{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,25]],"date-time":"2026-01-25T01:52:36Z","timestamp":1769305956586,"version":"3.49.0"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819984312","type":"print"},{"value":"9789819984329","type":"electronic"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"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":[[2024]]},"DOI":"10.1007\/978-981-99-8432-9_4","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"41-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Blendshape-Based Migratable Speech-Driven 3D Facial Animation with\u00a0Overlapping Chunking-Transformer"],"prefix":"10.1007","author":[{"given":"Jixi","family":"Chen","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaoliang","family":"Ma","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jun","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"4_CR1","unstructured":"Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and mandarin. In: ICML, pp. 173\u2013182. PMLR (2016)"},{"key":"4_CR2","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: a framework for self-supervised learning of speech representations. Adv. Neural Inf. Process. Syst. 33, 12449\u201312460 (2020)"},{"key":"4_CR3","doi-asserted-by":"crossref","unstructured":"Conneau, A., Baevski, A., Collobert, R., Mohamed, A., Auli, M.: Unsupervised cross-lingual representation learning for speech recognition. arXiv preprint arXiv:2006.13979 (2020)","DOI":"10.21437\/Interspeech.2021-329"},{"key":"4_CR4","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: CVPR, pp. 10101\u201310111 (2019)","DOI":"10.1109\/CVPR.2019.01034"},{"issue":"4","key":"4_CR5","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897824.2925984","volume":"35","author":"P Edwards","year":"2016","unstructured":"Edwards, P., Landreth, C., Fiume, E., Singh, K.: Jali: an animator-centric viseme model for expressive lip synchronization. ACM Trans. Graph. 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. Graph."},{"key":"4_CR6","doi-asserted-by":"crossref","unstructured":"Egger, B., et al.: 3d morphable face models-past, present, and future. ACM Trans. Graph. 39(5), 1\u201338 (2020)","DOI":"10.1145\/3395208"},{"key":"4_CR7","doi-asserted-by":"crossref","unstructured":"Ekman, P., Friesen, W.V.: Facial action coding system. Environ. Psychol. Nonverb. Behav. (1978)","DOI":"10.1037\/t27734-000"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Ezzat, T., Poggio, T.: Miketalk: a talking facial display based on morphing visemes. In: Proceedings Computer Animation 1998, pp. 96\u2013102. IEEE (1998)","DOI":"10.1109\/CA.1998.681913"},{"key":"4_CR9","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lin, Z., Saito, J., Wang, W., Komura, T.: Faceformer: speech-driven 3d facial animation with transformers. In: CVPR, pp. 18770\u201318780 (2022)","DOI":"10.1109\/CVPR52688.2022.01821"},{"issue":"6","key":"4_CR10","doi-asserted-by":"publisher","first-page":"591","DOI":"10.1109\/TMM.2010.2052239","volume":"12","author":"G Fanelli","year":"2010","unstructured":"Fanelli, G., Gall, J., Romsdorfer, H., Weise, T., Van Gool, L.: A 3-d audio-visual corpus of affective communication. IEEE Trans. Multim. 12(6), 591\u2013598 (2010)","journal-title":"IEEE Trans. Multim."},{"issue":"4","key":"4_CR11","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. 36(4), 1\u201312 (2017)","journal-title":"ACM Trans. Graph."},{"key":"4_CR12","unstructured":"Kitaev, N., Kaiser, \u0141., Levskaya, A.: Reformer: the efficient transformer. arXiv preprint arXiv:2001.04451 (2020)"},{"key":"4_CR13","doi-asserted-by":"crossref","unstructured":"Lahiri, A., Kwatra, V., Frueh, C., Lewis, J., Bregler, C.: Lipsync3d: data-efficient learning of personalized 3d talking faces from video using pose and lighting normalization. In: CVPR, pp. 2755\u20132764 (2021)","DOI":"10.1109\/CVPR46437.2021.00278"},{"issue":"4","key":"4_CR14","doi-asserted-by":"publisher","first-page":"118","DOI":"10.1002\/vis.4340020404","volume":"2","author":"J Lewis","year":"1991","unstructured":"Lewis, J.: Automated lip-sync: background and techniques. J. Vis. Comput. Animat. 2(4), 118\u2013122 (1991)","journal-title":"J. Vis. Comput. Animat."},{"key":"4_CR15","doi-asserted-by":"crossref","unstructured":"Li, R., et al.: Learning formation of physically-based face attributes. In: CVPR, pp. 3410\u20133419 (2020)","DOI":"10.1109\/CVPR42600.2020.00347"},{"issue":"6","key":"4_CR16","doi-asserted-by":"publisher","first-page":"194","DOI":"10.1145\/3130800.3130813","volume":"36","author":"T Li","year":"2017","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\u20131 (2017)","journal-title":"ACM Trans. Graph."},{"key":"4_CR17","doi-asserted-by":"publisher","unstructured":"Liu, H., et al.: BEAT: a large-scale semantic and emotional multi-modal dataset for conversational gestures synthesis. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) ECCV 2022. LNCS, vol. 13667, pp. 612\u2013630. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-20071-7_36","DOI":"10.1007\/978-3-031-20071-7_36"},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: ICCV, pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"issue":"6","key":"4_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2816795.2818013","volume":"34","author":"M Loper","year":"2015","unstructured":"Loper, M., Mahmood, N., Romero, J., Pons-Moll, G., Black, M.J.: Smpl: a skinned multi-person linear model. ACM Trans. Graph. 34(6), 1\u201316 (2015)","journal-title":"ACM Trans. Graph."},{"key":"4_CR20","unstructured":"Loshchilov, I., Hutter, F.: SGDR: stochastic gradient descent with warm restarts. arXiv preprint arXiv:1608.03983 (2016)"},{"key":"4_CR21","unstructured":"Loshchilov, I., Hutter, F.: Decoupled weight decay regularization. arXiv preprint arXiv:1711.05101 (2017)"},{"key":"4_CR22","doi-asserted-by":"crossref","unstructured":"Prajwal, K., Mukhopadhyay, R., Namboodiri, V.P., Jawahar, C.: A lip sync expert is all you need for speech to lip generation in the wild. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 484\u2013492 (2020)","DOI":"10.1145\/3394171.3413532"},{"key":"4_CR23","doi-asserted-by":"crossref","unstructured":"Richard, A., Zollh\u00f6fer, M., Wen, Y., De la Torre, F., Sheikh, Y.: Meshtalk: 3d face animation from speech using cross-modality disentanglement. In: ICCV, pp. 1173\u20131182 (2021)","DOI":"10.1109\/ICCV48922.2021.00121"},{"issue":"4","key":"4_CR24","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. 36(4), 1\u201313 (2017)","journal-title":"ACM Trans. Graph."},{"key":"4_CR25","unstructured":"Taylor, S.L., Mahler, M., Theobald, B.J., Matthews, I.: Dynamic units of visual speech. In: Proceedings of the 11th ACM SIGGRAPH\/Eurographics Conference on Computer Animation, pp. 275\u2013284 (2012)"},{"key":"4_CR26","doi-asserted-by":"crossref","unstructured":"Thambiraja, B., Habibie, I., Aliakbarian, S., Cosker, D., Theobalt, C., Thies, J.: Imitator: personalized speech-driven 3d facial animation. arXiv preprint arXiv:2301.00023 (2022)","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"4_CR27","doi-asserted-by":"publisher","unstructured":"Thies, J., Elgharib, M., Tewari, A., Theobalt, C., Nie\u00dfner, M.: Neural voice puppetry: audio-driven facial reenactment. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12361, pp. 716\u2013731. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58517-4_42","DOI":"10.1007\/978-3-030-58517-4_42"},{"key":"4_CR28","doi-asserted-by":"crossref","unstructured":"Tian, G., Yuan, Y., Liu, Y.: Audio2face: generating speech\/face animation from single audio with attention-based bidirectional LSTM networks. In: ICME, pp. 366\u2013371. IEEE (2019)","DOI":"10.1109\/ICMEW.2019.00069"},{"key":"4_CR29","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"4_CR30","doi-asserted-by":"crossref","unstructured":"Wang, S., Li, L., Ding, Y., Fan, C., Yu, X.: Audio2head: audio-driven one-shot talking-head generation with natural head motion. arXiv preprint arXiv:2107.09293 (2021)","DOI":"10.24963\/ijcai.2021\/152"},{"key":"4_CR31","doi-asserted-by":"crossref","unstructured":"Xing, J., Xia, M., Zhang, Y., Cun, X., Wang, J., Wong, T.T.: Codetalker: speech-driven 3d facial animation with discrete motion prior. In: CVPR, pp. 12780\u201312790 (2023)","DOI":"10.1109\/CVPR52729.2023.01229"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8432-9_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T19:33:18Z","timestamp":1730921598000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8432-9_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984312","9789819984329"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8432-9_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","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":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","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":"532","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":"37% - 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":"3,78","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":"3,69","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)"}}]}}