{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:03:31Z","timestamp":1776888211071,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":50,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733279","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:04Z","timestamp":1750876264000},"page":"1588-1597","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Audio-Driven Talking Face Video Generation with Joint Uncertainty Learning"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0002-3225-9220","authenticated-orcid":false,"given":"Yifan","family":"Xie","sequence":"first","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-5388-9125","authenticated-orcid":false,"given":"Fei","family":"Ma","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9714-8738","authenticated-orcid":false,"given":"Yi","family":"Bin","sequence":"additional","affiliation":[{"name":"Tongji University, Shanghai, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1733-9791","authenticated-orcid":false,"given":"Ying","family":"He","sequence":"additional","affiliation":[{"name":"Shenzhen University, Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1006-7594","authenticated-orcid":false,"given":"Fei","family":"Yu","sequence":"additional","affiliation":[{"name":"Guangdong Laboratory of Artificial Intelligence and Digital Economy (SZ), Shenzhen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"International Conference on Machine Learning. PMLR, 173--182","author":"Amodei Dario","year":"2016","unstructured":"Dario Amodei, Sundaram Ananthanarayanan, Rishita Anubhai, Jingliang Bai, Eric Battenberg, Carl Case, Jared Casper, Bryan Catanzaro, Qiang Cheng, Guoliang Chen, et al. 2016. Deep speech 2: End-to-end speech recognition in english and mandarin. In International Conference on Machine Learning. PMLR, 173--182."},{"key":"e_1_3_2_1_2_1","volume-title":"Openface: an open source facial behavior analysis toolkit. In 2016 IEEE winter conference on applications of computer vision (WACV)","author":"Baltru\u0161aitis Tadas","unstructured":"Tadas Baltru\u0161aitis, Peter Robinson, and Louis-Philippe Morency. 2016. Openface: an open source facial behavior analysis toolkit. In 2016 IEEE winter conference on applications of computer vision (WACV). IEEE, 1--10."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3596711.3596730"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.01379"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01653"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1145\/3550469.3555399"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"crossref","unstructured":"Antonin Cheymol Anatole L\u00e9cuyer Jean-Marie Normand Ferran Argelaguet et al. 2023. Beyond my real body: Characterization impacts applications and perspectives of ''dissimilar'' avatars in virtual reality. IEEE Transactions on Visualization and Computer Graphics (2023).","DOI":"10.1109\/TVCG.2023.3320209"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-54427-4_19"},{"key":"e_1_3_2_1_10_1","volume-title":"International conference on machine learning. PMLR, 2782--2792","author":"Dusenberry Michael","year":"2020","unstructured":"Michael Dusenberry, Ghassen Jerfel, Yeming Wen, Yian Ma, Jasper Snoek, Katherine Heller, Balaji Lakshminarayanan, and Dustin Tran. 2020. Efficient and scalable bayesian neural nets with rank-1 factors. In International conference on machine learning. PMLR, 2782--2792."},{"key":"e_1_3_2_1_11_1","volume-title":"2025 a. UniSync: A Unified Framework for Audio-Visual Synchronization. arXiv preprint arXiv:2503.16357","author":"Feng Tao","year":"2025","unstructured":"Tao Feng, Yifan Xie, Xun Guan, Jiyuan Song, Zhou Liu, Fei Ma, and Fei Yu. 2025 a. UniSync: A Unified Framework for Audio-Visual Synchronization. arXiv preprint arXiv:2503.16357 (2025)."},{"key":"e_1_3_2_1_12_1","volume-title":"2025 b. STFTCodec: High-Fidelity Audio Compression through Time-Frequency Domain Representation. arXiv preprint arXiv:2503.16989","author":"Feng Tao","year":"2025","unstructured":"Tao Feng, Zhiyuan Zhao, Yifan Xie, Yuqi Ye, Xiangyang Luo, Xun Guan, and Yu Li. 2025 b. STFTCodec: High-Fidelity Audio Compression through Time-Frequency Domain Representation. arXiv preprint arXiv:2503.16989 (2025)."},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00573"},{"key":"e_1_3_2_1_14_1","unstructured":"Awni Hannun Carl Case Jared Casper Bryan Catanzaro Greg Diamos Erich Elsen Ryan Prenger Sanjeev Satheesh Shubho Sengupta Adam Coates et al. 2014. Deep speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)."},{"key":"e_1_3_2_1_15_1","volume-title":"Jasper Snoek, Balaji Lakshminarayanan, Andrew M Dai, and Dustin Tran.","author":"Havasi Marton","year":"2020","unstructured":"Marton Havasi, Rodolphe Jenatton, Stanislav Fort, Jeremiah Zhe Liu, Jasper Snoek, Balaji Lakshminarayanan, Andrew M Dai, and Dustin Tran. 2020. Training independent subnetworks for robust prediction. arXiv preprint arXiv:2010.06610 (2020)."},{"key":"e_1_3_2_1_16_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","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_17_1","first-page":"6840","article-title":"Denoising diffusion probabilistic models","volume":"33","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.","journal-title":"Advances in Neural Information Processing Systems"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01234-2_40"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/3528233.3530745"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/TCSS.2022.3231987"},{"key":"e_1_3_2_1_22_1","volume-title":"Advances in Neural Information Processing Systems","volume":"30","author":"Kendall Alex","year":"2017","unstructured":"Alex Kendall and Yarin Gal. 2017. What uncertainties do we need in bayesian deep learning for computer vision? Advances in Neural Information Processing Systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_23_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_24_1","volume-title":"Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems","author":"Lakshminarayanan Balaji","year":"2017","unstructured":"Balaji Lakshminarayanan, Alexander Pritzel, and Charles Blundell. 2017. Simple and scalable predictive uncertainty estimation using deep ensembles. Advances in neural information processing systems, Vol. 30 (2017)."},{"key":"e_1_3_2_1_25_1","volume-title":"Packed-ensembles for efficient uncertainty estimation. arXiv preprint arXiv:2210.09184","author":"Laurent Olivier","year":"2022","unstructured":"Olivier Laurent, Adrien Lafage, Enzo Tartaglione, Geoffrey Daniel, Jean-Marc Martinez, Andrei Bursuc, and Gianni Franchi. 2022. Packed-ensembles for efficient uncertainty estimation. arXiv preprint arXiv:2210.09184 (2022)."},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.00696"},{"key":"e_1_3_2_1_27_1","volume-title":"Deep ensembling with no overhead for either training or testing: The all-round blessings of dynamic sparsity. arXiv preprint arXiv:2106.14568","author":"Liu Shiwei","year":"2021","unstructured":"Shiwei Liu, Tianlong Chen, Zahra Atashgahi, Xiaohan Chen, Ghada Sokar, Elena Mocanu, Mykola Pechenizkiy, Zhangyang Wang, and Decebal Constantin Mocanu. 2021. Deep ensembling with no overhead for either training or testing: The all-round blessings of dynamic sparsity. arXiv preprint arXiv:2106.14568 (2021)."},{"key":"e_1_3_2_1_28_1","doi-asserted-by":"publisher","DOI":"10.1145\/3664647.3681120"},{"key":"e_1_3_2_1_29_1","volume-title":"Fei Richard Yu, et al","author":"Ma Fei","year":"2024","unstructured":"Fei Ma, Yukan Li, Yifan Xie, Ying He, Yi Zhang, Hongwei Ren, Zhou Liu, Wei Yao, Fuji Ren, Fei Richard Yu, et al. 2024a. A Review of Human Emotion Synthesis Based on Generative Technology. arXiv preprint arXiv:2412.07116 (2024)."},{"key":"e_1_3_2_1_30_1","volume-title":"Fei Richard Yu, and Shiguang Ni","author":"Ma Fei","year":"2024","unstructured":"Fei Ma, Yucheng Yuan, Yifan Xie, Hongwei Ren, Ivan Liu, Ying He, Fuji Ren, Fei Richard Yu, and Shiguang Ni. 2024b. Generative technology for human emotion recognition: A scoping review. Information Fusion (2024), 102753."},{"key":"e_1_3_2_1_31_1","volume-title":"Dreamtalk: When expressive talking head generation meets diffusion probabilistic models. arXiv preprint arXiv:2312.09767","author":"Ma Yifeng","year":"2023","unstructured":"Yifeng Ma, Shiwei Zhang, Jiayu Wang, Xiang Wang, Yingya Zhang, and Zhidong Deng. 2023. Dreamtalk: When expressive talking head generation meets diffusion probabilistic models. arXiv preprint arXiv:2312.09767 (2023)."},{"key":"e_1_3_2_1_32_1","volume-title":"A practical Bayesian framework for backpropagation networks. Neural computation","author":"MacKay David JC","year":"1992","unstructured":"David JC MacKay. 1992. A practical Bayesian framework for backpropagation networks. Neural computation, Vol. 4, 3 (1992), 448--472."},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2017.304"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503250"},{"key":"e_1_3_2_1_35_1","volume-title":"Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG)","author":"M\u00fcller Thomas","year":"2022","unstructured":"Thomas M\u00fcller, Alex Evans, Christoph Schied, and Alexander Keller. 2022. Instant neural graphics primitives with a multiresolution hash encoding. ACM transactions on graphics (TOG), Vol. 41, 4 (2022), 1--15."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00070"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00329"},{"key":"e_1_3_2_1_38_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413532"},{"key":"e_1_3_2_1_39_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00197"},{"key":"e_1_3_2_1_40_1","volume-title":"Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556","author":"Simonyan Karen","year":"2014","unstructured":"Karen Simonyan and Andrew Zisserman. 2014. Very deep convolutional networks for large-scale image recognition. arXiv preprint arXiv:1409.1556 (2014)."},{"key":"e_1_3_2_1_41_1","volume-title":"Real-time neural radiance talking portrait synthesis via audio-spatial decomposition. arXiv preprint arXiv:2211.12368","author":"Tang Jiaxiang","year":"2022","unstructured":"Jiaxiang Tang, Kaisiyuan Wang, Hang Zhou, Xiaokang Chen, Dongliang He, Tianshu Hu, Jingtuo Liu, Gang Zeng, and Jingdong Wang. 2022. Real-time neural radiance talking portrait synthesis via audio-spatial decomposition. arXiv preprint arXiv:2211.12368 (2022)."},{"key":"e_1_3_2_1_42_1","volume-title":"EMO: Emote Portrait Alive-Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions. arXiv preprint arXiv:2402.17485","author":"Tian Linrui","year":"2024","unstructured":"Linrui Tian, Qi Wang, Bang Zhang, and Liefeng Bo. 2024. EMO: Emote Portrait Alive-Generating Expressive Portrait Videos with Audio2Video Diffusion Model under Weak Conditions. arXiv preprint arXiv:2402.17485 (2024)."},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01408"},{"key":"e_1_3_2_1_44_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58589-1_42"},{"key":"e_1_3_2_1_45_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v39i8.32946"},{"key":"e_1_3_2_1_46_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00068"},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"publisher","DOI":"10.1609\/aaai.v37i3.25464"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00366"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00938"},{"key":"e_1_3_2_1_50_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-16452-1_48"}],"event":{"name":"ICMR '25: International Conference on Multimedia Retrieval","location":"Chicago IL USA","acronym":"ICMR '25","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 2025 International Conference on Multimedia Retrieval"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3731715.3733279","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:07:36Z","timestamp":1755749256000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733279"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":50,"alternative-id":["10.1145\/3731715.3733279","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733279","relation":{},"subject":[],"published":{"date-parts":[[2025,6,30]]},"assertion":[{"value":"2025-06-30","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}