"},{"key":"1_CR54","doi-asserted-by":"publisher","unstructured":"Rose, C., Cohen, M., Bodenheimer, B.: Verbs and adverbs: multidimensional motion interpolation. IEEE Comput. Graphics Appl. 18(5), 32\u201340 (1998). https:\/\/doi.org\/10.1109\/38.708559. http:\/\/ieeexplore.ieee.org\/document\/708559\/","DOI":"10.1109\/38.708559"},{"key":"1_CR55","unstructured":"Shafir, Y., Tevet, G., Kapon, R., Bermano, A.H.: Human motion diffusion as a generative prior. arXiv preprint arXiv:2303.01418 (2023)"},{"key":"1_CR56","unstructured":"S\u00f8nderby, C.K., Raiko, T., Maal\u00f8e, L., S\u00f8nderby, S.K., Winther, O.: Ladder variational autoencoders. In: Proceedings of the 30th International Conference on Neural Information Processing Systems, NIPS 2016, pp. 3745\u20133753. Curran Associates Inc., Red Hook (2016)"},{"key":"1_CR57","unstructured":"Song, Y., Sohl-Dickstein, J., Kingma, D.P., Kumar, A., Ermon, S., Poole, B.: Score-based generative modeling through stochastic differential equations. arXiv preprint arXiv:2011.13456 (2020)"},{"key":"1_CR58","doi-asserted-by":"publisher","unstructured":"Starke, P., Starke, S., Komura, T., Steinicke, F.: Motion in-betweening with phase manifolds. Proc. ACM Comput. Graph. Interact. Tech. 6(3), 1\u201317 (2023). https:\/\/doi.org\/10.1145\/3606921. https:\/\/dl.acm.org\/doi\/10.1145\/3606921","DOI":"10.1145\/3606921"},{"key":"1_CR59","doi-asserted-by":"publisher","unstructured":"Starke, S., Mason, I., Komura, T.: DeepPhase: periodic autoencoders for learning motion phase manifolds. ACM Trans. Graph. 41(4), 1\u201313 (2022). https:\/\/doi.org\/10.1145\/3528223.3530178. https:\/\/dl.acm.org\/doi\/10.1145\/3528223.3530178","DOI":"10.1145\/3528223.3530178"},{"key":"1_CR60","doi-asserted-by":"publisher","unstructured":"Starke, S., Zhao, Y., Zinno, F., Komura, T.: Neural animation layering for synthesizing martial arts movements. ACM Trans. Graph. 40(4), 1\u201316 (2021). https:\/\/doi.org\/10.1145\/3450626.3459881. https:\/\/dl.acm.org\/doi\/10.1145\/3450626.3459881","DOI":"10.1145\/3450626.3459881"},{"key":"1_CR61","unstructured":"Sutton, R.S., Barto, A.G.: The reinforcement learning problem. In: Reinforcement Learning: An Introduction, pp. 51\u201385 (1998)"},{"key":"1_CR62","doi-asserted-by":"publisher","unstructured":"Tang, T., Jia, J., Mao, H.: Dance with melody: an LSTM-autoencoder approach to music-oriented dance synthesis. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1598\u20131606. ACM, Seoul Republic of Korea (2018). https:\/\/doi.org\/10.1145\/3240508.3240526. https:\/\/dl.acm.org\/doi\/10.1145\/3240508.3240526","DOI":"10.1145\/3240508.3240526"},{"key":"1_CR63","doi-asserted-by":"publisher","unstructured":"Tessler, C., Kasten, Y., Guo, Y., Mannor, S., Chechik, G., Peng, X.B.: CALM: conditional adversarial latent models for directable virtual characters. In: Special Interest Group on Computer Graphics and Interactive Techniques Conference Conference Proceedings, pp.\u00a01\u20139. ACM, Los Angeles CA USA (2023). https:\/\/doi.org\/10.1145\/3588432.3591541. https:\/\/dl.acm.org\/doi\/10.1145\/3588432.3591541","DOI":"10.1145\/3588432.3591541"},{"key":"1_CR64","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-Or, D., Bermano, A.H.: Human Motion Diffusion Model (2022). http:\/\/arxiv.org\/abs\/2209.14916. arXiv:2209.14916"},{"key":"1_CR65","doi-asserted-by":"crossref","unstructured":"Tu, L.W.: Manifolds. In: An Introduction to Manifolds, pp. 47\u201383. Springer (2011)","DOI":"10.1007\/978-1-4419-7400-6_3"},{"key":"1_CR66","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"1_CR67","unstructured":"Wang, H., Ho, E.S.L., Shum, H.P.H., Zhu, Z.: Spatio-temporal Manifold Learning for Human Motions via Long-horizon Modeling (2019). http:\/\/arxiv.org\/abs\/1908.07214. arXiv:1908.07214"},{"key":"1_CR68","doi-asserted-by":"publisher","unstructured":"Xu, H., Bazavan, E.G., Zanfir, A., Freeman, W.T., Sukthankar, R., Sminchisescu, C.: GHUM & GHUML: generative 3D human shape and articulated pose models. In: 2020 IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 6183\u20136192. IEEE, Seattle, WA, USA (2020). https:\/\/doi.org\/10.1109\/CVPR42600.2020.00622. https:\/\/ieeexplore.ieee.org\/document\/9157563\/","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"1_CR69","unstructured":"Yu, P., Zhao, Y., Li, C., Yuan, J., Chen, C.: Structure-Aware Human-Action Generation (2020). http:\/\/arxiv.org\/abs\/2007.01971. arXiv:2007.01971"},{"key":"1_CR70","unstructured":"Zeng, R., Dai, J., Bai, J., Pan, J., Qin, H.: Human motion synthesis and control via contextual manifold embedding. In: PG (Short Papers, Posters, and Work-in-Progress Papers), pp. 25\u201330 (2021)"},{"key":"1_CR71","doi-asserted-by":"publisher","unstructured":"Zhang, M., et al.: Motiondiffuse: text-driven human motion generation with diffusion model. IEEE Trans. Pattern Anal. Mach. Intell. 46(6), 4115\u20134128 (2024). https:\/\/doi.org\/10.1109\/TPAMI.2024.3355414","DOI":"10.1109\/TPAMI.2024.3355414"},{"key":"1_CR72","unstructured":"Zhang, M., et al.: ReMoDiffuse: Retrieval-Augmented Motion Diffusion Model (2023). http:\/\/arxiv.org\/abs\/2304.01116. arXiv:2304.01116"},{"key":"1_CR73","doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhang, Y., Ma, Q., Black, M.J., Tang, S.: PLACE: Proximity Learning of Articulation and Contact in 3D Environments (2020). http:\/\/arxiv.org\/abs\/2008.05570. arXiv:2008.05570","DOI":"10.1109\/3DV50981.2020.00074"},{"key":"1_CR74","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Black, M.J., Tang, S.: We are more than our joints: predicting how 3D bodies move. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3372\u20133382 (2021)","DOI":"10.1109\/CVPR46437.2021.00338"},{"key":"1_CR75","doi-asserted-by":"crossref","unstructured":"Zhu, W., Ma, X., Liu, Z., Liu, L., Wu, W., Wang, Y.: MotionBERT: A Unified Perspective on Learning Human Motion Representations (2023). http:\/\/arxiv.org\/abs\/2210.06551. arXiv:2210.06551","DOI":"10.1109\/ICCV51070.2023.01385"},{"key":"1_CR76","unstructured":"Zhu, W., et al.: Human Motion Generation: A Survey (2023). http:\/\/arxiv.org\/abs\/2307.10894. arXiv:2307.10894"},{"key":"1_CR77","doi-asserted-by":"crossref","unstructured":"Zuo, C., et al.: Loose inertial poser: motion capture with IMU-attached loose-wear jacket. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2209\u20132219 (2024)","DOI":"10.1109\/CVPR52733.2024.00215"}],"container-title":["Lecture Notes in Computer Science","Extended Reality"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-3679-2_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,4,10]],"date-time":"2025-04-10T09:36:31Z","timestamp":1744277791000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-3679-2_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819636785","9789819636792"],"references-count":77,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-3679-2_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"30 March 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICXR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Extended Reality","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"14 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"1","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icxr2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icxr.net\/2024","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}