{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,17]],"date-time":"2026-07-17T06:07:36Z","timestamp":1784268456198,"version":"3.55.0"},"publisher-location":"Cham","reference-count":43,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783031200649","type":"print"},{"value":"9783031200656","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-20065-6_41","type":"book-chapter","created":{"date-parts":[[2022,11,2]],"date-time":"2022-11-02T20:24:03Z","timestamp":1667420643000},"page":"712-728","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":24,"title":["Audio-Driven Stylized Gesture Generation with\u00a0Flow-Based Model"],"prefix":"10.1007","author":[{"given":"Sheng","family":"Ye","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yu-Hui","family":"Wen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yanan","family":"Sun","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ying","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ziyang","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yaoyuan","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Weihua","family":"He","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yong-Jin","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"key":"41_CR1","doi-asserted-by":"crossref","unstructured":"Aberman, K., Weng, Y., Lischinski, D., Cohen-Or, D., Chen, B.: Unpaired motion style transfer from video to animation. ACM Trans. Graph. (TOG) 39(4), 64\u20131 (2020)","DOI":"10.1145\/3386569.3392469"},{"key":"41_CR2","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"248","DOI":"10.1007\/978-3-030-58523-5_15","volume-title":"Computer Vision \u2013 ECCV 2020","author":"C Ahuja","year":"2020","unstructured":"Ahuja, C., Lee, D.W., Nakano, Y.I., Morency, L.-P.: Style transfer for co-speech gesture animation: a multi-speaker conditional-mixture approach. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12363, pp. 248\u2013265. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58523-5_15"},{"key":"41_CR3","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":"41_CR4","unstructured":"Alexanderson, S., Henter, G.E.: Robust model training and generalisation with studentising flows. In: ICML Workshop on Invertible Neural Networks, Normalizing Flows, and Explicit Likelihood Models (INNF+ 2020). vol. 2, pp. 25\u20131 (2020)"},{"key":"41_CR5","doi-asserted-by":"crossref","unstructured":"Alexanderson, S., Henter, G.E., Kucherenko, T., Beskow, J.: Style-controllable speech-driven gesture synthesis using normalising flows. In: Computer Graphics Forum, vol. 39, pp. 487\u2013496. Wiley Online Library (2020)","DOI":"10.1111\/cgf.13946"},{"key":"41_CR6","doi-asserted-by":"crossref","unstructured":"Bhattacharya, U., Childs, E., Rewkowski, N., Manocha, D.: Speech2affectivegestures: synthesizing co-speech gestures with generative adversarial affective expression learning. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 2027\u20132036 (2021)","DOI":"10.1145\/3474085.3475223"},{"key":"41_CR7","doi-asserted-by":"crossref","unstructured":"Bremner, P., Pipe, A.G., Melhuish, C., Fraser, M., Subramanian, S.: The effects of robot-performed co-verbal gesture on listener behaviour. In: 2011 11th IEEE-RAS International Conference on Humanoid Robots, pp. 458\u2013465. IEEE (2011)","DOI":"10.1109\/Humanoids.2011.6100810"},{"issue":"1","key":"41_CR8","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1075\/pc.7.1.03cas","volume":"7","author":"J Cassell","year":"1999","unstructured":"Cassell, J., McNeill, D., McCullough, K.E.: Speech-gesture mismatches: evidence for one underlying representation of linguistic and nonlinguistic information. Pragmatics Cogn. 7(1), 1\u201334 (1999)","journal-title":"Pragmatics Cogn."},{"key":"41_CR9","doi-asserted-by":"crossref","unstructured":"Cassell, J., et al.: Animated conversation: rule-based generation of facial expression, gesture & spoken intonation for multiple conversational agents. In: Proceedings of the 21st Annual Conference On Computer Graphics And Interactive Techniques, pp. 413\u2013420 (1994)","DOI":"10.1145\/192161.192272"},{"key":"41_CR10","unstructured":"Dinh, L., Sohl-Dickstein, J., Bengio, S.: Density estimation using real NVP. In: International Conference on Learning Representations (2017)"},{"key":"41_CR11","unstructured":"Du, H., Herrmann, E., Sprenger, J., Cheema, N., Hosseini, S., Fischer, K., Slusallek, P.: Stylistic locomotion modeling with conditional variational autoencoder. In: Eurographics (Short Papers), pp. 9\u201312 (2019)"},{"key":"41_CR12","doi-asserted-by":"crossref","unstructured":"Ferstl, Y., McDonnell, R.: 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)","DOI":"10.1145\/3267851.3267898"},{"key":"41_CR13","doi-asserted-by":"crossref","unstructured":"Gatys, L.A., Ecker, A.S., Bethge, M.: Image style transfer using convolutional neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 2414\u20132423 (2016)","DOI":"10.1109\/CVPR.2016.265"},{"key":"41_CR14","doi-asserted-by":"crossref","unstructured":"Ginosar, S., Bar, A., Kohavi, G., Chan, C., Owens, A., Malik, J.: Learning individual styles of conversational gesture. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3497\u20133506 (2019)","DOI":"10.1109\/CVPR.2019.00361"},{"key":"41_CR15","unstructured":"Goodfellow, I., et al.: Generative adversarial nets. In: Advances in Neural Information Processing Systems, vol. 27 (2014)"},{"key":"41_CR16","doi-asserted-by":"crossref","unstructured":"Hasegawa, D., Kaneko, N., Shirakawa, S., Sakuta, H., Sumi, K.: Evaluation of speech-to-gesture generation using bi-directional LSTM network. In: Proceedings of the 18th International Conference on Intelligent Virtual Agents, pp. 79\u201386 (2018)","DOI":"10.1145\/3267851.3267878"},{"key":"41_CR17","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Delving deep into rectifiers: surpassing human-level performance on ImageNet classification. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1026\u20131034 (2015)","DOI":"10.1109\/ICCV.2015.123"},{"issue":"6","key":"41_CR18","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417836","volume":"39","author":"GE Henter","year":"2020","unstructured":"Henter, G.E., Alexanderson, S., Beskow, J.: MoGlow: probabilistic and controllable motion synthesis using normalising flows. ACM Trans. Graph. (TOG) 39(6), 1\u201314 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR19","unstructured":"Ho, J., Chen, X., Srinivas, A., Duan, Y., Abbeel, P.: Flow++: improving flow-based generative models with variational dequantization and architecture design. In: International Conference on Machine Learning, pp. 2722\u20132730. PMLR (2019)"},{"issue":"4","key":"41_CR20","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. ACM Transa. Graph. (TOG) 35(4), 1\u201311 (2016)","journal-title":"ACM Transa. Graph. (TOG)"},{"key":"41_CR21","doi-asserted-by":"crossref","unstructured":"Huang, X., Belongie, S.: Arbitrary style transfer in real-time with adaptive instance normalization. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 1501\u20131510 (2017)","DOI":"10.1109\/ICCV.2017.167"},{"key":"41_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"694","DOI":"10.1007\/978-3-319-46475-6_43","volume-title":"Computer Vision \u2013 ECCV 2016","author":"J Johnson","year":"2016","unstructured":"Johnson, J., Alahi, A., Fei-Fei, L.: Perceptual losses for real-time style transfer and super-resolution. In: Leibe, B., Matas, J., Sebe, N., Welling, M. (eds.) ECCV 2016. LNCS, vol. 9906, pp. 694\u2013711. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46475-6_43"},{"key":"41_CR23","unstructured":"Kingma, D.P., Welling, M.: Auto-encoding variational bayes. In: International Conference on Learning Representations (2014)"},{"key":"41_CR24","unstructured":"Kingma, D.P., Dhariwal, P.: Glow: generative flow with invertible 1x1 convolutions. In: Advances in Neural Information Processing Systems, vol. 31 (2018)"},{"key":"41_CR25","volume-title":"Gesture Generation by Imitation: From Human Behavior to Computer Character Animation","author":"M Kipp","year":"2005","unstructured":"Kipp, M.: Gesture Generation by Imitation: From Human Behavior to Computer Character Animation. Universal-Publishers, Irvine (2005)"},{"key":"41_CR26","series-title":"Lecture Notes in Computer Science (Lecture Notes in Artificial Intelligence)","doi-asserted-by":"publisher","first-page":"205","DOI":"10.1007\/11821830_17","volume-title":"Intelligent Virtual Agents","author":"S Kopp","year":"2006","unstructured":"Kopp, S., et al.: Towards a common framework for multimodal generation: the behavior markup language. In: Gratch, J., Young, M., Aylett, R., Ballin, D., Olivier, P. (eds.) IVA 2006. LNCS (LNAI), vol. 4133, pp. 205\u2013217. Springer, Heidelberg (2006). https:\/\/doi.org\/10.1007\/11821830_17"},{"key":"41_CR27","doi-asserted-by":"crossref","unstructured":"Kucherenko, T., Hasegawa, D., Henter, G.E., Kaneko, N., Kjellstr\u00f6m, H.: Analyzing input and output representations for speech-driven gesture generation. In: Proceedings of the 19th ACM International Conference on Intelligent Virtual Agents, pp. 97\u2013104 (2019)","DOI":"10.1145\/3308532.3329472"},{"key":"41_CR28","doi-asserted-by":"crossref","unstructured":"Kucherenko, T., et al.: Gesticulator: a framework for semantically-aware speech-driven gesture generation. In: Proceedings of the 2020 International Conference on Multimodal Interaction, pp. 242\u2013250 (2020)","DOI":"10.1145\/3382507.3418815"},{"key":"41_CR29","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":"41_CR30","doi-asserted-by":"crossref","unstructured":"Levine, S., Kr\u00e4henb\u00fchl, P., Thrun, S., Koltun, V.: Gesture controllers. In: ACM SIGGRAPH 2010 papers, pp. 1\u201311. Association for Computing Machinery, New York, NY, United States (2010)","DOI":"10.1145\/1778765.1778861"},{"key":"41_CR31","doi-asserted-by":"crossref","unstructured":"Levine, S., Theobalt, C., Koltun, V.: Real-time prosody-driven synthesis of body language. In: ACM SIGGRAPH Asia 2009 papers, pp. 1\u201310. Association for Computing Machinery, New York, NY, United States (2009)","DOI":"10.1145\/1618452.1618518"},{"key":"41_CR32","doi-asserted-by":"crossref","unstructured":"Li, J., 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)","DOI":"10.1109\/ICCV48922.2021.01110"},{"key":"41_CR33","unstructured":"Ma, X., Kong, X., Zhang, S., Hovy, E.: MaCow: masked convolutional generative flow. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"41_CR34","unstructured":"Ma, X., Kong, X., Zhang, S., Hovy, E.H.: Decoupling global and local representations via invertible generative flows. In: International Conference on Learning Representations (2020)"},{"issue":"1","key":"41_CR35","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/1330511.1330516","volume":"27","author":"M Neff","year":"2008","unstructured":"Neff, M., Kipp, M., Albrecht, I., Seidel, H.P.: Gesture modeling and animation based on a probabilistic re-creation of speaker style. ACM Trans. Graph. (TOG) 27(1), 1\u201324 (2008)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR36","doi-asserted-by":"crossref","unstructured":"Pavllo, D., Feichtenhofer, C., Grangier, D., Auli, M.: 3D human pose estimation in video with temporal convolutions and semi-supervised training. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 7753\u20137762 (2019)","DOI":"10.1109\/CVPR.2019.00794"},{"key":"41_CR37","doi-asserted-by":"crossref","unstructured":"Qian, S., Tu, Z., Zhi, Y., Liu, W., Gao, S.: Speech drives templates: co-speech gesture synthesis with learned templates. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 11077\u201311086 (2021)","DOI":"10.1109\/ICCV48922.2021.01089"},{"key":"41_CR38","unstructured":"Simonyan, K., Zisserman, A.: Very deep convolutional networks for large-scale image recognition. In: International Conference on Learning Representations (2015)"},{"issue":"2","key":"41_CR39","doi-asserted-by":"publisher","first-page":"203","DOI":"10.1177\/002383099403700208","volume":"37","author":"M Studdert-Kennedy","year":"1994","unstructured":"Studdert-Kennedy, M.: Hand and mind: what gestures reveal about thought. Lang. Speech 37(2), 203\u2013209 (1994)","journal-title":"Lang. Speech"},{"key":"41_CR40","doi-asserted-by":"publisher","first-page":"209","DOI":"10.1016\/j.specom.2013.09.008","volume":"57","author":"P Wagner","year":"2014","unstructured":"Wagner, P., Malisz, Z., Kopp, S.: Gesture and speech in interaction: an overview. Speech Commun. 57, 209\u2013232 (2014)","journal-title":"Speech Commun."},{"key":"41_CR41","doi-asserted-by":"crossref","unstructured":"Wen, Y.H., Yang, Z., Fu, H., Gao, L., Sun, Y., Liu, Y.J.: Autoregressive stylized motion synthesis with generative flow. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13612\u201313621 (2021)","DOI":"10.1109\/CVPR46437.2021.01340"},{"issue":"6","key":"41_CR42","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3414685.3417838","volume":"39","author":"Y Yoon","year":"2020","unstructured":"Yoon, Y., et al.: Speech gesture generation from the trimodal context of text, audio, and speaker identity. ACM Trans. Graph. (TOG) 39(6), 1\u201316 (2020)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"41_CR43","doi-asserted-by":"crossref","unstructured":"Yoon, Y., Ko, W.R., Jang, M., Lee, J., Kim, J., Lee, G.: Robots learn social skills: End-to-end learning of co-speech gesture generation for humanoid robots. In: 2019 International Conference on Robotics and Automation (ICRA), pp. 4303\u20134309. IEEE (2019)","DOI":"10.1109\/ICRA.2019.8793720"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2022"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20065-6_41","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,7]],"date-time":"2022-11-07T00:20:38Z","timestamp":1667780438000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20065-6_41"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031200649","9783031200656"],"references-count":43,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20065-6_41","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"3 November 2022","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":"Tel Aviv","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Israel","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"17","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2022.ecva.net\/","order":11,"name":"conference_url","label":"Conference URL","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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5804","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":"1645","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":"28% - 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":"3.21","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":"3.91","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}