{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,4]],"date-time":"2026-03-04T17:20:59Z","timestamp":1772644859012,"version":"3.50.1"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031736674","type":"print"},{"value":"9783031736681","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T00:00:00Z","timestamp":1733011200000},"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\/978-3-031-73668-1_7","type":"book-chapter","created":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:04:08Z","timestamp":1733018648000},"page":"107-124","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Length-Aware Motion Synthesis via\u00a0Latent Diffusion"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-1432-7499","authenticated-orcid":false,"given":"Alessio","family":"Sampieri","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4332-9179","authenticated-orcid":false,"given":"Alessio","family":"Palma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1963-3548","authenticated-orcid":false,"given":"Indro","family":"Spinelli","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1875-7813","authenticated-orcid":false,"given":"Fabio","family":"Galasso","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,12,1]]},"reference":[{"key":"7_CR1","unstructured":"Balaji, Y., et al.: eDiff-I: text-to-image diffusion models with an ensemble of expert denoisers. arXiv abs\/2211.01324 (2022)"},{"key":"7_CR2","doi-asserted-by":"publisher","unstructured":"B\u00fctepage, J., Black, M.J., Kragic, D., Kjellstr\u00f6m, H.: Deep representation learning for human motion prediction and classification. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition (CVPR), pp. 1591\u20131599 (2017). https:\/\/doi.org\/10.1109\/CVPR.2017.173","DOI":"10.1109\/CVPR.2017.173"},{"key":"7_CR3","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":"7_CR4","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. In: Advances in Neural Information Processing Systems. Curran Associates, Inc. (2021)"},{"key":"7_CR5","doi-asserted-by":"crossref","unstructured":"Gu, S., et al.: Vector quantized diffusion model for text-to-image synthesis. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR), pp. 10696\u201310706 (2022)","DOI":"10.1109\/CVPR52688.2022.01043"},{"key":"7_CR6","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 (CVPR), pp. 5152\u20135161 (2022)","DOI":"10.1109\/CVPR52688.2022.00509"},{"key":"7_CR7","doi-asserted-by":"publisher","unstructured":"Guo, C., et al.: Action2motion: conditioned generation of 3D human motions. In: Proceedings of the 28th ACM International Conference on Multimedia, MM 2020, pp. 2021\u20132029. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3394171.3413635","DOI":"10.1145\/3394171.3413635"},{"key":"7_CR8","unstructured":"Ho, J., Jain, A., Abbeel, P.: Denoising diffusion probabilistic models. In: Proceedings of the 34th International Conference on Neural Information Processing Systems (NIPS) (2020)"},{"key":"7_CR9","doi-asserted-by":"crossref","unstructured":"Im, D.J., Ahn, S., Memisevic, R., Bengio, Y.: Denoising criterion for variational auto-encoding framework. In: Proceedings of the Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10777"},{"key":"7_CR10","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":"7_CR11","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: 2nd International Conference on Learning Representations, ICLR 2014 (2014)"},{"key":"7_CR12","doi-asserted-by":"crossref","unstructured":"Kong, H., Gong, K., Lian, D., Mi, M.B., Wang, X.: Priority-centric human motion generation in discrete latent space. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.01360"},{"key":"7_CR13","unstructured":"Lewis, P., et al.: Retrieval-augmented generation for knowledge-intensive NLP tasks. In: Proceedings of the 34th International Conference on Neural Information Processing Systems (2020)"},{"key":"7_CR14","doi-asserted-by":"crossref","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: SMPL: a skinned multi-person linear model. ACM Trans. Graphics (Proc. SIGGRAPH Asia) 34(6), 248:1\u2013248:16 (2015)","DOI":"10.1145\/2816795.2818013"},{"key":"7_CR15","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. In: International Conference on Learning Representations (2019)"},{"key":"7_CR16","unstructured":"van\u00a0den Oord, A., Vinyals, O., Kavukcuoglu, K.: Neural discrete representation learning. In: Proceedings of the 31st International Conference on Neural Information Processing Systems (NIPS) (2017)"},{"key":"7_CR17","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: Action-conditioned 3D human motion synthesis with transformer VAE. In: International Conference on Computer Vision (ICCV) (2021)","DOI":"10.1109\/ICCV48922.2021.01080"},{"key":"7_CR18","doi-asserted-by":"crossref","unstructured":"Petrovich, M., Black, M.J., Varol, G.: TEMOS: generating diverse human motions from textual descriptions. In: European Conference on Computer Vision (ECCV) (2022)","DOI":"10.1007\/978-3-031-20047-2_28"},{"issue":"4","key":"7_CR19","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":"7_CR20","unstructured":"Puig, X., et al.: Habitat 3.0: a co-habitat for humans, avatars and robots (2023)"},{"key":"7_CR21","unstructured":"Radford, A., Narasimhan, K.: Improving language understanding by generative pre-training. In: Proceedings of the 32nd International Conference on Neural Information Processing Systems (NIPS) (2018)"},{"key":"7_CR22","unstructured":"Ramesh, A., Dhariwal, P., Nichol, A., Chu, C., Chen, M.: Hierarchical text-conditional image generation with clip latents (2022)"},{"key":"7_CR23","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 (CVPR) (2022)","DOI":"10.1109\/CVPR52688.2022.01042"},{"issue":"4","key":"7_CR24","first-page":"4713","volume":"45","author":"C Saharia","year":"2023","unstructured":"Saharia, C., Ho, J., Chan, W., Salimans, T., Fleet, D.J., Norouzi, M.: Image super-resolution via iterative refinement. IEEE Trans. Pattern Anal. Mach. Intell. 45(4), 4713\u20134726 (2023)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"7_CR25","unstructured":"Tevet, G., Raab, S., Gordon, B., Shafir, Y., Cohen-or, D., Bermano, A.H.: Human motion diffusion model. In: The Eleventh International Conference on Learning Representations (2023). https:\/\/openreview.net\/forum?id=SJ1kSyO2jwu"},{"key":"7_CR26","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS 2017 (2017)"},{"key":"7_CR27","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: International Conference on Learning Representations (2018)"},{"key":"7_CR28","doi-asserted-by":"crossref","unstructured":"Wang, Y., Leng, Z., Li, F.W.B., Wu, S.C., Liang, X.: FG-T2M: fine-grained text-driven human motion generation via diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 22035\u201322044 (2023)","DOI":"10.1109\/ICCV51070.2023.02014"},{"key":"7_CR29","doi-asserted-by":"crossref","unstructured":"Zhang, J., et al.: T2M-GPT: generating human motion from textual descriptions with discrete representations. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2023)","DOI":"10.1109\/CVPR52729.2023.01415"},{"key":"7_CR30","unstructured":"Zhang, M., et al.: Motiondiffuse: text-driven human motion generation with diffusion model. arXiv preprint arXiv:2208.15001 (2022)"},{"key":"7_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, M., et al.: Remodiffuse: retrieval-augmented motion diffusion model. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00040"},{"key":"7_CR32","doi-asserted-by":"crossref","unstructured":"Zhong, C., Hu, L., Zhang, Z., Xia, S.: Attt2m: text-driven human motion generation with multi-perspective attention mechanism. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV) (2023)","DOI":"10.1109\/ICCV51070.2023.00053"}],"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\/978-3-031-73668-1_7","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,12,1]],"date-time":"2024-12-01T02:06:48Z","timestamp":1733018808000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-73668-1_7"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,12,1]]},"ISBN":["9783031736674","9783031736681"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-73668-1_7","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,12,1]]},"assertion":[{"value":"1 December 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"}}]}}