{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,26]],"date-time":"2025-03-26T15:29:39Z","timestamp":1743002979508,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":19,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819611508"},{"type":"electronic","value":"9789819611515"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-96-1151-5_25","type":"book-chapter","created":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:00:59Z","timestamp":1738857659000},"page":"240-249","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Controllable Talking Head Synthesis by\u00a0Equivariant Data Augmentation for\u00a0Spatial Coordinates"],"prefix":"10.1007","author":[{"given":"Wan","family":"Ding","sequence":"first","affiliation":[]},{"given":"Dong-Yan","family":"Huang","sequence":"additional","affiliation":[]},{"given":"Zehong","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Tianyu","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Linhuang","family":"Yan","sequence":"additional","affiliation":[]},{"given":"Xianjie","family":"Yang","sequence":"additional","affiliation":[]},{"given":"Penghui","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,2,7]]},"reference":[{"key":"25_CR1","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 (CVPR 2019) (2019)","DOI":"10.1109\/CVPR.2019.00802"},{"key":"25_CR2","doi-asserted-by":"crossref","unstructured":"Lu, Y., Chai, J., Cao, X.: Live speech portraits: real-time photorealistic talking-head animation. ACM Trans. Graph. 40(6) (2021)","DOI":"10.1145\/3478513.3480484"},{"key":"25_CR3","doi-asserted-by":"crossref","unstructured":"Zhang, Z., Li, L., Ding, Y., Fan, C.: Flow-guided one-shot talking face generation with a high-resolution audio-visual dataset. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3661\u20133670 (2021)","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"25_CR4","doi-asserted-by":"crossref","unstructured":"Zhang, S., Yuan, J., Liao, M., Zhang, L.: Text2Video: text-driven talking-head video synthesis with personalized phoneme - pose dictionary. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 2659\u20132663 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747380"},{"key":"25_CR5","unstructured":"Wang, X., Xie, Q., Zhu, J., Xie, L., Scharenborg, O.: AnyoneNet: synchronized speech and talking head generation for arbitrary person (2021)"},{"key":"25_CR6","unstructured":"Yao, S., Zhong, R.Z., Yan, Y., Zhai, G., Yang, X.: DFA-NeRF: personalized talking head generation via disentangled face attributes neural rendering (2022)"},{"key":"25_CR7","doi-asserted-by":"crossref","unstructured":"Hong, F.-T., Zhang, L., Shen, L., Xu, D.: Depth-aware generative adversarial network for talking head video generation (2022)","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"25_CR8","doi-asserted-by":"crossref","unstructured":"Li, L., et al.: Write-a-speaker: text-based emotional and rhythmic talking-head generation. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, no. 3, pp. 1911\u20131920 (2021)","DOI":"10.1609\/aaai.v35i3.16286"},{"key":"25_CR9","doi-asserted-by":"crossref","unstructured":"Meshry, M., Suri, S., Davis, L.S., Shrivastava, A.: Learned spatial representations for few-shot talking-head synthesis. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision (ICCV), pp. 13809\u201313818 (2021)","DOI":"10.1109\/ICCV48922.2021.01357"},{"key":"25_CR10","doi-asserted-by":"crossref","unstructured":"Fried, O., Tewari, A., Zollhfer, M., Finkelstein, A., Agrawala, M.: Text-based editing of talking-head video. ACM Trans. Graph. (TOG) (2019)","DOI":"10.1145\/3306346.3323028"},{"key":"25_CR11","doi-asserted-by":"crossref","unstructured":"Burkov, E., Pasechnik, I., Grigorev, A., Lempitsky, V.: Neural head reenactment with latent pose descriptors. In: Proceedings of IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) (2020)","DOI":"10.1109\/CVPR42600.2020.01380"},{"key":"25_CR12","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 Conference on Computer Vision and Pattern Recognition (CVPR) (2021)","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"25_CR13","doi-asserted-by":"crossref","unstructured":"Liang, B., et al.: Expressive talking head generation with granular audio-visual control. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 3387\u20133396 (2022)","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"25_CR14","unstructured":"Tandon, P., et al.: Txt2Vid: ultra-low bitrate compression of talking-head videos via text (2021)"},{"key":"25_CR15","doi-asserted-by":"crossref","unstructured":"Wang, J., Zhao, Y., Liu, L., Xu, T., Li, Q., Li, S.: Emotional talking head generation based on memory-sharing and attention-augmented networks. In: Proceedings of INTERSPEECH, pp. 2\u20136 (2023)","DOI":"10.21437\/Interspeech.2023-749"},{"key":"25_CR16","doi-asserted-by":"crossref","unstructured":"Wang, J., et al.: Memory-augmented contrastive learning for talking head generation. In: Proceedings of the IEEE International Conference on Acoustics Speech and Signal Processing (ICASSP), pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096593"},{"key":"25_CR17","doi-asserted-by":"publisher","first-page":"2218","DOI":"10.1109\/TIFS.2021.3050065","volume":"16","author":"F Chaoyou","year":"2021","unstructured":"Chaoyou, F., Yibo, H., Xiang, W., Wang, G., Zhang, Q., He, R.: High-fidelity face manipulation with extreme poses and expressions. IEEE Trans. Inf. Forensics Secur. 16, 2218\u20132231 (2021)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"25_CR18","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_CR19","unstructured":"Wang, T.-C., et al.: Video-to-video synthesis. In: Conference on Neural Information Processing Systems (NeurIPS) (2018)"}],"container-title":["Lecture Notes in Computer Science","Social Robotics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-96-1151-5_25","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,2,6]],"date-time":"2025-02-06T16:01:12Z","timestamp":1738857672000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-96-1151-5_25"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819611508","9789819611515"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-981-96-1151-5_25","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"7 February 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICSR + InnoBiz","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Social Robotics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Shenzhen","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"26 September 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2024","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":"socrob2024b","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/www.asianlp.sg\/conferences\/icsr2024\/web\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}