{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,2]],"date-time":"2026-06-02T09:30:49Z","timestamp":1780392649729,"version":"3.54.1"},"publisher-location":"New York, NY, USA","reference-count":53,"publisher":"ACM","content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2025,6,30]]},"DOI":"10.1145\/3731715.3733411","type":"proceedings-article","created":{"date-parts":[[2025,6,25]],"date-time":"2025-06-25T18:31:39Z","timestamp":1750876299000},"page":"1340-1349","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":3,"title":["OT-Talk: Animating 3D Talking Head with Optimal Transportation"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-5655-4342","authenticated-orcid":false,"given":"Xinmu","family":"Wang","sequence":"first","affiliation":[{"name":"Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0005-4385-3630","authenticated-orcid":false,"given":"Xiang","family":"Gao","sequence":"additional","affiliation":[{"name":"Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0006-3114-7322","authenticated-orcid":false,"given":"Xiyun","family":"Song","sequence":"additional","affiliation":[{"name":"Futurewei Technologies, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-4793-7585","authenticated-orcid":false,"given":"Heather","family":"Yu","sequence":"additional","affiliation":[{"name":"Futurewei Technologies, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0002-6111-0708","authenticated-orcid":false,"given":"Zongfang","family":"Lin","sequence":"additional","affiliation":[{"name":"Futurewei Technologies, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0009-0000-5161-9688","authenticated-orcid":false,"given":"Liang","family":"Peng","sequence":"additional","affiliation":[{"name":"Futurewei Technologies, Santa Clara, CA, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-8226-5851","authenticated-orcid":false,"given":"Xianfeng","family":"Gu","sequence":"additional","affiliation":[{"name":"Stony Brook University, Stony Brook, NY, USA"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"320","published-online":{"date-parts":[[2025,6,30]]},"reference":[{"key":"e_1_3_2_1_1_1","doi-asserted-by":"publisher","DOI":"10.1145\/3503161.3548101"},{"key":"e_1_3_2_1_2_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_3_1","doi-asserted-by":"publisher","DOI":"10.1093\/imaiai\/iaz003"},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1007\/s10851-014-0506-3"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2019.00731"},{"key":"e_1_3_2_1_6_1","series-title":"SIAM journal on Imaging Sciences","volume-title":"The varifold representation of nonoriented shapes for diffeomorphic registration","author":"Charon Nicolas","year":"2013","unstructured":"Nicolas Charon and Alain Trouv\u00e9. 2013. The varifold representation of nonoriented shapes for diffeomorphic registration. SIAM journal on Imaging Sciences, Vol. 6, 4 (2013), 2547--2580."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58545-7_3"},{"key":"e_1_3_2_1_8_1","volume-title":"Meshgan: Non-linear 3d morphable models of faces. arXiv preprint arXiv:1903.10384","author":"Cheng Shiyang","year":"2019","unstructured":"Shiyang Cheng, Michael Bronstein, Yuxiang Zhou, Irene Kotsia, Maja Pantic, and Stefanos Zafeiriou. 2019. Meshgan: Non-linear 3d morphable models of faces. arXiv preprint arXiv:1903.10384 (2019)."},{"key":"e_1_3_2_1_9_1","volume-title":"Proceedings of the Asian conference on computer vision.","author":"Cheng Shiyang","year":"2020","unstructured":"Shiyang Cheng, Georgios Tzimiropoulos, Jie Shen, and Maja Pantic. 2020. Faster, better and more detailed: 3d face reconstruction with graph convolutional networks. In Proceedings of the Asian conference on computer vision."},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.2312\/LocalChapterEvents\/ItalChap\/ItalianChapConf2008\/129--136"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2019.01034"},{"key":"e_1_3_2_1_12_1","volume-title":"Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems","author":"Cuturi Marco","year":"2013","unstructured":"Marco Cuturi. 2013. Sinkhorn distances: Lightspeed computation of optimal transport. Advances in neural information processing systems, Vol. 26 (2013)."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings, Part XXX 16","author":"Das Dipanjan","year":"2020","unstructured":"Dipanjan Das, Sandika Biswas, Sanjana Sinha, and Brojeshwar Bhowmick. 2020. Speech-driven facial animation using cascaded gans for learning of motion and texture. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XXX 16. Springer, 408--424."},{"key":"e_1_3_2_1_14_1","volume-title":"Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems","author":"Defferrard Micha\u00ebl","year":"2016","unstructured":"Micha\u00ebl Defferrard, Xavier Bresson, and Pierre Vandergheynst. 2016. Convolutional neural networks on graphs with fast localized spectral filtering. Advances in neural information processing systems, Vol. 29 (2016)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1145\/2897824.2925984"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1145\/3395208"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52688.2022.01821"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2010.2052239"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1145\/258734.258849"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2004.1315234"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1145\/3472306.3478335"},{"key":"e_1_3_2_1_22_1","volume-title":"Deep Speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567","author":"Hannun A","year":"2014","unstructured":"A Hannun. 2014. Deep Speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)."},{"key":"e_1_3_2_1_23_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_24_1","volume-title":"Kushal Lakhotia","author":"Hsu Wei-Ning","year":"2021","unstructured":"Wei-Ning Hsu, Benjamin Bolte, Yao-Hung Hubert Tsai, Kushal Lakhotia, Ruslan Salakhutdinov, and Abdelrahman Mohamed. 2021. Hubert: Self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM transactions on audio, speech, and language processing, Vol. 29 (2021), 3451--3460."},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01386"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.487"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073658"},{"key":"e_1_3_2_1_28_1","volume-title":"Pose-aware 3D talking face synthesis using geometry-guided audio-vertices attention","author":"Li Bo","year":"2024","unstructured":"Bo Li, Xiaolin Wei, Bin Liu, Zhifen He, Junjie Cao, and Yu-Kun Lai. 2024. Pose-aware 3D talking face synthesis using geometry-guided audio-vertices attention. IEEE Transactions on Visualization and Computer Graphics (2024)."},{"key":"e_1_3_2_1_29_1","volume-title":"Computer Graphics Forum","author":"Li Kun","unstructured":"Kun Li, Jingying Liu, Yu-Kun Lai, and Jingyu Yang. 2019. Generating 3D Faces using Multi-column Graph Convolutional Networks. In Computer Graphics Forum, Vol. 38. Wiley Online Library, 215--224."},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1145\/3130800.3130813"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00202"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1109\/TVCG.2021.3107669"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-031-73397-0_2"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611734"},{"key":"e_1_3_2_1_35_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV51070.2023.01891"},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1561\/2200000073"},{"key":"e_1_3_2_1_37_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW.2017.287"},{"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":"10.1007\/978-3-030-01219-9_43"},{"key":"e_1_3_2_1_40_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV48922.2021.00121"},{"key":"e_1_3_2_1_41_1","doi-asserted-by":"publisher","DOI":"10.1145\/3623264.3624447"},{"key":"e_1_3_2_1_42_1","doi-asserted-by":"publisher","DOI":"10.1145\/3658221"},{"key":"e_1_3_2_1_43_1","doi-asserted-by":"publisher","DOI":"10.1145\/3072959.3073640"},{"key":"e_1_3_2_1_44_1","volume-title":"Proceedings of the 11th ACM SIGGRAPH\/Eurographics conference on Computer Animation. 275--284","author":"Taylor Sarah L","year":"2012","unstructured":"Sarah L Taylor, Moshe Mahler, Barry-John Theobald, and Iain Matthews. 2012. Dynamic units of visual speech. In Proceedings of the 11th ACM SIGGRAPH\/Eurographics conference on Computer Animation. 275--284."},{"key":"e_1_3_2_1_45_1","volume-title":"Proceedings, Part XVI 16","author":"Thies Justus","year":"2020","unstructured":"Justus Thies, Mohamed Elgharib, Ayush Tewari, Christian Theobalt, and Matthias Nie\u00dfner. 2020. Neural voice puppetry: Audio-driven facial reenactment. In Computer Vision--ECCV 2020: 16th European Conference, Glasgow, UK, August 23--28, 2020, Proceedings, Part XVI 16. Springer, 716--731."},{"key":"e_1_3_2_1_46_1","volume-title":"Topics in optimal transportation","author":"Villani C\u00e9dric","unstructured":"C\u00e9dric Villani. 2021. Topics in optimal transportation. Vol. 58. American Mathematical Soc."},{"key":"e_1_3_2_1_47_1","doi-asserted-by":"crossref","unstructured":"C\u00e9dric Villani et al. 2009. Optimal transport: old and new. Vol. 338. Springer.","DOI":"10.1007\/978-3-540-71050-9"},{"key":"e_1_3_2_1_48_1","doi-asserted-by":"publisher","DOI":"10.1007\/s11263-019-01251-8"},{"key":"e_1_3_2_1_49_1","doi-asserted-by":"publisher","DOI":"10.1145\/3581783.3611775"},{"key":"e_1_3_2_1_50_1","volume-title":"Multiface: A dataset for neural face rendering. arXiv preprint arXiv:2207.11243","author":"Zheng Ningyuan","year":"2022","unstructured":"Cheng-hsin Wuu, Ningyuan Zheng, Scott Ardisson, Rohan Bali, Danielle Belko, Eric Brockmeyer, Lucas Evans, Timothy Godisart, Hyowon Ha, Xuhua Huang, et al. 2022. Multiface: A dataset for neural face rendering. arXiv preprint arXiv:2207.11243 (2022)."},{"key":"e_1_3_2_1_51_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.01229"},{"key":"e_1_3_2_1_52_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.00416"},{"key":"e_1_3_2_1_53_1","doi-asserted-by":"crossref","first-page":"1","DOI":"10.1145\/3197517.3201292","article-title":"Visemenet: Audio-driven animator-centric speech animation","volume":"37","author":"Zhou Yang","year":"2018","unstructured":"Yang Zhou, Zhan Xu, Chris Landreth, Evangelos Kalogerakis, Subhransu Maji, and Karan Singh. 2018. Visemenet: Audio-driven animator-centric speech animation. ACM Transactions on Graphics (TOG), Vol. 37, 4 (2018), 1--10.","journal-title":"ACM Transactions on Graphics (TOG)"}],"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\/3731715.3733411","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T04:11:44Z","timestamp":1755749504000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3731715.3733411"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,6,30]]},"references-count":53,"alternative-id":["10.1145\/3731715.3733411","10.1145\/3731715"],"URL":"https:\/\/doi.org\/10.1145\/3731715.3733411","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"}}]}}