{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T15:52:23Z","timestamp":1766159543115,"version":"3.41.0"},"publisher-location":"New York, NY, USA","reference-count":43,"publisher":"ACM","license":[{"start":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T00:00:00Z","timestamp":1730073600000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"National Nature Science Foundation of China","award":["62121002,U23B2028,62232006,62102127"],"award-info":[{"award-number":["62121002,U23B2028,62232006,62102127"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3681644","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:41Z","timestamp":1729925981000},"page":"3519-3527","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Control-Talker: A Rapid-Customization Talking Head Generation Method for Multi-Condition Control and High-Texture Enhancement"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0007-3230-4753","authenticated-orcid":false,"given":"Yiding","family":"Li","sequence":"first","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-6403-761X","authenticated-orcid":false,"given":"Lingyun","family":"Yu","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0009-0004-7234-9145","authenticated-orcid":false,"given":"Li","family":"Wang","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-6249-5315","authenticated-orcid":false,"given":"Hongtao","family":"Xie","sequence":"additional","affiliation":[{"name":"University of Science and Technology of China, Hefei, China"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems","author":"Baevski Alexei","year":"2020","unstructured":"Alexei Baevski, Yuhao Zhou, Abdelrahman Mohamed, and Michael Auli. 2020. wav2vec 2.0: A framework for self-supervised learning of speech representations. Advances in neural information processing systems, Vol. 33 (2020), 12449--12460."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00630"},{"volume-title":"Workshop on Multi-view Lip-reading, ACCV.","author":"Chung J. S.","key":"e_1_3_2_1_3_1","unstructured":"J. S. Chung and A. Zisserman. 2016. Out of time: automated lip sync in the wild. In Workshop on Multi-view Lip-reading, ACCV."},{"key":"e_1_3_2_1_4_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20311--20322","author":"Danvevcek Radek","year":"2022","unstructured":"Radek Danvevcek, Michael J Black, and Timo Bolkart. 2022. Emoca: Emotion driven monocular face capture and animation. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition. 20311--20322."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01225"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01413"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3547838"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1145\/3450626.3459936"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2024.3358415"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"e_1_3_2_1_12_1","volume-title":"A Generalist FaceX via Learning Unified Facial Representation. arXiv preprint arXiv:2401.00551","author":"Han Yue","year":"2023","unstructured":"Yue Han, Jiangning Zhang, Junwei Zhu, Xiangtai Li, Yanhao Ge, Wei Li, Chengjie Wang, Yong Liu, Xiaoming Liu, and Ying Tai. 2023. A Generalist FaceX via Learning Unified Facial Representation. arXiv preprint arXiv:2401.00551 (2023)."},{"key":"e_1_3_2_1_13_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_14_1","volume-title":"Denoising diffusion probabilistic models. Advances in neural information processing systems","author":"Ho Jonathan","year":"2020","unstructured":"Jonathan Ho, Ajay Jain, and Pieter Abbeel. 2020. Denoising diffusion probabilistic models. Advances in neural information processing systems, Vol. 33 (2020), 6840--6851."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00339"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.632"},{"key":"e_1_3_2_1_17_1","volume-title":"Alias-free generative adversarial networks. Advances in neural information processing systems","author":"Karras Tero","year":"2021","unstructured":"Tero Karras, Miika Aittala, Samuli Laine, Erik H\u00e4rk\u00f6nen, Janne Hellsten, Jaakko Lehtinen, and Timo Aila. 2021. Alias-free generative adversarial networks. Advances in neural information processing systems, Vol. 34 (2021), 852--863."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.00453"},{"key":"e_1_3_2_1_19_1","volume-title":"Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980","author":"Kingma Diederik P","year":"2014","unstructured":"Diederik P Kingma and Jimmy Ba. 2014. Adam: A method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.00338"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00612"},{"key":"e_1_3_2_1_23_1","volume-title":"DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior. arXiv preprint arXiv:2308.15070","author":"Lin Xinqi","year":"2023","unstructured":"Xinqi Lin, Jingwen He, Ziyan Chen, Zhaoyang Lyu, Ben Fei, Bo Dai, Wanli Ouyang, Yu Qiao, and Chao Dong. 2023. DiffBIR: Towards Blind Image Restoration with Generative Diffusion Prior. arXiv preprint arXiv:2308.15070 (2023)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1145\/3478513.3480484"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.02154"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/TIP.2011.2131660"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.01350"},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19775-8_39"},{"key":"e_1_3_2_1_30_1","volume-title":"First order motion model for image animation. Advances in neural information processing systems","author":"Siarohin Aliaksandr","year":"2019","unstructured":"Aliaksandr Siarohin, St\u00e9phane Lathuili\u00e8re, Sergey Tulyakov, Elisa Ricci, and Nicu Sebe. 2019. First order motion model for image animation. Advances in neural information processing systems, Vol. 32 (2019)."},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01330"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00991"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW56347.2022.00081"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00639"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-19790-1_6"},{"key":"e_1_3_2_1_37_1","volume-title":"Proceedings, Part XII 16","author":"Zakharov Egor","year":"2020","unstructured":"Egor Zakharov, Aleksei Ivakhnenko, Aliaksandra Shysheya, and Victor Lempitsky. 2020. Fast bi-layer neural synthesis of one-shot realistic head avatars. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XII 16. Springer, 524--540."},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00355"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00836"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.01235"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"e_1_3_2_1_43_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)"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Melbourne VIC Australia","acronym":"MM '24"},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681644","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3681644","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:49Z","timestamp":1750295869000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3681644"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":43,"alternative-id":["10.1145\/3664647.3681644","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3681644","relation":{},"subject":[],"published":{"date-parts":[[2024,10,28]]},"assertion":[{"value":"2024-10-28","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}