{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,9]],"date-time":"2025-12-09T04:25:10Z","timestamp":1765254310600,"version":"3.40.3"},"publisher-location":"Cham","reference-count":32,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031270765"},{"type":"electronic","value":"9783031270772"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-27077-2_18","type":"book-chapter","created":{"date-parts":[[2023,3,28]],"date-time":"2023-03-28T05:03:10Z","timestamp":1679979790000},"page":"231-242","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":18,"title":["DiffMotion: Speech-Driven Gesture Synthesis Using Denoising Diffusion Model"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-9534-1777","authenticated-orcid":false,"given":"Fan","family":"Zhang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6986-3766","authenticated-orcid":false,"given":"Naye","family":"Ji","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Fuxing","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yongping","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,3,29]]},"reference":[{"key":"18_CR1","first-page":"17981","volume":"34","author":"J Austin","year":"2021","unstructured":"Austin, J., Johnson, D.D., Ho, J., Tarlow, D., van den Berg, R.: Structured denoising diffusion models in discrete state-spaces. Adv. Neural Inf. Process. Syst. 34, 17981\u201317993 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"18_CR2","doi-asserted-by":"crossref","unstructured":"Avrahami, O., Lischinski, D., Fried, O.: Blended diffusion for text-driven editing of natural images. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18208\u201318218 (2022)","DOI":"10.1109\/CVPR52688.2022.01767"},{"key":"18_CR3","unstructured":"David, M.: Gesture and Thought. University of Chicago press, Chicago (2008)"},{"key":"18_CR4","first-page":"8780","volume":"34","author":"P Dhariwal","year":"2021","unstructured":"Dhariwal, P., Nichol, A.: Diffusion models beat GANs on image synthesis. Adv. Neural Inf. Process. Syst. 34, 8780\u20138794 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"18_CR5","unstructured":"Dinh, L., Krueger, D., Bengio, Y.: NICE: non-linear independent components estimation. arXiv preprint arXiv:1410.8516 (2014)"},{"key":"18_CR6","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. arXiv preprint arXiv:1605.08803 (2016)"},{"issue":"6","key":"18_CR7","first-page":"1","volume":"39","author":"HG Eje","year":"2020","unstructured":"Eje, H.G., Simon, A., Jonas, B.: MoGlow: probabilistic and controllable motion synthesis using normalising flows. ACM Trans. Graph. 39(6), 1\u201314 (2020)","journal-title":"ACM Trans. Graph."},{"issue":"3","key":"18_CR8","doi-asserted-by":"publisher","first-page":"29","DOI":"10.1080\/10867651.1998.10487493","volume":"3","author":"F Grassia","year":"1998","unstructured":"Grassia, F.: Sebastian: Practical parameterization of rotations using the exponential map. J. Graph. Tool. 3(3), 29\u201348 (1998)","journal-title":"J. Graph. Tool."},{"key":"18_CR9","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":"18_CR10","unstructured":"Ian, G., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems 27 (2014)"},{"key":"18_CR11","unstructured":"Jing, L., et al.: Audio2Gestures: generating diverse gestures from speech audio with conditional variational autoencoders. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11293\u201311302 (2021)"},{"issue":"1980","key":"18_CR12","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1515\/9783110813098.207","volume":"25","author":"A Kendon","year":"1980","unstructured":"Kendon, A.: Gesticulation and speech: two aspects of the process of utterance. Relat. verbal Nonverbal Commun. 25(1980), 207\u2013227 (1980)","journal-title":"Relat. verbal Nonverbal Commun."},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Kucherenko, T., Jonell, P., Yoon, Y., Wolfert, P., Henter, G.E.: The GENEA challenge 2020: benchmarking gesture-generation systems on common data. In: International Workshop on Generation and Evaluation of Non-Verbal Behaviour for Embodied Agents (GENEA workshop) 2020 (2020)","DOI":"10.1145\/3462244.3480983"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Kucherenko, T., Jonell, P., Yoon, Y., Wolfert, P., Henter, G.E.: A large, crowdsourced evaluation of gesture generation systems on common data: the GENEA challenge 2020. In: 26th International Conference on Intelligent User Interfaces, pp. 11\u201321 (2021)","DOI":"10.1145\/3397481.3450692"},{"key":"18_CR15","doi-asserted-by":"publisher","first-page":"47","DOI":"10.1016\/j.neucom.2022.01.029","volume":"479","author":"H Li","year":"2022","unstructured":"Li, H., et al.: SRDiff: single image super-resolution with diffusion probabilistic models. Neurocomputing 479, 47\u201359 (2022)","journal-title":"Neurocomputing"},{"key":"18_CR16","doi-asserted-by":"crossref","unstructured":"Matthew, B.: Voice puppetry. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 21\u201328 (1999)","DOI":"10.1145\/311535.311537"},{"key":"18_CR17","unstructured":"McNeill, D.: Hand and mind: what gestures reveal about thought. In: Advances in Visual Semiotics, p. 351 (1992)"},{"key":"18_CR18","unstructured":"P., K.D., Prafulla, D.: Glow: generative flow with invertible 1x1 convolutions. arXiv preprint arXiv:1807.03039 (2018)"},{"key":"18_CR19","unstructured":"Paul, L.: sur la th\u00e9orie du mouvement brownien. C. R. Acad. Sci. 65(11), 146, 530\u2013533 (1908), publisher: American Association of Physics Teachers"},{"issue":"6","key":"18_CR20","doi-asserted-by":"publisher","first-page":"669","DOI":"10.1063\/1.4822961","volume":"4","author":"WH Press","year":"1990","unstructured":"Press, W.H., Teukolsky, S.A.: Savitzky-golay smoothing filters. Comput. Phys. 4(6), 669\u2013672 (1990)","journal-title":"Comput. Phys."},{"key":"18_CR21","unstructured":"Rasul, K., Seward, C., Schuster, I., Vollgraf, R.: Autoregressive denoising diffusion models for multivariate probabilistic time series forecasting. In: International Conference on Machine Learning, pp. 8857\u20138868 (2021)"},{"key":"18_CR22","doi-asserted-by":"crossref","unstructured":"Sarah, T., Jonathan, W., David, G., Iain, M.: Speech-driven conversational agents using conditional flow-VAEs. In: European Conference on Visual Media Production, pp. 1\u20139 (2021)","DOI":"10.1145\/3485441.3485647"},{"key":"18_CR23","doi-asserted-by":"crossref","unstructured":"Simon, A., Eje, H.G., Taras, K., Jonas, B.: Style-controllable speech-driven gesture synthesis using normalising flows. In: Computer Graphics Forum. vol. 39, no. 2, pp. 487\u2013496. Wiley Online Library (2020)","DOI":"10.1111\/cgf.13946"},{"key":"18_CR24","unstructured":"Sohl-Dickstein, J., Weiss, E., Maheswaranathan, N., Ganguli, S.: Deep unsupervised learning using nonequilibrium thermodynamics. In: International Conference on Machine Learning, pp. 2256\u20132265. PMLR (2015)"},{"key":"18_CR25","doi-asserted-by":"crossref","unstructured":"Wolfert, P., Robinson, N., Belpaeme, T.: A review of evaluation practices of gesture generation in embodied conversational agents. IEEE Trans. Human Mach. Syst. 52(3), 379\u2013389 (2022)","DOI":"10.1109\/THMS.2022.3149173"},{"key":"18_CR26","unstructured":"Yang, L., Zhang, Z., Hong, S., Zhang, W., Cui, B.: Diffusion models: A comprehensive survey of methods and applications (Sep 2022)"},{"issue":"12","key":"18_CR27","first-page":"2878","volume":"35","author":"Y Yi","year":"2012","unstructured":"Yi, Y., Deva, R.: Articulated human detection with flexible mixtures of parts. IEEE Trans. Pattern Anal. Mach. Intell. 35(12), 2878\u20132890 (2012)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"18_CR28","unstructured":"Ylva, F., Michael, N., Rachel, M.: Multi-objective adversarial gesture generation. In: Motion, Interaction and Games, pp. 1\u201310. ACM, Newcastle upon Tyne United Kingdom (2019)"},{"key":"18_CR29","unstructured":"Ylva, F., Rachel, M.: Investigating the use of recurrent motion modelling for speech gesture generation. In: Proceedings of the 18th International Conference on Intelligent Virtual Agents, pp. 93\u201398 (2018)"},{"key":"18_CR30","doi-asserted-by":"crossref","unstructured":"Yoon, Y., et al.: The GENEA challenge 2022: A large evaluation of data-driven co-speech gesture generation (2022)","DOI":"10.1145\/3536221.3558058"},{"key":"18_CR31","unstructured":"Zhang, Q., Chen, Y.: Diffusion normalizing flow. In: Advances in Neural Information Processing Systems. vol. 34 (2021)"},{"key":"18_CR32","unstructured":"Zhu, Y., Wu, Y., Olszewski, K., Ren, J., Tulyakov, S., Yan, Y.: Discrete contrastive diffusion for cross-modal and conditional generation (2022)"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27077-2_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,17]],"date-time":"2024-10-17T04:34:47Z","timestamp":1729139687000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27077-2_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031270765","9783031270772"],"references-count":32,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27077-2_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"29 March 2023","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":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"86","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"32% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"4","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}