{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T12:29:32Z","timestamp":1771244972452,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":32,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819569496","type":"print"},{"value":"9789819569502","type":"electronic"}],"license":[{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,1,1]],"date-time":"2026-01-01T00:00:00Z","timestamp":1767225600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-6950-2_29","type":"book-chapter","created":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:03Z","timestamp":1771243143000},"page":"407-421","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Conditional VQ-VAE for\u00a0Action-Conditioned Motion Generation"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0009-0360-5172","authenticated-orcid":false,"given":"Zhaoyang","family":"Li","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0005-9271-7176","authenticated-orcid":false,"given":"Jinglan","family":"Tian","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-2017-2518","authenticated-orcid":false,"given":"Na","family":"Lyu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2026,2,17]]},"reference":[{"key":"29_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: 2018 IEEE International Conference on Robotics and Automation (ICRA), pp. 5915\u20135920. IEEE (2018)","DOI":"10.1109\/ICRA.2018.8460608"},{"key":"29_CR2","doi-asserted-by":"crossref","unstructured":"Ahuja, C., Morency, L.P.: Language2pose: Natural language grounded pose forecasting. In: 2019 International conference on 3D vision (3DV), pp. 719\u2013728. IEEE (2019)","DOI":"10.1109\/3DV.2019.00084"},{"key":"29_CR3","doi-asserted-by":"crossref","unstructured":"Aksan, E., Kaufmann, M., Hilliges, O.: Structured prediction helps 3d human motion modelling. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 7144\u20137153 (2019)","DOI":"10.1109\/ICCV.2019.00724"},{"issue":"6","key":"29_CR4","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3550454.3555435","volume":"41","author":"T Ao","year":"2022","unstructured":"Ao, T., Gao, Q., Lou, Y., Chen, B., Liu, L.: Rhythmic gesticulator: rhythm-aware co-speech gesture synthesis with hierarchical neural embeddings. ACM Trans. Graphics (TOG) 41(6), 1\u201319 (2022)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"29_CR5","unstructured":"Aristidou, A., Yiannakidis, A., Aberman, K., Cohen-Or, D., Shamir, A., Chrysanthou, Y.: Rhythm is a dancer: Music-driven motion synthesis with global structure. arXiv preprint arXiv:2111.12159 (2021)"},{"key":"29_CR6","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":"29_CR7","unstructured":"Dhariwal, P., Jun, H., Payne, C., Kim, J.W., Radford, A., Sutskever, I.: Jukebox: a generative model for music. arXiv preprint arXiv:2005.00341 (2020)"},{"key":"29_CR8","doi-asserted-by":"crossref","unstructured":"Esser, P., Rombach, R., Ommer, B.: Taming transformers for high-resolution image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12873\u201312883 (2021)","DOI":"10.1109\/CVPR46437.2021.01268"},{"key":"29_CR9","doi-asserted-by":"crossref","unstructured":"Fragkiadaki, K., Levine, S., Felsen, P., Malik, J.: Recurrent network models for human dynamics. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 4346\u20134354 (2015)","DOI":"10.1109\/ICCV.2015.494"},{"key":"29_CR10","doi-asserted-by":"crossref","unstructured":"Gong, K., et al.: Tm2d: Bimodality driven 3D dance generation via music-text integration. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 9942\u20139952 (2023)","DOI":"10.1109\/ICCV51070.2023.00912"},{"key":"29_CR11","doi-asserted-by":"crossref","unstructured":"Guo, C., et al.: Action2motion: Conditioned generation of 3D human motions. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2021\u20132029 (2020)","DOI":"10.1145\/3394171.3413635"},{"key":"29_CR12","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":"29_CR13","doi-asserted-by":"crossref","unstructured":"Ionescu, C., Li, F., Sminchisescu, C.: Latent structured models for human pose estimation. In: 2011 International Conference on Computer Vision, pp. 2220\u20132227. IEEE (2011)","DOI":"10.1109\/ICCV.2011.6126500"},{"key":"29_CR14","doi-asserted-by":"crossref","unstructured":"Ji, Y., et al.: A large-scale RGB-D database for arbitrary-view human action recognition. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 1510\u20131518 (2018)","DOI":"10.1145\/3240508.3240675"},{"key":"29_CR15","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. arXiv preprint arXiv:1312.6114 (2013)"},{"key":"29_CR16","unstructured":"Lin, X., Amer, M.R.: Human motion modeling using dvgans. arXiv preprint arXiv:1804.10652 (2018)"},{"key":"29_CR17","doi-asserted-by":"crossref","unstructured":"Lu, Q., Zhang, Y., Lu, M., Roychowdhury, V.: Action-conditioned on-demand motion generation. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 2249\u20132257 (2022)","DOI":"10.1145\/3503161.3548287"},{"key":"29_CR18","doi-asserted-by":"crossref","unstructured":"Lucas, T., Baradel, F., Weinzaepfel, P., Rogez, G.: Posegpt: Quantization-based 3D human motion generation and forecasting. In: European Conference on Computer Vision, pp. 417\u2013435. Springer (2022)","DOI":"10.1007\/978-3-031-20068-7_24"},{"key":"29_CR19","doi-asserted-by":"crossref","unstructured":"Martinez, J., Black, M.J., Romero, J.: On human motion prediction using recurrent neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2891\u20132900 (2017)","DOI":"10.1109\/CVPR.2017.497"},{"issue":"14","key":"29_CR20","doi-asserted-by":"publisher","first-page":"1264","DOI":"10.1016\/j.imavis.2005.09.004","volume":"23","author":"D Ormoneit","year":"2005","unstructured":"Ormoneit, D., Black, M.J., Hastie, T., Kjellstr\u00f6m, H.: Representing cyclic human motion using functional analysis. Image Vis. Comput. 23(14), 1264\u20131276 (2005)","journal-title":"Image Vis. Comput."},{"key":"29_CR21","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10985\u201310995 (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"29_CR22","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":"29_CR23","unstructured":"Ramesh, A., et al.: Zero-shot text-to-image generation. In: International Conference on Machine Learning, pp. 8821\u20138831. PMLR (2021)"},{"key":"29_CR24","doi-asserted-by":"crossref","unstructured":"Rombach, R., Blattmann, A., Lorenz, D., Esser, P., Ommer, B.: High-resolution image synthesis with latent diffusion models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10684\u201310695 (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"key":"29_CR25","doi-asserted-by":"crossref","unstructured":"Siyao, L., et al.: Bailando: 3D dance generation by actor-critic GPT with choreographic memory. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 11050\u201311059 (2022)","DOI":"10.1109\/CVPR52688.2022.01077"},{"key":"29_CR26","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":"29_CR27","unstructured":"Van Den\u00a0Oord, A., Vinyals, O., et\u00a0al.: Neural discrete representation learning. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"29_CR28","doi-asserted-by":"crossref","unstructured":"Xu, H., et al.: Ghum & ghuml: Generative 3D human shape and articulated pose models. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6184\u20136193 (2020)","DOI":"10.1109\/CVPR42600.2020.00622"},{"key":"29_CR29","doi-asserted-by":"crossref","unstructured":"Yan, S., Li, Z., Xiong, Y., Yan, H., Lin, D.: Convolutional sequence generation for skeleton-based action synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 4394\u20134402 (2019)","DOI":"10.1109\/ICCV.2019.00449"},{"key":"29_CR30","doi-asserted-by":"crossref","unstructured":"Yan, S., Xiong, Y., Lin, D.: Spatial temporal graph convolutional networks for skeleton-based action recognition. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol.\u00a032 (2018)","DOI":"10.1609\/aaai.v32i1.12328"},{"issue":"6","key":"29_CR31","doi-asserted-by":"publisher","first-page":"4115","DOI":"10.1109\/TPAMI.2024.3355414","volume":"46","author":"M Zhang","year":"2024","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)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"29_CR32","doi-asserted-by":"crossref","unstructured":"Zou, S., et al.: 3D human shape reconstruction from a polarization image. In: European Conference on Computer Vision, pp. 351\u2013368. Springer (2020)","DOI":"10.1007\/978-3-030-58568-6_21"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-6950-2_29","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T11:59:12Z","timestamp":1771243152000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-6950-2_29"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026]]},"ISBN":["9789819569496","9789819569502"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-6950-2_29","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026]]},"assertion":[{"value":"17 February 2026","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Prague","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Czech Republic","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2026","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 January 2026","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 January 2026","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2026","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/mmm2026.cz\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}