{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T06:15:18Z","timestamp":1742969718834,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984312"},{"type":"electronic","value":"9789819984329"}],"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_6","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"66-78","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sem-Avatar: Semantic Controlled Neural Field for\u00a0High-Fidelity Audio Driven Avatar"],"prefix":"10.1007","author":[{"given":"Xiang","family":"Zhou","sequence":"first","affiliation":[]},{"given":"Weichen","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yikang","family":"Ding","sequence":"additional","affiliation":[]},{"given":"Fan","family":"Zhou","sequence":"additional","affiliation":[]},{"given":"Kai","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"key":"6_CR1","unstructured":"Amodei, D., et al.: Deep speech 2: end-to-end speech recognition in English and mandarin. In: International Conference on Machine Learning (2015)"},{"key":"6_CR2","doi-asserted-by":"crossref","unstructured":"Blanz, V., Vetter, T.: A morphable model for the synthesis of 3d faces. In: Proceedings of the 26th Annual Conference on Computer Graphics and Interactive Techniques, pp. 187\u2013194 (1999)","DOI":"10.1145\/311535.311556"},{"issue":"4","key":"6_CR3","doi-asserted-by":"publisher","first-page":"1283","DOI":"10.1145\/1095878.1095881","volume":"24","author":"Y Cao","year":"2005","unstructured":"Cao, Y., Tien, W.C., Faloutsos, P., Pighin, F.: Expressive speech-driven facial animation. ACM Trans. Graph. (TOG) 24(4), 1283\u20131302 (2005)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"6_CR4","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Zisserman, A.: Out of time: automated lip sync in the wild. In: Asian Conference on Computer Vision (2016)","DOI":"10.1007\/978-3-319-54427-4_19"},{"issue":"4","key":"6_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. (TOG) 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"6_CR6","doi-asserted-by":"crossref","unstructured":"Gafni, G., Thies, J., Zollh\u00f6fer, M., Nie\u00dfner, M.: Dynamic neural radiance fields for monocular 4d facial avatar reconstruction. In: Computer Vision and Pattern Recognition (2021)","DOI":"10.1109\/CVPR46437.2021.00854"},{"key":"6_CR7","doi-asserted-by":"crossref","unstructured":"Grassal, P.W., Prinzler, M., Leistner, T., Rother, C., Nie\u00dfner, M., Thies, J.: Neural head avatars from monocular rgb videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18653\u201318664 (2022)","DOI":"10.1109\/CVPR52688.2022.01810"},{"key":"6_CR8","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)","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"6_CR9","doi-asserted-by":"crossref","unstructured":"Ji, X., et al.: Audio-driven emotional video portraits. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14080\u201314089 (2021)","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"6_CR10","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. (2017)","DOI":"10.1145\/3130800.3130813"},{"key":"6_CR11","doi-asserted-by":"publisher","unstructured":"Liu, X., Xu, Y., Wu, Q., Zhou, H., Wu, W., Zhou, B.: Semantic-aware implicit neural audio-driven video portrait generation. In: Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XXXVII, pp. 106\u2013125. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_7","DOI":"10.1007\/978-3-031-19836-6_7"},{"issue":"6","key":"6_CR12","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3478513.3480484","volume":"40","author":"Y Lu","year":"2021","unstructured":"Lu, Y., Chai, J., Cao, X.: Live speech portraits: real-time photorealistic talking-head animation. ACM Trans. Graph. (TOG) 40(6), 1\u201317 (2021)","journal-title":"ACM Trans. Graph. (TOG)"},{"key":"6_CR13","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"},{"key":"6_CR14","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Nerfies: deformable neural radiance fields. In: International Conference on Computer Vision (2020)","DOI":"10.1109\/ICCV48922.2021.00581"},{"key":"6_CR15","doi-asserted-by":"crossref","unstructured":"Park, K., et al.: Hypernerf: a higher-dimensional representation for topologically varying neural radiance fields. arXiv preprint arXiv:2106.13228 (2021)","DOI":"10.1145\/3478513.3480487"},{"key":"6_CR16","doi-asserted-by":"crossref","unstructured":"Prajwal, K.R., Mukhopadhyay, R., Namboodiri, V.P., Jawahar, C.V.: A lip sync expert is all you need for speech to lip generation in the wild. ACM Multimedia (2020)","DOI":"10.1145\/3394171.3413532"},{"key":"6_CR17","doi-asserted-by":"publisher","unstructured":"Shen, S., Li, W., Zhu, Z., Duan, Y., Zhou, J., Lu, J.: Learning dynamic facial radiance fields for few-shot talking head synthesis. In: Computer Vision-ECCV 2022: 17th European Conference, Tel Aviv, Israel, 23\u201327 October 2022, Proceedings, Part XII, pp. 666\u2013682. Springer (2022). https:\/\/doi.org\/10.1007\/978-3-031-19775-8_39","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"6_CR18","first-page":"7462","volume":"33","author":"V Sitzmann","year":"2020","unstructured":"Sitzmann, V., Martel, J., Bergman, A., Lindell, D., Wetzstein, G.: Implicit neural representations with periodic activation functions. Adv. Neural. Inf. Process. Syst. 33, 7462\u20137473 (2020)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"6_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"716","DOI":"10.1007\/978-3-030-58517-4_42","volume-title":"Computer Vision \u2013 ECCV 2020","author":"J Thies","year":"2020","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"},{"key":"6_CR20","doi-asserted-by":"crossref","unstructured":"Wen, X., Wang, M., Richardt, C., Chen, Z.Y., Hu, S.M.: Photorealistic audio-driven video portraits. In: International Symposium on Mixed and Augmented Reality (2020)","DOI":"10.1109\/TVCG.2020.3023573"},{"key":"6_CR21","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":"6_CR22","doi-asserted-by":"crossref","unstructured":"Zheng, Y., Abrevaya, V.F., B\u00fchler, M.C., Chen, X., Black, M.J., Hilliges, O.: Im avatar: implicit morphable head avatars from videos. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 13545\u201313555 (2022)","DOI":"10.1109\/CVPR52688.2022.01318"},{"issue":"6","key":"6_CR23","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","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8432-9_6","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T19:32:50Z","timestamp":1730921570000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8432-9_6"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984312","9789819984329"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8432-9_6","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"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)"}}]}}