{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,7]],"date-time":"2026-03-07T19:08:40Z","timestamp":1772910520991,"version":"3.50.1"},"publisher-location":"New York, NY, USA","reference-count":60,"publisher":"ACM","license":[{"start":{"date-parts":[[2020,10,21]],"date-time":"2020-10-21T00:00:00Z","timestamp":1603238400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2020,10,21]]},"DOI":"10.1145\/3382507.3418840","type":"proceedings-article","created":{"date-parts":[[2020,10,22]],"date-time":"2020-10-22T10:04:35Z","timestamp":1603361075000},"page":"378-386","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":36,"title":["Modality Dropout for Improved Performance-driven Talking Faces"],"prefix":"10.1145","author":[{"given":"Ahmed","family":"Hussen Abdelaziz","sequence":"first","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Barry-John","family":"Theobald","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Paul","family":"Dixon","sequence":"additional","affiliation":[{"name":"Apple, Zurick, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Reinhard","family":"Knothe","sequence":"additional","affiliation":[{"name":"Apple, Zurick, Switzerland"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Nicholas","family":"Apostoloff","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Sachin","family":"Kajareker","sequence":"additional","affiliation":[{"name":"Apple, Cupertino, CA, USA"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2020,10,22]]},"reference":[{"key":"e_1_3_2_2_1_1","first-page":"3","article-title":"Comparing fusion models for DNN-based audiovisual continuous speech recognition","volume":"26","author":"Abdelaziz A.","year":"2017","unstructured":"A. Abdelaziz . 2017 . Comparing fusion models for DNN-based audiovisual continuous speech recognition . Transactions on Audio, Speech, and Language Processing , Vol. 26 , 3 (March 2017), 475--484. A. Abdelaziz. 2017. Comparing fusion models for DNN-based audiovisual continuous speech recognition. Transactions on Audio, Speech, and Language Processing, Vol. 26, 3 (March 2017), 475--484.","journal-title":"Transactions on Audio, Speech, and Language Processing"},{"key":"e_1_3_2_2_2_1","volume-title":"Speaker-Independent Speech-Driven Visual Speech Synthesis Using Domain-Adapted Acoustic Models. In International Conference on Multimodal Interaction. 220--225","author":"Abdelaziz A.","unstructured":"A. Abdelaziz , B. Theobald , J. Binder , G. Fanelli , P. Dixon , N. Apostoloff , T. Weise , and S. Kajareker . 2019 . Speaker-Independent Speech-Driven Visual Speech Synthesis Using Domain-Adapted Acoustic Models. In International Conference on Multimodal Interaction. 220--225 . A. Abdelaziz, B. Theobald, J. Binder, G. Fanelli, P. Dixon, N. Apostoloff, T. Weise, and S. Kajareker. 2019. Speaker-Independent Speech-Driven Visual Speech Synthesis Using Domain-Adapted Acoustic Models. In International Conference on Multimodal Interaction. 220--225."},{"key":"e_1_3_2_2_3_1","first-page":"5","article-title":"Learning Dynamic Stream Weights For Coupled-HMM-Based Audio-Visual Speech Recognition","volume":"23","author":"Abdelaziz A.","year":"2015","unstructured":"A. Abdelaziz , S. Zeiler , and D. Kolossa . 2015 . Learning Dynamic Stream Weights For Coupled-HMM-Based Audio-Visual Speech Recognition . Transactions on Audio, Speech, and Language Processing , Vol. 23 , 5 (May 2015), 863--876. A. Abdelaziz, S. Zeiler, and D. Kolossa. 2015. Learning Dynamic Stream Weights For Coupled-HMM-Based Audio-Visual Speech Recognition. Transactions on Audio, Speech, and Language Processing, Vol. 23, 5 (May 2015), 863--876.","journal-title":"Transactions on Audio, Speech, and Language Processing"},{"key":"e_1_3_2_2_4_1","unstructured":"T. Afouras J. Chung A. Senior O. Vinyals and A. Zisserman. 2018. Deep Audio-Visual Speech Recognition. CoRR Vol. abs\/1809.02108 (2018). arxiv: 1809.02108 http:\/\/arxiv.org\/abs\/1809.02108  T. Afouras J. Chung A. Senior O. Vinyals and A. Zisserman. 2018. Deep Audio-Visual Speech Recognition. CoRR Vol. abs\/1809.02108 (2018). arxiv: 1809.02108 http:\/\/arxiv.org\/abs\/1809.02108"},{"key":"e_1_3_2_2_5_1","volume-title":"The Digital Emily Project: Photoreal Facial Modeling and Animation. In ACM SIGGRAPH 2009 Courses. 12:1--12:15","author":"Alexander O.","unstructured":"O. Alexander , M. Rogers , W. Lambeth , M. Chiang , and P. Debevec . 2009 . The Digital Emily Project: Photoreal Facial Modeling and Animation. In ACM SIGGRAPH 2009 Courses. 12:1--12:15 . O. Alexander, M. Rogers, W. Lambeth, M. Chiang, and P. Debevec. 2009. The Digital Emily Project: Photoreal Facial Modeling and Animation. In ACM SIGGRAPH 2009 Courses. 12:1--12:15."},{"key":"e_1_3_2_2_6_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition. 3382--3389","author":"Anderson R.","unstructured":"R. Anderson , B. Stenger , V. Wan , and R. Cipolla . 2013. Expressive visual text-to-speech using active appearance models . In IEEE Conference on Computer Vision and Pattern Recognition. 3382--3389 . R. Anderson, B. Stenger, V. Wan, and R. Cipolla. 2013. Expressive visual text-to-speech using active appearance models. In IEEE Conference on Computer Vision and Pattern Recognition. 3382--3389."},{"key":"e_1_3_2_2_7_1","volume-title":"International Conference on Auditory-Visual Speech Processing. 175--180","author":"Arslan L.","unstructured":"L. Arslan and D. Talkin . 1998. 3D face point trajectory synthesis using an automatically derived visual phoneme similarity matrix . In International Conference on Auditory-Visual Speech Processing. 175--180 . L. Arslan and D. Talkin. 1998. 3D face point trajectory synthesis using an automatically derived visual phoneme similarity matrix. In International Conference on Auditory-Visual Speech Processing. 175--180."},{"key":"e_1_3_2_2_8_1","doi-asserted-by":"publisher","DOI":"10.1145\/2010324.1964970"},{"key":"e_1_3_2_2_9_1","volume-title":"International Conference on Computer Vision. 3604--3612","author":"Bolkart T.","unstructured":"T. Bolkart and S. Wuhrer . 2015. A Groupwise Multilinear Correspondence Optimization for 3D Faces . In International Conference on Computer Vision. 3604--3612 . T. Bolkart and S. Wuhrer. 2015. A Groupwise Multilinear Correspondence Optimization for 3D Faces. In International Conference on Computer Vision. 3604--3612."},{"key":"e_1_3_2_2_10_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2461976"},{"key":"e_1_3_2_2_11_1","doi-asserted-by":"crossref","unstructured":"M. Brand. 1999. Voice puppetry. In SIGGRAPH. 21--28.  M. Brand. 1999. Voice puppetry. In SIGGRAPH. 21--28.","DOI":"10.1145\/311535.311537"},{"key":"e_1_3_2_2_12_1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258880"},{"key":"e_1_3_2_2_13_1","doi-asserted-by":"publisher","DOI":"10.1145\/2766943"},{"key":"e_1_3_2_2_14_1","doi-asserted-by":"publisher","DOI":"10.1145\/2601097.2601204"},{"key":"e_1_3_2_2_15_1","doi-asserted-by":"publisher","DOI":"10.1023\/A:1011171430700"},{"key":"e_1_3_2_2_16_1","volume-title":"Lip Reading Sentences in the Wild. In Conference on Computer Vision and Pattern Recognition. 3444--3453","author":"Chung J.","unstructured":"J. Chung , A. Senior , O. Vinyals , and A. Zisserman . 2016 . Lip Reading Sentences in the Wild. In Conference on Computer Vision and Pattern Recognition. 3444--3453 . J. Chung, A. Senior, O. Vinyals, and A. Zisserman. 2016. Lip Reading Sentences in the Wild. In Conference on Computer Vision and Pattern Recognition. 3444--3453."},{"key":"e_1_3_2_2_17_1","unstructured":"S. Chung J. Chung and H. Kang. 2018. Perfect match: Improved cross-modal embeddings for audio-visual synchronisation. CoRR Vol. abs\/1809.08001 (2018). arxiv: 1809.08001 http:\/\/arxiv.org\/abs\/1809.08001  S. Chung J. Chung and H. Kang. 2018. Perfect match: Improved cross-modal embeddings for audio-visual synchronisation. CoRR Vol. abs\/1809.08001 (2018). arxiv: 1809.08001 http:\/\/arxiv.org\/abs\/1809.08001"},{"key":"e_1_3_2_2_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/6046.865480"},{"key":"e_1_3_2_2_19_1","unstructured":"D. Cudeiro T. Bolkart C. Laidlaw A. Ranjan and M. Black. 2019. Capture Learning and Synthesis of 3D Speaking Styles. CoRR Vol. abs\/1905.03079 (2019). arxiv: 1905.03079 http:\/\/arxiv.org\/abs\/1905.03079  D. Cudeiro T. Bolkart C. Laidlaw A. Ranjan and M. Black. 2019. Capture Learning and Synthesis of 3D Speaking Styles. CoRR Vol. abs\/1905.03079 (2019). arxiv: 1905.03079 http:\/\/arxiv.org\/abs\/1905.03079"},{"key":"e_1_3_2_2_20_1","doi-asserted-by":"crossref","unstructured":"P. Ekman and W. Friesen. 1978. Facial Action Coding System: A Technique for the Measurement of Facial Movement .Consulting Psychologists Press Palo Alto.  P. Ekman and W. Friesen. 1978. Facial Action Coding System: A Technique for the Measurement of Facial Movement .Consulting Psychologists Press Palo Alto.","DOI":"10.1037\/t27734-000"},{"key":"e_1_3_2_2_21_1","volume-title":"Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation. CoRR","author":"Ephrat A.","year":"2018","unstructured":"A. Ephrat , I. Mosseri , O. Lang , T. Dekel , K. Wilson , A. Hassidim , W. Freeman , and M. Rubinstein . 2018 . Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation. CoRR , Vol. abs\/ 1804 .03619 (2018). arxiv: 1804.03619 http:\/\/arxiv.org\/abs\/1804.03619 A. Ephrat, I. Mosseri, O. Lang, T. Dekel, K. Wilson, A. Hassidim, W. Freeman, and M. Rubinstein. 2018. Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation. CoRR, Vol. abs\/1804.03619 (2018). arxiv: 1804.03619 http:\/\/arxiv.org\/abs\/1804.03619"},{"key":"e_1_3_2_2_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/566654.566594"},{"key":"e_1_3_2_2_23_1","volume-title":"International Conference on Acoustics, Speech and Signal Processing. 4884--4888","author":"Fan B.","unstructured":"B. Fan , L. Wang , F. Soong , and L. Xie . 2015. Photo-real talking head with deep bidirectional LSTM . In International Conference on Acoustics, Speech and Signal Processing. 4884--4888 . B. Fan, L. Wang, F. Soong, and L. Xie. 2015. Photo-real talking head with deep bidirectional LSTM. In International Conference on Acoustics, Speech and Signal Processing. 4884--4888."},{"key":"e_1_3_2_2_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2005.843341"},{"key":"e_1_3_2_2_25_1","volume-title":"Vdub: Modifying face video of actors for plausible visual alignment to a dubbed audio track. In Computer graphics forum","author":"Garrido P.","year":"2015","unstructured":"P. Garrido , L. Valgaerts , H. Sarmadi , I. Steiner , K. Varanasi , P. Perez , and C. Theobalt . 2015 . Vdub: Modifying face video of actors for plausible visual alignment to a dubbed audio track. In Computer graphics forum , Vol. 34 . 193--204. P. Garrido, L. Valgaerts, H. Sarmadi, I. Steiner, K. Varanasi, P. Perez, and C. Theobalt. 2015. Vdub: Modifying face video of actors for plausible visual alignment to a dubbed audio track. In Computer graphics forum, Vol. 34. 193--204."},{"key":"e_1_3_2_2_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2004.840611"},{"key":"e_1_3_2_2_27_1","unstructured":"S. Jalalifar H. Hasani and H. Aghajan. 2018. Speech-Driven Facial Reenactment Using Conditional Generative Adversarial Networks. arXiv preprint arXiv:1803.07461 (2018).  S. Jalalifar H. Hasani and H. Aghajan. 2018. Speech-Driven Facial Reenactment Using Conditional Generative Adversarial Networks. arXiv preprint arXiv:1803.07461 (2018)."},{"key":"e_1_3_2_2_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"e_1_3_2_2_29_1","volume-title":"International Conference on Knowledge Discovery and Data Mining. 577--586","author":"Kim T.","unstructured":"T. Kim , Y. Yue , S. Taylor , and I. Matthews . 2015. A decision tree framework for spatiotemporal sequence prediction . In International Conference on Knowledge Discovery and Data Mining. 577--586 . T. Kim, Y. Yue, S. Taylor, and I. Matthews. 2015. A decision tree framework for spatiotemporal sequence prediction. In International Conference on Knowledge Discovery and Data Mining. 577--586."},{"key":"e_1_3_2_2_30_1","first-page":"1","article-title":"Production-level Facial Performance Capture Using Deep Convolutional Neural Networks","volume":"10","author":"Laine S.","year":"2017","unstructured":"S. Laine , T. Karras , T. Aila , A. Herva , S. Saito , R. Yu , H. Li , and J. Lehtinen . 2017 . Production-level Facial Performance Capture Using Deep Convolutional Neural Networks . In Symposium on Computer Animation. 10 : 1 -- 10 :10. S. Laine, T. Karras, T. Aila, A. Herva, S. Saito, R. Yu, H. Li, and J. Lehtinen. 2017. Production-level Facial Performance Capture Using Deep Convolutional Neural Networks. In Symposium on Computer Animation. 10:1--10:10.","journal-title":"Symposium on Computer Animation."},{"key":"e_1_3_2_2_31_1","unstructured":"S. Latif R. Rana J. Qadir and J. Epps. 2017. Variational Autoencoders for Learning Latent Representations of Speech Emotion. ArXiv Vol. abs\/1712.08708 (2017).  S. Latif R. Rana J. Qadir and J. Epps. 2017. Variational Autoencoders for Learning Latent Representations of Speech Emotion. ArXiv Vol. abs\/1712.08708 (2017)."},{"key":"e_1_3_2_2_32_1","first-page":"1","article-title":"Example-based Facial Rigging","volume":"32","author":"Li H.","year":"2010","unstructured":"H. Li , T. Weise , and M. Pauly . 2010 . Example-based Facial Rigging . In SIGGRAPH. 32 : 1 -- 32 :6. H. Li, T. Weise, and M. Pauly. 2010. Example-based Facial Rigging. In SIGGRAPH. 32:1--32:6.","journal-title":"SIGGRAPH."},{"key":"e_1_3_2_2_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/2461912.2462019"},{"key":"e_1_3_2_2_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/2816795.2818122"},{"key":"e_1_3_2_2_35_1","first-page":"7","article-title":"Comprehensive many-to-many phoneme-to-viseme mapping and its application for concatenative visual speech synthesis","volume":"55","author":"Mattheyses W.","year":"2013","unstructured":"W. Mattheyses , L. Latacz , and W. Verhelst . 2013 . Comprehensive many-to-many phoneme-to-viseme mapping and its application for concatenative visual speech synthesis . Speech Communication , Vol. 55 , 7 -- 8 (2013), 857--876. W. Mattheyses, L. Latacz, and W. Verhelst. 2013. Comprehensive many-to-many phoneme-to-viseme mapping and its application for concatenative visual speech synthesis. Speech Communication, Vol. 55, 7--8 (2013), 857--876.","journal-title":"Speech Communication"},{"key":"e_1_3_2_2_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2015.2461544"},{"key":"e_1_3_2_2_37_1","unstructured":"J. Ovalle T. Solorio M. Montes-y G\u00f3mez and F. Gonz\u00e1lez. 2017. Gated Multimodal Units for Information Fusion. ArXiv Vol. abs\/1702.01992 (2017).  J. Ovalle T. Solorio M. Montes-y G\u00f3mez and F. Gonz\u00e1lez. 2017. Gated Multimodal Units for Information Fusion. ArXiv Vol. abs\/1702.01992 (2017)."},{"key":"e_1_3_2_2_38_1","volume-title":"International Conference on Acoustics, Speech and Signal Processing","author":"Parker J.","year":"2017","unstructured":"J. Parker , R. Maia , Y. Stylianou , and R. Cipolla . 2017. Expressive visual text to speech and expression adaptation using deep neural networks . International Conference on Acoustics, Speech and Signal Processing ( 2017 ), 4920--4924. J. Parker, R. Maia, Y. Stylianou, and R. Cipolla. 2017. Expressive visual text to speech and expression adaptation using deep neural networks. International Conference on Acoustics, Speech and Signal Processing (2017), 4920--4924."},{"key":"e_1_3_2_2_39_1","doi-asserted-by":"crossref","unstructured":"H. Pham Y. Wang and V. Pavlovic. 2017. End-to-end learning for 3D facial animation from raw waveforms of speech. arXiv preprint arXiv:1710.00920 (2017).  H. Pham Y. Wang and V. Pavlovic. 2017. End-to-end learning for 3D facial animation from raw waveforms of speech. arXiv preprint arXiv:1710.00920 (2017).","DOI":"10.1145\/3242969.3243017"},{"key":"e_1_3_2_2_40_1","unstructured":"N. Sadoughi and C. Busso. 2018. Speech-Driven Expressive Talking Lips with Conditional Sequential Generative Adversarial Networks. CoRR Vol. abs\/1806.00154 (2018). arxiv: 1806.00154 http:\/\/arxiv.org\/abs\/1806.00154  N. Sadoughi and C. Busso. 2018. Speech-Driven Expressive Talking Lips with Conditional Sequential Generative Adversarial Networks. CoRR Vol. abs\/1806.00154 (2018). arxiv: 1806.00154 http:\/\/arxiv.org\/abs\/1806.00154"},{"key":"e_1_3_2_2_41_1","volume-title":"International Symposium on System Integration (SII). IEEE, 100--105","author":"Shimba T.","unstructured":"T. Shimba , R. Sakurai , H. Yamazoe , and J. Lee . 2015. Talking heads synthesis from audio with deep neural networks . In International Symposium on System Integration (SII). IEEE, 100--105 . T. Shimba, R. Sakurai, H. Yamazoe, and J. Lee. 2015. Talking heads synthesis from audio with deep neural networks. In International Symposium on System Integration (SII). IEEE, 100--105."},{"key":"e_1_3_2_2_42_1","unstructured":"S. Shon T. Oh and J. Glass. 2018. Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion. CoRR Vol. abs\/1811.10813 (2018). arxiv: 1811.10813 http:\/\/arxiv.org\/abs\/1811.10813  S. Shon T. Oh and J. Glass. 2018. Noise-tolerant Audio-visual Online Person Verification using an Attention-based Neural Network Fusion. CoRR Vol. abs\/1811.10813 (2018). arxiv: 1811.10813 http:\/\/arxiv.org\/abs\/1811.10813"},{"key":"e_1_3_2_2_43_1","volume-title":"Conference on Computer Vision and Pattern Recognition","volume":"2","author":"Song M.","unstructured":"M. Song , J. Bu , C. Chen , and N. Li . 2004. Audio-visual based emotion recognition -- A new approach . In Conference on Computer Vision and Pattern Recognition , Vol. 2 . M. Song, J. Bu, C. Chen, and N. Li. 2004. Audio-visual based emotion recognition -- A new approach. In Conference on Computer Vision and Pattern Recognition, Vol. 2."},{"key":"e_1_3_2_2_44_1","doi-asserted-by":"crossref","unstructured":"Y. Song J. Zhu X. Wang and H. Qi. 2018. Talking Face Generation by Conditional Recurrent Adversarial Network. arXiv preprint arXiv:1804.04786 (2018).  Y. Song J. Zhu X. Wang and H. Qi. 2018. Talking Face Generation by Conditional Recurrent Adversarial Network. arXiv preprint arXiv:1804.04786 (2018).","DOI":"10.24963\/ijcai.2019\/129"},{"key":"e_1_3_2_2_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"e_1_3_2_2_46_1","doi-asserted-by":"crossref","unstructured":"S. Taylor A. Kato B. Milner and I. Matthews. 2016. Audio-to-visual speech conversion using deep neural networks. In Interspeech .  S. Taylor A. Kato B. Milner and I. Matthews. 2016. Audio-to-visual speech conversion using deep neural networks. In Interspeech .","DOI":"10.21437\/Interspeech.2016-483"},{"key":"e_1_3_2_2_47_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073699"},{"key":"e_1_3_2_2_48_1","volume-title":"Symposium on Computer Animation. 275--284","author":"Taylor S.","unstructured":"S. Taylor , M. Mahler , B. Theobald , and I. Matthews . 2012. Dynamic units of visual speech . In Symposium on Computer Animation. 275--284 . S. Taylor, M. Mahler, B. Theobald, and I. Matthews. 2012. Dynamic units of visual speech. In Symposium on Computer Animation. 275--284."},{"key":"e_1_3_2_2_49_1","unstructured":"J. Thies M. Elgharib A. Tewari C. Theobalt and M. Niessner. 2019. Neural Voice Puppetry: Audio-driven Facial Reenactment. arXiv 2019 (2019).  J. Thies M. Elgharib A. Tewari C. Theobalt and M. Niessner. 2019. Neural Voice Puppetry: Audio-driven Facial Reenactment. arXiv 2019 (2019)."},{"key":"e_1_3_2_2_50_1","first-page":"96","article-title":"Face2Face","volume":"62","author":"Thies J.","year":"2018","unstructured":"J. Thies , M. Zollhoefer , M. Stamminger , C. Theobalt , and M. Niessner . 2018 . Face2Face : Real-time Face Capture and Reenactment of RGB Videos. Commun. ACM , Vol. 62 , 1 (2018), 96 -- 104 . J. Thies, M. Zollhoefer, M. Stamminger, C. Theobalt, and M. Niessner. 2018. Face2Face: Real-time Face Capture and Reenactment of RGB Videos. Commun. ACM, Vol. 62, 1 (2018), 96--104.","journal-title":"Real-time Face Capture and Reenactment of RGB Videos. Commun. ACM"},{"key":"e_1_3_2_2_51_1","volume-title":"Canonical correlation analysis. Encyclopedia of statistics in behavioral science","author":"Thompson B.","year":"2005","unstructured":"B. Thompson . 2005. Canonical correlation analysis. Encyclopedia of statistics in behavioral science ( 2005 ). B. Thompson. 2005. Canonical correlation analysis. Encyclopedia of statistics in behavioral science (2005)."},{"key":"e_1_3_2_2_52_1","unstructured":"K. Vougioukas S. Petridis and M. Pantic. 2018. End-to-end speech-driven facial animation with temporal gans. arXiv preprint arXiv:1805.09313 (2018).  K. Vougioukas S. Petridis and M. Pantic. 2018. End-to-end speech-driven facial animation with temporal gans. arXiv preprint arXiv:1805.09313 (2018)."},{"key":"e_1_3_2_2_53_1","doi-asserted-by":"crossref","unstructured":"L. Wang X. Qian L. Ma Y. Qian Y. Chen and F. Soong. 2008. A real-time text to audio-visual speech synthesis system. In Interspeech .  L. Wang X. Qian L. Ma Y. Qian Y. Chen and F. Soong. 2008. A real-time text to audio-visual speech synthesis system. In Interspeech .","DOI":"10.21437\/Interspeech.2008-596"},{"key":"e_1_3_2_2_54_1","first-page":"1","article-title":"Realtime performance-based facial animation. In ACM transactions on graphics (TOG), Vol. 30","volume":"77","author":"Weise T.","year":"2011","unstructured":"T. Weise , S. Bouaziz , H. Li , and M. Pauly . 2011 . Realtime performance-based facial animation. In ACM transactions on graphics (TOG), Vol. 30 . ACM , 77 : 1 -- 77 :10. T. Weise, S. Bouaziz, H. Li, and M. Pauly. 2011. Realtime performance-based facial animation. In ACM transactions on graphics (TOG), Vol. 30. ACM, 77:1--77:10.","journal-title":"ACM"},{"key":"e_1_3_2_2_55_1","volume-title":"SIGGRAPH.","author":"Williams L.","unstructured":"L. Williams . 1990. Performance-driven facial animation . In SIGGRAPH. Vol. 24 . 235--242. L. Williams. 1990. Performance-driven facial animation. In SIGGRAPH. Vol. 24. 235--242."},{"key":"e_1_3_2_2_56_1","doi-asserted-by":"crossref","unstructured":"C. Wu D. Bradley M. Gross and T. Beeler. 2016. An Anatomically-constrained Local Deformation Model for Monocular Face Capture. ACM transactions on graphics (TOG) Vol. 35 4 (2016) 115:1--115:12.  C. Wu D. Bradley M. Gross and T. Beeler. 2016. An Anatomically-constrained Local Deformation Model for Monocular Face Capture. ACM transactions on graphics (TOG) Vol. 35 4 (2016) 115:1--115:12.","DOI":"10.1145\/2897824.2925882"},{"key":"e_1_3_2_2_57_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2006.12.001"},{"key":"e_1_3_2_2_58_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2006.888009"},{"key":"e_1_3_2_2_59_1","unstructured":"A. Zadeh M. Chen S. Poria E. Cambria and L. Morency. 2017. Tensor Fusion Network for Multimodal Sentiment Analysis. CoRR Vol. abs\/1707.07250 (2017). arxiv: 1707.07250 http:\/\/arxiv.org\/abs\/1707.07250  A. Zadeh M. Chen S. Poria E. Cambria and L. Morency. 2017. Tensor Fusion Network for Multimodal Sentiment Analysis. CoRR Vol. abs\/1707.07250 (2017). arxiv: 1707.07250 http:\/\/arxiv.org\/abs\/1707.07250"},{"key":"e_1_3_2_2_60_1","volume-title":"International Conference on Automatic Face & Gesture Recognition. 200--207","author":"Zhenliang H.","unstructured":"H. Zhenliang , K. Meina , J. Jie , C. Xilin , and S. Shiguang . 2017. A Fully End-to-End Cascaded CNN for Facial Landmark Detection . In International Conference on Automatic Face & Gesture Recognition. 200--207 . H. Zhenliang, K. Meina, J. Jie, C. Xilin, and S. Shiguang. 2017. A Fully End-to-End Cascaded CNN for Facial Landmark Detection. In International Conference on Automatic Face & Gesture Recognition. 200--207."}],"event":{"name":"ICMI '20: INTERNATIONAL CONFERENCE ON MULTIMODAL INTERACTION","location":"Virtual Event Netherlands","acronym":"ICMI '20","sponsor":["SIGCHI ACM Special Interest Group on Computer-Human Interaction"]},"container-title":["Proceedings of the 2020 International Conference on Multimodal Interaction"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3382507.3418840","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3382507.3418840","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,17]],"date-time":"2025-06-17T22:02:48Z","timestamp":1750197768000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3382507.3418840"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020,10,21]]},"references-count":60,"alternative-id":["10.1145\/3382507.3418840","10.1145\/3382507"],"URL":"https:\/\/doi.org\/10.1145\/3382507.3418840","relation":{},"subject":[],"published":{"date-parts":[[2020,10,21]]},"assertion":[{"value":"2020-10-22","order":2,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}