{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T18:04:19Z","timestamp":1779991459935,"version":"3.53.1"},"publisher-location":"New York, NY, USA","reference-count":68,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2026,6,29]]},"DOI":"10.1145\/3774905.3794684","type":"proceedings-article","created":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:14:56Z","timestamp":1779988496000},"page":"1316-1325","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":0,"title":["Talking-Head Generation in Practice"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-1791-0938","authenticated-orcid":false,"given":"Zhicheng","family":"Zhang","sequence":"first","affiliation":[{"name":"University of New South Wales, Canberra, Australian Capital Territory, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8600-7099","authenticated-orcid":false,"given":"Lei","family":"Wang","sequence":"additional","affiliation":[{"name":"Griffith University, Brisbane, Queensland, Australia and Data61\/CSIRO, Canberra, Australian Capital Territory, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-5382-5351","authenticated-orcid":false,"given":"Yongsheng","family":"Gao","sequence":"additional","affiliation":[{"name":"Griffith University, Brisbane, Queensland, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8747-2603","authenticated-orcid":false,"given":"Yu","family":"Zhang","sequence":"additional","affiliation":[{"name":"University of New South Wales, Canberra, Australian Capital Territory, Australia"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2026,5,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7099-7108","author":"Afouras Triantafyllos","year":"2018","unstructured":"Triantafyllos Afouras, Joon Son Chung, Andrew Senior, Oriol Vinyals, and Andrew Zisserman. 2018b. Deep audio-visual speech recognition. In IEEE Conference on Computer Vision and Pattern Recognition (CVPR). 7099-7108."},{"key":"e_1_3_2_1_2_1","volume-title":"Joon Son Chung, and Andrew Zisserman","author":"Afouras Triantafyllos","year":"2018","unstructured":"Triantafyllos Afouras, Joon Son Chung, and Andrew Zisserman. 2018a. LRS3-TED: a large-scale dataset for visual speech recognition. arXiv preprint arXiv:1809.00496 (2018)."},{"key":"e_1_3_2_1_3_1","volume-title":"Informatics","author":"Al-Kfairy Mousa","unstructured":"Mousa Al-Kfairy, Dheya Mustafa, Nir Kshetri, Mazen Insiew, and Omar Alfandi. 2024. Ethical challenges and solutions of generative AI: An interdisciplinary perspective. In Informatics, Vol. 11. Multidisciplinary Digital Publishing Institute, 58."},{"key":"e_1_3_2_1_4_1","volume-title":"Crema-d: Crowd-sourced emotional multimodal actors dataset","author":"Cao Houwei","year":"2014","unstructured":"Houwei Cao, David G Cooper, Michael K Keutmann, Ruben C Gur, Ani Nenkova, and Ragini Verma. 2014. Crema-d: Crowd-sourced emotional multimodal actors dataset. IEEE transactions on affective computing, Vol. 5, 4 (2014), 377-390."},{"key":"e_1_3_2_1_5_1","volume-title":"What comprises a good talking-head video generation?: A survey and benchmark. arXiv preprint arXiv:2005.03201","author":"Chen Lele","year":"2020","unstructured":"Lele Chen, Guofeng Cui, Ziyi Kou, Haitian Zheng, and Chenliang Xu. 2020. What comprises a good talking-head video generation?: A survey and benchmark. arXiv preprint arXiv:2005.03201 (2020)."},{"key":"e_1_3_2_1_6_1","volume-title":"You said that? arXiv preprint arXiv:1705.02966","author":"Chung Joon Son","year":"2017","unstructured":"Joon Son Chung, Amir Jamaludin, and Andrew Zisserman. 2017. You said that? arXiv preprint arXiv:1705.02966 (2017)."},{"key":"e_1_3_2_1_7_1","volume-title":"Voxceleb2: Deep speaker recognition. arXiv preprint arXiv:1806.05622","author":"Chung Joon Son","year":"2018","unstructured":"Joon Son Chung, Arsha Nagrani, and Andrew Zisserman. 2018. Voxceleb2: Deep speaker recognition. arXiv preprint arXiv:1806.05622 (2018)."},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1121\/1.2229005"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1049\/ipr2.70132"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3613753"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.02069"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"e_1_3_2_1_15_1","volume-title":"Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems","author":"Heusel Martin","year":"2017","unstructured":"Martin Heusel, Hubert Ramsauer, Thomas Unterthiner, Bernhard Nessler, and Sepp Hochreiter. 2017. Gans trained by a two time-scale update rule converge to a local nash equilibrium. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICPR.2010.579"},{"key":"e_1_3_2_1_17_1","volume-title":"Dual watermarking framework for privacy protection and content authentication of multimedia. Future generation computer Systems","author":"Hurrah Nasir N","year":"2019","unstructured":"Nasir N Hurrah, Shabir A Parah, Nazir A Loan, Javaid A Sheikh, Mohammad Elhoseny, and Khan Muhammad. 2019. Dual watermarking framework for privacy protection and content authentication of multimedia. Future generation computer Systems, Vol. 94 (2019), 654-673."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.3390\/info15110675"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.62762\/JIAP.2025.431672"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i4.32452"},{"key":"e_1_3_2_1_21_1","volume-title":"Alexandre De Brebisson, and Yoshua Bengio","author":"Kumar Rithesh","year":"2017","unstructured":"Rithesh Kumar, Jose Sotelo, Kundan Kumar, Alexandre De Brebisson, and Yoshua Bengio. 2017. Obamanet: Photo-realistic lip-sync from text. arXiv preprint arXiv:1801.01442 (2017)."},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1145\/3746027.3755075"},{"key":"e_1_3_2_1_23_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01723"},{"key":"e_1_3_2_1_24_1","volume-title":"A Metric for Evaluating Motion Consistency in Videos. arXiv preprint arXiv:2407.16124","author":"Liu Jiahe","year":"2024","unstructured":"Jiahe Liu, Youran Qu, Qi Yan, Xiaohui Zeng, Lele Wang, and Renjie Liao. 2024. Fr$backslash$'echet Video Motion Distance: A Metric for Evaluating Motion Consistency in Videos. arXiv preprint arXiv:2407.16124 (2024)."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1371\/journal.pone.0196391"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.ssaho.2025.101882"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1093\/jiplp\/jpz167"},{"key":"e_1_3_2_1_28_1","volume-title":"International Conference on Pattern Recognition. Springer, 320-337","author":"Nadimpalli Aakash Varma","year":"2022","unstructured":"Aakash Varma Nadimpalli and Ajita Rattani. 2022. GBDF: gender balanced deepfake dataset towards fair deepfake detection. In International Conference on Pattern Recognition. Springer, 320-337."},{"key":"e_1_3_2_1_29_1","volume-title":"International conference on machine learning. PMLR, 7176-7185","author":"Naeem Muhammad Ferjad","year":"2020","unstructured":"Muhammad Ferjad Naeem, Seong Joon Oh, Youngjung Uh, Yunjey Choi, and Jaejun Yoo. 2020. Reliable fidelity and diversity metrics for generative models. In International conference on machine learning. PMLR, 7176-7185."},{"key":"e_1_3_2_1_30_1","volume-title":"Joon Son Chung, and Andrew Zisserman","author":"Nagrani Arsha","year":"2017","unstructured":"Arsha Nagrani, Joon Son Chung, and Andrew Zisserman. 2017. Voxceleb: a large-scale speaker identification dataset. arXiv preprint arXiv:1706.08612 (2017)."},{"key":"e_1_3_2_1_31_1","volume-title":"MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control. arXiv preprint arXiv:2510.22810","author":"Nazarieh Fatemeh","year":"2025","unstructured":"Fatemeh Nazarieh, Zhenhua Feng, Diptesh Kanojia, Muhammad Awais, and Josef Kittler. 2025. MAGIC-Talk: Motion-aware Audio-Driven Talking Face Generation with Customizable Identity Control. arXiv preprint arXiv:2510.22810 (2025)."},{"key":"e_1_3_2_1_32_1","volume-title":"Deepfake generation and detection: A benchmark and survey. arXiv","author":"Pei G","year":"2024","unstructured":"G Pei, J Zhang, M Hu, G Zhai, C Wang, Z Zhang, J Yang, C Shen, and D Tao. [n.d.]. Deepfake generation and detection: A benchmark and survey. arXiv 2024. arXiv preprint arXiv:2403.17881 ([n.d.])."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.3390\/computers14010007"},{"key":"e_1_3_2_1_35_1","volume-title":"Sarbajit Pal, Amitabha Das, and Tapas Samanta.","author":"Rakesh Vineet Kumar","year":"2025","unstructured":"Vineet Kumar Rakesh, Soumya Mazumdar, Research Pratim Maity, Sarbajit Pal, Amitabha Das, and Tapas Samanta. 2025. Advancing Talking Head Generation: A Comprehensive Survey of Multi-Modal Methodologies, Datasets, Evaluation Metrics, and Loss Functions. arXiv preprint arXiv:2507.02900 (2025)."},{"key":"e_1_3_2_1_36_1","unstructured":"NUR AINI RAKHMAWATI. [n.d.]. ANALYZING ETHICAL CHALLENGES OF DEEPFAKE TECHNOLOGY IN MEDIA AND COMMUNICATION USING BIBLIOMETRIC RESEARCH AND VOSVIEWER VISUALIZATION. ([n.d.])."},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.clsr.2025.106162"},{"key":"e_1_3_2_1_38_1","volume-title":"Multimodal emotion recognition based on a fusion of audiovisual information with temporal dynamics. Multimedia tools and applications","author":"Salas-C\u00e1ceres Jos\u00e9","year":"2025","unstructured":"Jos\u00e9 Salas-C\u00e1ceres, Javier Lorenzo-Navarro, David Freire-Obreg\u00f3n, and Modesto Castrill\u00f3n-Santana. 2025. Multimodal emotion recognition based on a fusion of audiovisual information with temporal dynamics. Multimedia tools and applications, Vol. 84, 23 (2025), 27327-27343."},{"key":"e_1_3_2_1_39_1","volume-title":"Term-weighting approaches in automatic text retrieval. Information processing & management","author":"Salton Gerard","year":"1988","unstructured":"Gerard Salton and Christopher Buckley. 1988. Term-weighting approaches in automatic text retrieval. Information processing & management, Vol. 24, 5 (1988), 513-523."},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"e_1_3_2_1_41_1","volume-title":"A survey on audio synthesis and audio-visual multimodal processing. arXiv preprint arXiv:2108.00443","author":"Shi Zhaofeng","year":"2021","unstructured":"Zhaofeng Shi. 2021. A survey on audio synthesis and audio-visual multimodal processing. arXiv preprint arXiv:2108.00443 (2021)."},{"key":"e_1_3_2_1_42_1","volume-title":"Emotion-controllable generalized talking face generation. arXiv preprint arXiv:2205.01155","author":"Sinha Sanjana","year":"2022","unstructured":"Sanjana Sinha, Sandika Biswas, Ravindra Yadav, and Brojeshwar Bhowmick. 2022. Emotion-controllable generalized talking face generation. arXiv preprint arXiv:2205.01155 (2022)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICIP.2017.8297089"},{"key":"e_1_3_2_1_44_1","volume-title":"Ethical Challenges in Computer Vision: Ensuring Privacy and Mitigating Bias in Publicly Available Datasets. arXiv preprint arXiv:2409.10533","author":"Tahir Ghalib Ahmed","year":"2024","unstructured":"Ghalib Ahmed Tahir. 2024. Ethical Challenges in Computer Vision: Ensuring Privacy and Mitigating Bias in Publicly Available Datasets. arXiv preprint arXiv:2409.10533 (2024)."},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1145\/2929464.2929475"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2020.06.014"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.119678"},{"key":"e_1_3_2_1_48_1","volume-title":"An examination of fairness of ai models for deepfake detection. arXiv preprint arXiv:2105.00558","author":"Trinh Loc","year":"2021","unstructured":"Loc Trinh and Yan Liu. 2021. An examination of fairness of ai models for deepfake detection. arXiv preprint arXiv:2105.00558 (2021)."},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.61838\/kman.isslp.2.2.2"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"e_1_3_2_1_51_1","volume-title":"Image quality assessment: from error visibility to structural similarity","author":"Wang Zhou","year":"2004","unstructured":"Zhou Wang, Alan C Bovik, Hamid R Sheikh, and Eero P Simoncelli. 2004. Image quality assessment: from error visibility to structural similarity. IEEE transactions on image processing, Vol. 13, 4 (2004), 600-612."},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1145\/3531146.3533779"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"e_1_3_2_1_54_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00129"},{"key":"e_1_3_2_1_55_1","doi-asserted-by":"publisher","DOI":"10.1109\/TTS.2024.3365421"},{"key":"e_1_3_2_1_56_1","volume-title":"European Conference on Computer Vision. Springer, 236-253","author":"Xu Zhihao","year":"2024","unstructured":"Zhihao Xu, Shengjie Gong, Jiapeng Tang, Lingyu Liang, Yining Huang, Haojie Li, and Shuangping Huang. 2024a. Kmtalk: Speech-driven 3d facial animation with key motion embedding. In European Conference on Computer Vision. Springer, 236-253."},{"key":"e_1_3_2_1_57_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW63382.2024.00607"},{"key":"e_1_3_2_1_58_1","volume-title":"Leonard B\u00e4rmann, Hazim Kemal Ekenel, and Alexander Waibel.","author":"Yaman Dogucan","year":"2025","unstructured":"Dogucan Yaman, Fevziye Irem Eyiokur, Leonard B\u00e4rmann, Hazim Kemal Ekenel, and Alexander Waibel. 2025. Mask-Free Audio-driven Talking Face Generation for Enhanced Visual Quality and Identity Preservation. arXiv preprint arXiv:2507.20953 (2025)."},{"key":"e_1_3_2_1_59_1","volume-title":"Geneface: Generalized and high-fidelity audio-driven 3d talking face synthesis. arXiv preprint arXiv:2301.13430","author":"Ye Zhenhui","year":"2023","unstructured":"Zhenhui Ye, Ziyue Jiang, Yi Ren, Jinglin Liu, Jinzheng He, and Zhou Zhao. 2023. Geneface: Generalized and high-fidelity audio-driven 3d talking face synthesis. arXiv preprint arXiv:2301.13430 (2023)."},{"key":"e_1_3_2_1_60_1","volume-title":"Audio-driven talking face video generation with learning-based personalized head pose. arXiv preprint arXiv:2002.10137","author":"Yi Ran","year":"2020","unstructured":"Ran Yi, Zipeng Ye, Juyong Zhang, Hujun Bao, and Yong-Jin Liu. 2020. Audio-driven talking face video generation with learning-based personalized head pose. arXiv preprint arXiv:2002.10137 (2020)."},{"key":"e_1_3_2_1_61_1","doi-asserted-by":"publisher","DOI":"10.5555\/1126250.1126340"},{"key":"e_1_3_2_1_62_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.02116"},{"key":"e_1_3_2_1_63_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"e_1_3_2_1_64_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"e_1_3_2_1_65_1","doi-asserted-by":"publisher","DOI":"10.7544\/issn1000-1239.202440207"},{"key":"e_1_3_2_1_66_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3414685.3417774","article-title":"Makelttalk: speaker-aware talking-head animation","volume":"39","author":"Zhou Yang","year":"2020","unstructured":"Yang Zhou, Xintong Han, Eli Shechtman, Jose Echevarria, Evangelos Kalogerakis, and Dingzeyu Li. 2020. Makelttalk: speaker-aware talking-head animation. ACM Transactions On Graphics (TOG), Vol. 39, 6 (2020), 1-15.","journal-title":"ACM Transactions On Graphics (TOG)"},{"key":"e_1_3_2_1_67_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-20071-7_38"},{"key":"e_1_3_2_1_68_1","volume-title":"Big data ethics. Big data & society","author":"Zwitter Andrej","year":"2014","unstructured":"Andrej Zwitter. 2014. Big data ethics. Big data & society, Vol. 1, 2 (2014), 2053951714559253."}],"event":{"name":"WWW '26: The ACM Web Conference 2026","location":"Dubai United Arab Emirates","sponsor":["SIGWEB ACM Special Interest Group on Hypertext, Hypermedia, and Web"]},"container-title":["Companion Proceedings of the ACM Web Conference 2026"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3774905.3794684","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,28]],"date-time":"2026-05-28T17:22:55Z","timestamp":1779988975000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3774905.3794684"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,5,28]]},"references-count":68,"alternative-id":["10.1145\/3774905.3794684","10.1145\/3774905"],"URL":"https:\/\/doi.org\/10.1145\/3774905.3794684","relation":{},"subject":[],"published":{"date-parts":[[2026,5,28]]},"assertion":[{"value":"2026-05-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}