{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:06:04Z","timestamp":1757624764156,"version":"3.44.0"},"publisher-location":"Singapore","reference-count":40,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819500994"},{"type":"electronic","value":"9789819501007"}],"license":[{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,19]],"date-time":"2025-08-19T00:00:00Z","timestamp":1755561600000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-0100-7_1","type":"book-chapter","created":{"date-parts":[[2025,8,18]],"date-time":"2025-08-18T04:37:26Z","timestamp":1755491846000},"page":"3-20","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Speech-Driven 3D Facial Animation with\u00a0Regional Attention for\u00a0Style Capture"],"prefix":"10.1007","author":[{"given":"Bailin","family":"Yang","sequence":"first","affiliation":[]},{"given":"Jiahao","family":"Pan","sequence":"additional","affiliation":[]},{"given":"Fangzhe","family":"Nan","sequence":"additional","affiliation":[]},{"given":"Jiajie","family":"Wu","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,19]]},"reference":[{"key":"1_CR1","doi-asserted-by":"crossref","unstructured":"Aneja, S., Thies, J., Dai, A., Nie\u00dfner, M.: Facetalk: audio-driven motion diffusion for neural parametric head models. arXiv preprint arXiv:2312.08459 (2023)","DOI":"10.1109\/CVPR52733.2024.02009"},{"key":"1_CR2","unstructured":"Baevski, A., Zhou, Y., Mohamed, A., Auli, M.: wav2vec 2.0: A framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems 33: Annual Conference on Neural Information Processing Systems 2020, NeurIPS 2020, December 6-12, 2020, virtual (2020)"},{"key":"1_CR3","doi-asserted-by":"crossref","unstructured":"Cao, C., Wu, H., Weng, Y., Shao, T., Zhou, K.: Real-time facial animation with image-based dynamic avatars. ACM Trans. Graphics 35(4) (2016)","DOI":"10.1145\/2897824.2925873"},{"key":"1_CR4","doi-asserted-by":"crossref","unstructured":"Carion, N., Massa, F., Synnaeve, G., Usunier, N., Kirillov, A., Zagoruyko, S.: End-to-end object detection with transformers. In: European Conference on Computer Vision. pp. 213\u2013229. Springer (2020)","DOI":"10.1007\/978-3-030-58452-8_13"},{"key":"1_CR5","unstructured":"Chai, Y., Shao, T., Weng, Y., Zhou, K.: Personalized audio-driven 3d facial animation via style-content disentanglement. IEEE Trans. Visual. Comput. Graphics (2022)"},{"key":"1_CR6","doi-asserted-by":"crossref","unstructured":"Chen, L., et al.: Adamesh: personalized facial expressions and head poses for adaptive speech-driven 3d facial animation. IEEE Trans. Multimedia (2025)","DOI":"10.1109\/TMM.2025.3535287"},{"key":"1_CR7","doi-asserted-by":"crossref","unstructured":"Chu, X., Yang, W., Ouyang, W., Ma, C., Yuille, A.L., Wang, X.: Multi-context attention for human pose estimation. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 1831\u20131840 (2017)","DOI":"10.1109\/CVPR.2017.601"},{"key":"1_CR8","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\/CVF Conference on Computer Vision and Pattern Recognition. pp. 10101\u201310111 (2019)","DOI":"10.1109\/CVPR.2019.01034"},{"key":"1_CR9","doi-asserted-by":"crossref","unstructured":"Dai, T., Cai, J., Zhang, Y., Xia, S.T., Zhang, L.: Second-order attention network for single image super-resolution. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 11065\u201311074 (2019)","DOI":"10.1109\/CVPR.2019.01132"},{"key":"1_CR10","doi-asserted-by":"crossref","unstructured":"Dan\u011b\u010dek, R., Chhatre, K., Tripathi, S., Wen, Y., Black, M., Bolkart, T.: Emotional speech-driven animation with content-emotion disentanglement. In: SIGGRAPH Asia 2023 Conference Papers. pp. 1\u201313 (2023)","DOI":"10.1145\/3610548.3618183"},{"key":"1_CR11","unstructured":"Dosovitskiy, A., et\u00a0al.: An image is worth 16x16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"issue":"4","key":"1_CR12","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. graphics (TOG) 35(4), 1\u201311 (2016)","journal-title":"ACM Trans. graphics (TOG)"},{"key":"1_CR13","doi-asserted-by":"crossref","unstructured":"Fan, Y., Lin, Z., Saito, J., Wang, W., Komura, T.: Faceformer: speech-driven 3d facial animation with transformers. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2022, New Orleans, LA, USA, June 18-24, 2022. pp. 18749\u201318758 (2022)","DOI":"10.1109\/CVPR52688.2022.01821"},{"issue":"6","key":"1_CR14","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. Multimedia 12(6), 591\u2013598 (2010)","journal-title":"IEEE Trans. Multimedia"},{"issue":"4","key":"1_CR15","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3306346.3323028","volume":"38","author":"O Fried","year":"2019","unstructured":"Fried, O., et al.: Text-based editing of talking-head video. ACM Trans. Graphics (TOG) 38(4), 1\u201314 (2019)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"1_CR16","doi-asserted-by":"publisher","unstructured":"Guo, M.-H., et al.: Attention mechanisms in computer vision: a survey. Comput. Visual Media , 1\u201338 (2022). https:\/\/doi.org\/10.1007\/s41095-022-0271-y","DOI":"10.1007\/s41095-022-0271-y"},{"key":"1_CR17","doi-asserted-by":"crossref","unstructured":"Hu, J., Shen, L., Sun, G.: Squeeze-and-excitation networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7132\u20137141 (2018)","DOI":"10.1109\/CVPR.2018.00745"},{"key":"1_CR18","unstructured":"Jaderberg, M., Simonyan, K., Zisserman, A., et\u00a0al.: Spatial transformer networks. Adv. Neural Inf. Process. Syst. 28 (2015)"},{"issue":"1","key":"1_CR19","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3691341","volume":"44","author":"S Jung","year":"2024","unstructured":"Jung, S., et al.: Speed-aware audio-driven speech animation using adaptive windows. ACM Trans. Graphics 44(1), 1\u201314 (2024)","journal-title":"ACM Trans. Graphics"},{"issue":"4","key":"1_CR20","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. Graphics (TOG) 36(4), 1\u201312 (2017)","journal-title":"ACM Trans. Graphics (TOG)"},{"issue":"4","key":"1_CR21","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3197517.3201283","volume":"37","author":"H Kim","year":"2018","unstructured":"Kim, H., et al.: Deep video portraits. ACM Trans. Graphics (TOG) 37(4), 1\u201314 (2018)","journal-title":"ACM Trans. Graphics (TOG)"},{"key":"1_CR22","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: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 2755\u20132764 (2021)","DOI":"10.1109\/CVPR46437.2021.00278"},{"issue":"4","key":"1_CR23","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1145\/2461912.2462019","volume":"32","author":"H Li","year":"2013","unstructured":"Li, H., Yu, J., Ye, Y., Bregler, C.: Realtime facial animation with on-the-fly correctives. ACM Trans. Graph. 32(4), 42\u20131 (2013)","journal-title":"ACM Trans. Graph."},{"issue":"6","key":"1_CR24","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":"1_CR25","doi-asserted-by":"crossref","unstructured":"Liu, Z., et al.: Swin transformer: hierarchical vision transformer using shifted windows. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 10012\u201310022 (2021)","DOI":"10.1109\/ICCV48922.2021.00986"},{"key":"1_CR26","unstructured":"Mnih, V., Heess, N., Graves, A., et\u00a0al.: Recurrent models of visual attention. Adv. Neural Inf. Process. Syst. 27 (2014)"},{"key":"1_CR27","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: Selftalk: a self-supervised commutative training diagram to comprehend 3d talking faces. In: Proceedings of the 31st ACM International Conference on Multimedia, MM 2023, Ottawa, ON, Canada, 29 October 2023- 3 November 2023. pp. 5292\u20135301 (2023)","DOI":"10.1145\/3581783.3611734"},{"key":"1_CR28","doi-asserted-by":"crossref","unstructured":"Peng, Z., et al.: Emotalk: speech-driven emotional disentanglement for 3d face animation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 20687\u201320697 (2023)","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"1_CR29","doi-asserted-by":"crossref","unstructured":"Richard, A., Zollh\u00f6fer, M., Wen, Y., De\u00a0la Torre, F., Sheikh, Y.: Meshtalk: 3d face animation from speech using cross-modality disentanglement. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 1173\u20131182 (2021)","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"1_CR30","doi-asserted-by":"crossref","unstructured":"Song, W., et al.: Expressive 3d facial animation generation based on local-to-global latent diffusion. IEEE Trans. Visual. Comput. Graph. (2024)","DOI":"10.1109\/TVCG.2024.3456213"},{"key":"1_CR31","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":"1_CR32","doi-asserted-by":"crossref","unstructured":"Thambiraja, B., Habibie, I., Aliakbarian, S., Cosker, D., Theobalt, C., Thies, J.: Imitator: personalized speech-driven 3d facial animation. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision. pp. 20621\u201320631 (2023)","DOI":"10.1109\/ICCV51070.2023.01885"},{"key":"1_CR33","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":"1_CR34","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., Uszkoreit, J., Jones, L., Gomez, A.N., Kaiser, \u0141., Polosukhin, I.: Attention is all you need. Advances in neural information processing systems 30 (2017)"},{"key":"1_CR35","doi-asserted-by":"crossref","unstructured":"Wang, Q., Wu, T., Zheng, H., Guo, G.: Hierarchical pyramid diverse attention networks for face recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp. 8326\u20138335 (2020)","DOI":"10.1109\/CVPR42600.2020.00835"},{"key":"1_CR36","doi-asserted-by":"crossref","unstructured":"Wang, X., Girshick, R., Gupta, A., He, K.: Non-local neural networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition. pp. 7794\u20137803 (2018)","DOI":"10.1109\/CVPR.2018.00813"},{"key":"1_CR37","doi-asserted-by":"crossref","unstructured":"Wu, H., Zhou, S., Jia, J., Xing, J., Wen, Q., Wen, X.: Speech-driven 3d face animation with composite and regional facial movements. In: Proceedings of the 31st ACM International Conference on Multimedia. pp. 6822\u20136830 (2023)","DOI":"10.1145\/3581783.3611775"},{"key":"1_CR38","doi-asserted-by":"crossref","unstructured":"Xing, J., Xia, M., Zhang, Y., Cun, X., Wang, J., Wong, T.: Codetalker: speech-driven 3d facial animation with discrete motion prior. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, CVPR 2023, Vancouver, BC, Canada, June 17-24, 2023. pp. 12780\u201312790 (2023)","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"1_CR39","doi-asserted-by":"crossref","unstructured":"Xu, Y., Feng, A.W., Marsella, S., Shapiro, A.: A practical and configurable lip sync method for games. In: Proceedings of Motion on Games, pp. 131\u2013140 (2013)","DOI":"10.1145\/2522628.2522904"},{"key":"1_CR40","doi-asserted-by":"crossref","unstructured":"Yang, K.D., Ranjan, A., Chang, J.H.R., Vemulapalli, R., Tuzel, O.: Probabilistic speech-driven 3d facial motion synthesis: new benchmarks, methods, and applications. arXiv preprint arXiv:2311.18168 (2023)","DOI":"10.1109\/CVPR52733.2024.02577"}],"container-title":["Lecture Notes in Computer Science","Computer Animation and Social Agents"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0100-7_1","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T15:16:35Z","timestamp":1757430995000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0100-7_1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,19]]},"ISBN":["9789819500994","9789819501007"],"references-count":40,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0100-7_1","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025,8,19]]},"assertion":[{"value":"19 August 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CASA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Computer Animation and Social Agents","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Strasbourg","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"France","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 June 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"5 June 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"38","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"casa2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/casa2025.sciencesconf.org\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}