{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T20:19:11Z","timestamp":1784837951107,"version":"3.55.0"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585167","type":"print"},{"value":"9783030585174","type":"electronic"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"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":[[2020]]},"DOI":"10.1007\/978-3-030-58517-4_42","type":"book-chapter","created":{"date-parts":[[2020,10,9]],"date-time":"2020-10-09T19:03:11Z","timestamp":1602270191000},"page":"716-731","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":283,"title":["Neural Voice Puppetry: Audio-Driven Facial Reenactment"],"prefix":"10.1007","author":[{"given":"Justus","family":"Thies","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Mohamed","family":"Elgharib","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ayush","family":"Tewari","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Christian","family":"Theobalt","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Matthias","family":"Nie\u00dfner","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,10,10]]},"reference":[{"key":"42_CR1","doi-asserted-by":"crossref","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3D faces. In: ACM Transactions on Graphics (Proceedings of SIGGRAPH), pp. 187\u2013194 (1999)","DOI":"10.1145\/311535.311556"},{"key":"42_CR2","doi-asserted-by":"crossref","unstructured":"Bregler, C., Covell, M., Slaney, M.: Video rewrite: driving visual speech with audio. In: Proceedings of the 24th Annual Conference on Computer Graphics and Interactive Techniques. SIGGRAPH 1997, pp. 353\u2013360 (1997)","DOI":"10.1145\/258734.258880"},{"key":"42_CR3","doi-asserted-by":"crossref","unstructured":"Chen, L., Maddox, R.K., Duan, Z., Xu, C.: Hierarchical cross-modal talking face generation with dynamic pixel-wise loss. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 7832\u20137841 (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"42_CR4","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"251","DOI":"10.1007\/978-3-319-54427-4_19","volume-title":"Computer Vision \u2013 ACCV 2016 Workshops","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Chen, C.-S., Lu, J., Ma, K.-K. (eds.) ACCV 2016. LNCS, vol. 10117, pp. 251\u2013263. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54427-4_19"},{"key":"42_CR5","unstructured":"Chung, J.S., Jamaludin, A., Zisserman, A.: You said that? In: British Machine Vision Conference (BMVC) (2017)"},{"key":"42_CR6","doi-asserted-by":"crossref","unstructured":"Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M.: Capture, learning, and synthesis of 3D speaking styles. In: Computer Vision and Pattern Recognition (CVPR) (2019)","DOI":"10.1109\/CVPR.2019.01034"},{"issue":"4","key":"42_CR7","doi-asserted-by":"publisher","first-page":"112:1","DOI":"10.1145\/3197517.3201357","volume":"37","author":"A Ephrat","year":"2018","unstructured":"Ephrat, A., et al.: Looking to listen at the cocktail party: a speaker-independent audio-visual model for speech separation. ACM Trans. Graph. 37(4), 112:1\u2013112:11 (2018)","journal-title":"ACM Trans. Graph."},{"key":"42_CR8","doi-asserted-by":"publisher","first-page":"388","DOI":"10.1145\/566654.566594","volume":"21","author":"T Ezzat","year":"2002","unstructured":"Ezzat, T., Geiger, G., Poggio, T.: Trainable videorealistic speech animation. ACM Trans. Graph. 21, 388\u2013398 (2002)","journal-title":"ACM Trans. Graph."},{"key":"42_CR9","volume-title":"Video-Mediated Communication","author":"KE Finn","year":"1997","unstructured":"Finn, K.E.: Video-Mediated Communication. L. Erlbaum Associates Inc., Mahwah (1997)"},{"issue":"4","key":"42_CR10","first-page":"68:1","volume":"38","author":"O Fried","year":"2019","unstructured":"Fried, O., et al.: Text-based editing of talking-head video. ACM Trans. Graph. (Proceedings of SIGGRAPH) 38(4), 68:1\u201368:14 (2019)","journal-title":"ACM Trans. Graph. (Proceedings of SIGGRAPH)"},{"key":"42_CR11","doi-asserted-by":"crossref","unstructured":"Garrido, P., et al.: VDub - modifying face video of actors for plausible visual alignment to a dubbed audio track. In: Computer Graphics Forum (Proceedings of EUROGRAPHICS) (2015)","DOI":"10.1111\/cgf.12552"},{"issue":"3","key":"42_CR12","first-page":"28","volume":"35","author":"P Garrido","year":"2016","unstructured":"Garrido, P., et al.: Reconstruction of personalized 3D face rigs from monocular video. ACM Trans. Graph. (Proceedings of SIGGRAPH) 35(3), 28 (2016)","journal-title":"ACM Trans. Graph. (Proceedings of SIGGRAPH)"},{"key":"42_CR13","unstructured":"Hannun, A., et al.: DeepSpeech: scaling up end-to-end speech recognition, December 2014"},{"key":"42_CR14","unstructured":"Jia, Y., et al.: Transfer learning from speaker verification to multispeaker text-to-speech synthesis. In: International Conference on Neural Information Processing Systems (NIPS), pp. 4485\u20134495 (2018)"},{"key":"42_CR15","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"},{"issue":"4","key":"42_CR16","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073658","volume":"36","author":"T Karras","year":"2017","unstructured":"Karras, T., Aila, T., Laine, S., Herva, A., Lehtinen, J.: Audio-driven facial animation by joint end-to-end learning of pose and emotion. ACM Trans. Graph. (Proceedings of SIGGRAPH) 36(4), 1\u201312 (2017)","journal-title":"ACM Trans. Graph. (Proceedings of SIGGRAPH)"},{"key":"42_CR17","first-page":"1","volume":"38","author":"H Kim","year":"2019","unstructured":"Kim, H., et al.: Neural style-preserving visual dubbing. ACM Trans. Graph. (SIGGRAPH Asia) 38, 1\u201313 (2019)","journal-title":"ACM Trans. Graph. (SIGGRAPH Asia)"},{"issue":"4","key":"42_CR18","first-page":"163:1","volume":"37","author":"H Kim","year":"2018","unstructured":"Kim, H., et al.: Deep video portraits. ACM Trans. Graph. (Proceedings of SIGGRAPH) 37(4), 163:1\u2013163:14 (2018)","journal-title":"ACM Trans. Graph. (Proceedings of SIGGRAPH)"},{"key":"42_CR19","doi-asserted-by":"crossref","unstructured":"Li, T., Bolkart, T., Black, M.J., Li, H., Romero, J.: Learning a model of facial shape and expression from 4D scans. ACM Trans. Graph. 36(6), 194:1\u2013194:17 (2017). Two first authors contributed equally","DOI":"10.1145\/3130800.3130813"},{"issue":"4","key":"42_CR20","first-page":"68:1","volume":"37","author":"S Lombardi","year":"2018","unstructured":"Lombardi, S., Saragih, J., Simon, T., Sheikh, Y.: Deep appearance models for face rendering. ACM Trans. Graph. (Proceedings of SIGGRAPH) 37(4), 68:1\u201368:13 (2018)","journal-title":"ACM Trans. Graph. (Proceedings of SIGGRAPH)"},{"key":"42_CR21","unstructured":"van den Oord, A., et al.: WaveNet: a generative model for raw audio. arXiv (2016). https:\/\/arxiv.org\/abs\/1609.03499"},{"key":"42_CR22","doi-asserted-by":"crossref","unstructured":"Pham, H.X., Cheung, S., Pavlovic, V.: Speech-driven 3D facial animation with implicit emotional awareness: a deep learning approach. In: 2017 IEEE Conference on Computer Vision and Pattern Recognition Workshops, CVPR Workshops 2017, Honolulu, HI, USA, 21\u201326 July 2017, pp. 2328\u20132336. IEEE Computer Society (2017)","DOI":"10.1109\/CVPRW.2017.287"},{"issue":"4","key":"42_CR23","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073640","volume":"36","author":"S Suwajanakorn","year":"2017","unstructured":"Suwajanakorn, S., Seitz, S.M., Kemelmacher-Shlizerman, I.: Synthesizing Obama: learning lip sync from audio. ACM Trans. Graph. (Proceedings of SIGGRAPH) 36(4), 1\u201313 (2017)","journal-title":"ACM Trans. Graph. (Proceedings of SIGGRAPH)"},{"key":"42_CR24","doi-asserted-by":"publisher","first-page":"64","DOI":"10.3389\/fpsyg.2013.00064","volume":"4","author":"J Tarasuik","year":"2013","unstructured":"Tarasuik, J., Kaufman, J., Galligan, R.: Seeing is believing but is hearing? comparing audio and video communication for young children. Front. Psychol. 4, 64 (2013)","journal-title":"Front. Psychol."},{"issue":"4","key":"42_CR25","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3072959.3073699","volume":"36","author":"S Taylor","year":"2017","unstructured":"Taylor, S., et al.: A deep learning approach for generalized speech animation. ACM Trans. Graph. 36(4), 1\u201311 (2017)","journal-title":"ACM Trans. Graph."},{"issue":"2","key":"42_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3182644","volume":"37","author":"J Thies","year":"2018","unstructured":"Thies, J., Zollh\u00f6fer, M., Stamminger, M., Theobalt, C., Nie\u00dfner, M.: FaceVR: real-time gaze-aware facial reenactment in virtual reality. ACM Trans. Graph. 37(2), 1\u201315 (2018)","journal-title":"ACM Trans. Graph."},{"key":"42_CR27","first-page":"1","volume":"37","author":"J Thies","year":"2018","unstructured":"Thies, J., Zollh\u00f6fer, M., Stamminger, M., Theobalt, C., Nie\u00dfner, M.: HeadOn: real-time reenactment of human portrait videos. ACM Trans. Graph. (Proceedings of SIGGRAPH) 37, 1\u201313 (2018)","journal-title":"ACM Trans. Graph. (Proceedings of SIGGRAPH)"},{"key":"42_CR28","doi-asserted-by":"crossref","unstructured":"Thies, J., Zollh\u00f6fer, M., Stamminger, M., Theobalt, C., Nie\u00dfner, M.: Face2Face: real-time face capture and reenactment of RGB videos. In: CVPR (2016)","DOI":"10.1145\/2929464.2929475"},{"key":"42_CR29","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3323035","volume":"38","author":"J Thies","year":"2019","unstructured":"Thies, J., Zollh\u00f6fer, M., Nie\u00dfner, M.: Deferred neural rendering: image synthesis using neural textures. ACM Trans. Graph. (Proceedings of SIGGRAPH) 38, 1\u201312 (2019)","journal-title":"ACM Trans. Graph. (Proceedings of SIGGRAPH)"},{"key":"42_CR30","doi-asserted-by":"crossref","unstructured":"Tzirakis, P., Papaioannou, A., Lattas, A., Tarasiou, M., Schuller, B.W., Zafeiriou, S.: Synthesising 3D facial motion from \u201cin-the-wild\u201d speech. CoRR abs\/1904.07002 (2019)","DOI":"10.1109\/FG47880.2020.00100"},{"key":"42_CR31","doi-asserted-by":"crossref","unstructured":"Vougioukas, K., Petridis, S., Pantic, M.: End-to-end speech-driven facial animation with temporal GANs. In: BMVC (2018)","DOI":"10.1007\/s11263-019-01251-8"},{"issue":"5","key":"42_CR32","doi-asserted-by":"publisher","first-page":"1398","DOI":"10.1007\/s11263-019-01251-8","volume":"128","author":"K Vougioukas","year":"2019","unstructured":"Vougioukas, K., Petridis, S., Pantic, M.: Realistic speech-driven facial animation with GANs. Int. J. Comput. Vis. 128(5), 1398\u20131413 (2019)","journal-title":"Int. J. Comput. Vis."},{"key":"42_CR33","unstructured":"Zhang, H., Goodfellow, I.J., Metaxas, D.N., Odena, A.: Self-attention generative adversarial networks. arXiv:1805.08318 (2018)"},{"key":"42_CR34","doi-asserted-by":"crossref","unstructured":"Zollh\u00f6fer, M., et al.: State of the art on monocular 3D face reconstruction, tracking, and applications. Comput. Graph. Forum (Eurographics State of the Art Reports) 37, 523\u2013550 (2018)","DOI":"10.1111\/cgf.13382"}],"container-title":["Lecture Notes in Computer Science","Computer Vision \u2013 ECCV 2020"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-58517-4_42","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,9]],"date-time":"2024-10-09T00:17:49Z","timestamp":1728433069000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58517-4_42"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585167","9783030585174"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58517-4_42","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"10 October 2020","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":"Glasgow","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"United Kingdom","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 August 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 August 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"16","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"eccv2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/eccv2020.eu\/","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":"OpenReview","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"5025","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":"1360","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":"27% - 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":"7","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)"}},{"value":"The conference was held virtually due to the COVID-19 pandemic. From the ECCV Workshops 249 full papers, 18 short papers, and 21 further contributions were published out of a total of 467 submissions.","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"This content has been made available to all.","name":"free","label":"Free to read"}]}}