{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:13:27Z","timestamp":1784736807922,"version":"3.55.0"},"publisher-location":"Cham","reference-count":37,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030585761","type":"print"},{"value":"9783030585778","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\/978-3-030-58577-8_25","type":"book-chapter","created":{"date-parts":[[2020,9,23]],"date-time":"2020-09-23T14:04:27Z","timestamp":1600869867000},"page":"408-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":77,"title":["Speech-Driven Facial Animation Using Cascaded GANs for Learning of Motion and Texture"],"prefix":"10.1007","author":[{"given":"Dipanjan","family":"Das","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sandika","family":"Biswas","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Sanjana","family":"Sinha","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Brojeshwar","family":"Bhowmick","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2020,9,24]]},"reference":[{"key":"25_CR1","doi-asserted-by":"crossref","unstructured":"Baltrusaitis, T., Zadeh, A., Lim, Y.C., Morency, L.P.: Openface 2.0: facial behavior analysis toolkit. In: 2018 13th IEEE International Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 59\u201366. IEEE (2018)","DOI":"10.1109\/FG.2018.00019"},{"key":"25_CR2","unstructured":"Brock, A., Donahue, J., Simonyan, K.: Large scale GAN training for high fidelity natural image synthesis. arXiv preprint arXiv:1809.11096 (2018)"},{"key":"25_CR3","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"538","DOI":"10.1007\/978-3-030-01234-2_32","volume-title":"Computer Vision \u2013 ECCV 2018","author":"L Chen","year":"2018","unstructured":"Chen, L., Li, Z., Maddox, R.K., Duan, Z., Xu, C.: Lip movements generation at a glance. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 538\u2013553. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_32"},{"key":"25_CR4","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":"25_CR5","doi-asserted-by":"crossref","unstructured":"Chen, L., Srivastava, S., Duan, Z., Xu, C.: Deep cross-modal audio-visual generation. In: Proceedings of the on Thematic Workshops of ACM Multimedia. pp. 349\u2013357. ACM (2017)","DOI":"10.1145\/3126686.3126723"},{"key":"25_CR6","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Workshop on Multi-view Lip-reading, ACCV (2016)","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"25_CR7","unstructured":"Chung, J.S., Jamaludin, A., Zisserman, A.: You said that? arXiv preprint arXiv:1705.02966 (2017)"},{"key":"25_CR8","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"87","DOI":"10.1007\/978-3-319-54184-6_6","volume-title":"Computer Vision \u2013 ACCV 2016","author":"JS Chung","year":"2017","unstructured":"Chung, J.S., Zisserman, A.: Lip reading in the wild. In: Lai, S.-H., Lepetit, V., Nishino, K., Sato, Y. (eds.) ACCV 2016. LNCS, vol. 10112, pp. 87\u2013103. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-54184-6_6"},{"issue":"5","key":"25_CR9","doi-asserted-by":"publisher","first-page":"2421","DOI":"10.1121\/1.2229005","volume":"120","author":"M Cooke","year":"2006","unstructured":"Cooke, M., Barker, J., Cunningham, S., Shao, X.: An audio-visual corpus for speech perception and automatic speech recognition. J. Acoust. Soc. Am. 120(5), 2421\u20132424 (2006)","journal-title":"J. Acoust. Soc. Am."},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Cudeiro, D., Bolkart, T., Laidlaw, C., Ranjan, A., Black, M.J.: Capture, learning, and synthesis of 3d speaking styles. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 10101\u201310111 (2019)","DOI":"10.1109\/CVPR.2019.01034"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Fan, B., Wang, L., Soong, F.K., Xie, L.: Photo-real talking head with deep bidirectional lstm. In: 2015 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 4884\u20134888. IEEE (2015)","DOI":"10.1109\/ICASSP.2015.7178899"},{"key":"25_CR12","unstructured":"Finn, C., Abbeel, P., Levine, S.: Model-agnostic meta-learning for fast adaptation of deep networks. In: Proceedings of the 34th International Conference on Machine Learning-Volume 70, pp. 1126\u20131135. JMLR. org (2017)"},{"key":"25_CR13","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, vol. 34, pp. 193\u2013204. Wiley Online Library (2015)","DOI":"10.1111\/cgf.12552"},{"key":"25_CR14","doi-asserted-by":"crossref","unstructured":"Gretton, A., Borgwardt, K., Rasch, M., Sch\u00f6lkopf, B., Smola, A.J.: A kernel method for the two-sample-problem. In: Advances in Neural Information Processing Systems, pp. 513\u2013520 (2007)","DOI":"10.7551\/mitpress\/7503.003.0069"},{"key":"25_CR15","unstructured":"Hannun, A., et al.: Deep speech: scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)"},{"issue":"5","key":"25_CR16","doi-asserted-by":"publisher","first-page":"603","DOI":"10.1109\/TMM.2015.2407694","volume":"17","author":"N Harte","year":"2015","unstructured":"Harte, N., Gillen, E.: TCD-TIMIT: an audio-visual corpus of continuous speech. IEEE Trans. Multimedia 17(5), 603\u2013615 (2015)","journal-title":"IEEE Trans. Multimedia"},{"key":"25_CR17","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":"25_CR18","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":"25_CR19","doi-asserted-by":"crossref","unstructured":"Kazemi, V., Sullivan, J.: One millisecond face alignment with an ensemble of regression trees. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 1867\u20131874 (2014)","DOI":"10.1109\/CVPR.2014.241"},{"key":"25_CR20","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"25_CR21","doi-asserted-by":"crossref","unstructured":"Li, Y., Chang, M.C., Lyu, S.: In ICTU oculi: exposing AI generated fake face videos by detecting eye blinking. arXiv preprint arXiv:1806.02877 (2018)","DOI":"10.1109\/WIFS.2018.8630787"},{"key":"25_CR22","doi-asserted-by":"crossref","unstructured":"Mittal, G., Wang, B.: Animating face using disentangled audio representations. In: The IEEE Winter Conference on Applications of Computer Vision, pp. 3290\u20133298 (2020)","DOI":"10.1109\/WACV45572.2020.9093527"},{"key":"25_CR23","unstructured":"Miyato, T., Kataoka, T., Koyama, M., Yoshida, Y.: Spectral normalization for generative adversarial networks. arXiv preprint arXiv:1802.05957 (2018)"},{"key":"25_CR24","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Chung, J.S., Zisserman, A.: VoxCeleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)","DOI":"10.21437\/Interspeech.2017-950"},{"key":"25_CR25","doi-asserted-by":"crossref","unstructured":"Narvekar, N.D., Karam, L.J.: A no-reference perceptual image sharpness metric based on a cumulative probability of blur detection. In: 2009 International Workshop on Quality of Multimedia Experience, pp. 87\u201391. IEEE (2009)","DOI":"10.1109\/QOMEX.2009.5246972"},{"key":"25_CR26","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A., et al.: Deep face recognition. In: BMVC, vol. 1, 6 (2015)","DOI":"10.5244\/C.29.41"},{"key":"25_CR27","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: FaceNet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"25_CR28","doi-asserted-by":"crossref","unstructured":"Song, Y., Zhu, J., Wang, X., Qi, H.: Talking face generation by conditional recurrent adversarial network. arXiv preprint arXiv:1804.04786 (2018)","DOI":"10.24963\/ijcai.2019\/129"},{"issue":"4","key":"25_CR29","doi-asserted-by":"publisher","first-page":"590","DOI":"10.1109\/TPAMI.2005.86","volume":"27","author":"A Srivastava","year":"2005","unstructured":"Srivastava, A., Joshi, S.H., Mio, W., Liu, X.: Statistical shape analysis: clustering, learning, and testing. IEEE Trans. Pattern Anal. Mach. Intell. 27(4), 590\u2013602 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"issue":"4","key":"25_CR30","doi-asserted-by":"publisher","first-page":"95","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. Graphics (TOG) 36(4), 95 (2017)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"25_CR31","unstructured":"Vougioukas, K., Center, S.A., Petridis, S., Pantic, M.: End-to-end speech-driven realistic facial animation with temporal GANs. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition Workshops, pp. 37\u201340 (2019)"},{"key":"25_CR32","doi-asserted-by":"crossref","unstructured":"Vougioukas, K., Petridis, S., Pantic, M.: Realistic speech-driven facial animation with GANs. Int. J. Comput. Vision pp. 1\u201316 (2019)","DOI":"10.1007\/s11263-019-01251-8"},{"key":"25_CR33","unstructured":"Xu, B., Wang, N., Chen, T., Li, M.: Empirical evaluation of rectified activations in convolutional network. arXiv preprint arXiv:1505.00853 (2015)"},{"key":"25_CR34","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"334","DOI":"10.1007\/978-3-030-01261-8_20","volume-title":"Computer Vision \u2013 ECCV 2018","author":"C Yu","year":"2018","unstructured":"Yu, C., Wang, J., Peng, C., Gao, C., Yu, G., Sang, N.: BiSeNet: bilateral segmentation network for real-time semantic segmentation. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 334\u2013349. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_20"},{"key":"25_CR35","unstructured":"Zhang, H., Goodfellow, I., Metaxas, D., Odena, A.: Self-attention generative adversarial networks. arXiv preprint arXiv:1805.08318 (2018)"},{"key":"25_CR36","doi-asserted-by":"crossref","unstructured":"Zhou, H., Liu, Y., Liu, Z., Luo, P., Wang, X.: Talking face generation by adversarially disentangled audio-visual representation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 9299\u20139306 (2019)","DOI":"10.1609\/aaai.v33i01.33019299"},{"key":"25_CR37","unstructured":"Zhu, H., Zheng, A., Huang, H., He, R.: High-resolution talking face generation via mutual information approximation. arXiv preprint arXiv:1812.06589 (2018)"}],"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\/978-3-030-58577-8_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,9,23]],"date-time":"2024-09-23T00:06:15Z","timestamp":1727049975000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-58577-8_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030585761","9783030585778"],"references-count":37,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-58577-8_25","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":"24 September 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.","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"}]}}