{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,27]],"date-time":"2025-03-27T03:47:52Z","timestamp":1743047272501,"version":"3.40.3"},"publisher-location":"Cham","reference-count":17,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031202322"},{"type":"electronic","value":"9783031202339"}],"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\/978-3-031-20233-9_53","type":"book-chapter","created":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:02:48Z","timestamp":1667433768000},"page":"519-528","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Synthesizing Talking Face Videos with\u00a0a\u00a0Spatial Attention Mechanism"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-6201-4350","authenticated-orcid":false,"given":"Ting","family":"Wang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8531-0945","authenticated-orcid":false,"given":"Chaoyong","family":"Zhou","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5213-5877","authenticated-orcid":false,"given":"Shiqi","family":"Yu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,11,3]]},"reference":[{"doi-asserted-by":"crossref","unstructured":"Afouras, T., Chung, J.S., Senior, A., Vinyals, O., Zisserman, A.: Deep audio-visual speech recognition. IEEE Trans. Pattern Anal. Mach. Intell. (2018)","key":"53_CR1","DOI":"10.1109\/TPAMI.2018.2889052"},{"unstructured":"Afouras, T., Chung, J.S., Zisserman, A.: LRS3-TED: a large-scale dataset for visual speech recognition. arXiv preprint arXiv:1809.00496 (2018)","key":"53_CR2"},{"key":"53_CR3","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"},{"key":"53_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"},{"doi-asserted-by":"crossref","unstructured":"Guo, Y., Chen, K., Liang, S., Liu, Y.J., Bao, H., Zhang, J.: AD-NeRF: Audio driven neural radiance fields for talking head synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 5784\u20135794 (2021)","key":"53_CR5","DOI":"10.1109\/ICCV48922.2021.00573"},{"unstructured":"Heusel, M., Ramsauer, H., Unterthiner, T., Nessler, B., Hochreiter, S.: GANs trained by a two time-scale update rule converge to a local nash equilibrium. In: Advances in Neural Information Processing Systems 30 (2017)","key":"53_CR6"},{"issue":"11","key":"53_CR7","doi-asserted-by":"publisher","first-page":"1767","DOI":"10.1007\/s11263-019-01150-y","volume":"127","author":"A Jamaludin","year":"2019","unstructured":"Jamaludin, A., Chung, J.S., Zisserman, A.: You said that?: Synthesising talking faces from audio. Int. J. Comput. Vision 127(11), 1767\u20131779 (2019)","journal-title":"Int. J. Comput. Vision"},{"key":"53_CR8","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":"53_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"405","DOI":"10.1007\/978-3-030-58452-8_24","volume-title":"Computer Vision \u2013 ECCV 2020","author":"B Mildenhall","year":"2020","unstructured":"Mildenhall, B., Srinivasan, P.P., Tancik, M., Barron, J.T., Ramamoorthi, R., Ng, R.: NeRF: representing scenes as neural radiance fields for view synthesis. In: Vedaldi, A., Bischof, H., Brox, T., Frahm, J.-M. (eds.) ECCV 2020. LNCS, vol. 12346, pp. 405\u2013421. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-58452-8_24"},{"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)","key":"53_CR10","DOI":"10.1145\/3394171.3413532"},{"issue":"4","key":"53_CR11","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. (ToG) 36(4), 1\u201313 (2017)","journal-title":"ACM Trans. Graph. (ToG)"},{"key":"53_CR12","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1007\/978-3-030-01234-2_1","volume-title":"Computer Vision \u2013 ECCV 2018","author":"S Woo","year":"2018","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: CBAM: convolutional block attention module. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11211, pp. 3\u201319. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01234-2_1"},{"doi-asserted-by":"crossref","unstructured":"Yang, T., Ren, P., Xie, X., Zhang, L.: GAN prior embedded network for blind face restoration in the wild. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 672\u2013681 (2021)","key":"53_CR13","DOI":"10.1109\/CVPR46437.2021.00073"},{"unstructured":"Yao, S., Zhong, R., Yan, Y., Zhai, G., Yang, X.: DFA-NERF: personalized talking head generation via disentangled face attributes neural rendering. arXiv preprint arXiv:2201.00791 (2022)","key":"53_CR14"},{"doi-asserted-by":"crossref","unstructured":"Zhang, S., Zhu, X., Lei, Z., Shi, H., Wang, X., Li, S.Z.: S3FD: single shot scale-invariant face detector. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 192\u2013201 (2017)","key":"53_CR15","DOI":"10.1109\/ICCV.2017.30"},{"doi-asserted-by":"crossref","unstructured":"Zhou, H., Sun, Y., Wu, W., Loy, C.C., Wang, X., Liu, Z.: Pose-controllable talking face generation by implicitly modularized audio-visual representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4176\u20134186 (2021)","key":"53_CR16","DOI":"10.1109\/CVPR46437.2021.00416"},{"issue":"6","key":"53_CR17","first-page":"1","volume":"39","author":"Y Zhou","year":"2020","unstructured":"Zhou, Y., Han, X., Shechtman, E., Echevarria, J., Kalogerakis, E., Li, D.: MakeltTalk: speaker-aware talking-head animation. ACM Trans. Graph. (TOG) 39(6), 1\u201315 (2020)","journal-title":"ACM Trans. Graph. (TOG)"}],"container-title":["Lecture Notes in Computer Science","Biometric Recognition"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-20233-9_53","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,11,3]],"date-time":"2022-11-03T00:32:24Z","timestamp":1667435544000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-20233-9_53"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031202322","9783031202339"],"references-count":17,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-20233-9_53","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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":"CCBR","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Biometric Recognition","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Beijing","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"27 October 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28 October 2022","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":"ccbr2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/ccbr99.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"115","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":"70","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":"61% - 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":"3","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)"}}]}}