{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,19]],"date-time":"2025-12-19T10:00:58Z","timestamp":1766138458401,"version":"3.44.0"},"publisher-location":"New York, NY, USA","reference-count":37,"publisher":"ACM","license":[{"start":{"date-parts":[[2023,10,26]],"date-time":"2023-10-26T00:00:00Z","timestamp":1698278400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.acm.org\/publications\/policies\/copyright_policy#Background"}],"funder":[{"name":"Zhejiang Lab","award":["2021KH0AB01"],"award-info":[{"award-number":["2021KH0AB01"]}]},{"name":"NSFC\/Research Grants Council (RGC) Joint Research Scheme","award":["N_HKBU214\/21"],"award-info":[{"award-number":["N_HKBU214\/21"]}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2023,10,26]]},"DOI":"10.1145\/3581783.3611938","type":"proceedings-article","created":{"date-parts":[[2023,10,27]],"date-time":"2023-10-27T07:27:40Z","timestamp":1698391660000},"page":"7056-7064","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":1,"title":["Taking a Part for the Whole: An Archetype-agnostic Framework for Voice-Face Association"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0001-3468-9913","authenticated-orcid":false,"given":"Guancheng","family":"Chen","sequence":"first","affiliation":[{"name":"Huaqiao University & Zhejiang Lab, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-0011-6260","authenticated-orcid":false,"given":"Xin","family":"Liu","sequence":"additional","affiliation":[{"name":"Huaqiao University & Zhejiang Lab, Xiamen, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5685-3123","authenticated-orcid":false,"given":"Xing","family":"Xu","sequence":"additional","affiliation":[{"name":"University of Electronic Science and Technology of China, Chengdu, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7629-4648","authenticated-orcid":false,"given":"Yiu-ming","family":"Cheung","sequence":"additional","affiliation":[{"name":"Hong Kong Baptist University, Hong Kong SAR, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-3279-7125","authenticated-orcid":false,"given":"Taihao","family":"Li","sequence":"additional","affiliation":[{"name":"Zhejiang Lab, Hangzhou, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2023,10,27]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Lucas Smaira, Sander Dieleman, and Andrew Zisserman.","author":"Alayrac Jean-Baptiste","year":"2020","unstructured":"Jean-Baptiste Alayrac, Adria Recasens, Rosalia Schneider, Relja Arandjelovi\u0107, Jason Ramapuram, Jeffrey De Fauw, Lucas Smaira, Sander Dieleman, and Andrew Zisserman. 2020. Self-supervised multimodal versatile networks. Advances in Neural Information Processing Systems (2020), 25--37."},{"key":"e_1_3_2_1_2_1","doi-asserted-by":"publisher","DOI":"10.1145\/3512527.3531364"},{"key":"e_1_3_2_1_3_1","volume-title":"Proceedings of the International Conference on Machine Learning (ICML). 1597--1607","author":"Chen Ting","year":"2020","unstructured":"Ting Chen, Simon Kornblith, Mohammad Norouzi, and Geoffrey Hinton. 2020. A Simple Framework for Contrastive Learning of Visual Representations. In Proceedings of the International Conference on Machine Learning (ICML). 1597--1607."},{"key":"e_1_3_2_1_4_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2017.145"},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413710"},{"key":"e_1_3_2_1_6_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413869"},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"e_1_3_2_1_8_1","article-title":"Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation","volume":"112","author":"Ephrat Ariel","year":"2018","unstructured":"Ariel Ephrat, Inbar Mosseri, Oran Lang, et al. 2018. Looking to Listen at the Cocktail Party: A Speaker-Independent Audio-Visual Model for Speech Separation. In ACM Transactions on Graphics. Article 112, 11 pages.","journal-title":"ACM Transactions on Graphics. Article"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCVW54120.2021.00261"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"e_1_3_2_1_11_1","volume-title":"Proceedings of the thirteenth international conference on artificial intelligence and statistics. 297--304","author":"Gutmann Michael","year":"2010","unstructured":"Michael Gutmann and Aapo Hyv\"arinen. 2010. Noise-contrastive estimation: A new estimation principle for unnormalized statistical models. In Proceedings of the thirteenth international conference on artificial intelligence and statistics. 297--304."},{"key":"e_1_3_2_1_12_1","volume-title":"Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition (CVPR). 9729--9738","author":"He Kaiming","year":"2019","unstructured":"Kaiming He, Haoqi Fan, Yuxin Wu, Saining Xie, and Ross Girshick. 2019. Momentum Contrast for Unsupervised Visual Representation Learning. In Proceedings of the IEEE\/CVF conference on Computer Vision and Pattern Recognition (CVPR). 9729--9738."},{"key":"e_1_3_2_1_13_1","volume-title":"Proceedings of the International conference on machine learning (ICML). 4182--4192","author":"Henaff Olivier","year":"2020","unstructured":"Olivier Henaff. 2020. Data-efficient image recognition with contrastive predictive coding. In Proceedings of the International conference on machine learning (ICML). 4182--4192."},{"key":"e_1_3_2_1_14_1","volume-title":"Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR).","author":"Hermans Alexander","year":"2017","unstructured":"Alexander Hermans, Lucas Beyer, and Bastian Leibe. 2017. In Defense of the Triplet Loss for Person Re-Identification. In Proceedings of the IEEE conference on Computer Vision and Pattern Recognition (CVPR)."},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1016\/j.cub.2003.09.005"},{"key":"e_1_3_2_1_16_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"e_1_3_2_1_17_1","volume-title":"Learning Disentangled Latent Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach. arXiv preprint arXiv:2012.00682","author":"Kim Minyoung","year":"2020","unstructured":"Minyoung Kim, Ricardo Guerrero, and Vladimir Pavlovic. 2020. Learning Disentangled Latent Factors from Paired Data in Cross-Modal Retrieval: An Implicit Identifiable VAE Approach. arXiv preprint arXiv:2012.00682 (2020)."},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/TPAMI.2019.2940446"},{"key":"e_1_3_2_1_19_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01229"},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"e_1_3_2_1_21_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP40776.2020.9054057"},{"key":"e_1_3_2_1_23_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_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2016.434"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_2_1_27_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2015.7298682"},{"key":"e_1_3_2_1_28_1","volume-title":"Advances in Neural Information Processing Systems (NIPS)","volume":"29","author":"Sohn Kihyuk","year":"2016","unstructured":"Kihyuk Sohn. 2016. Improved deep metric learning with multi-class N-pair loss objective. Advances in Neural Information Processing Systems (NIPS), Vol. 29 (2016)."},{"key":"e_1_3_2_1_29_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR42600.2020.00643"},{"key":"e_1_3_2_1_30_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW50498.2020.00488"},{"key":"e_1_3_2_1_31_1","doi-asserted-by":"publisher","DOI":"10.1007\/978-3-030-58621-8_45"},{"key":"e_1_3_2_1_32_1","doi-asserted-by":"publisher","DOI":"10.1145\/3397271.3401302"},{"key":"e_1_3_2_1_33_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICCV.2015.320"},{"key":"e_1_3_2_1_34_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01608"},{"key":"e_1_3_2_1_35_1","volume-title":"Proceedings of the International Conference on Learning Representations (ICLR).","author":"Wen Yandong","year":"2018","unstructured":"Yandong Wen, Mahmoud Al Ismail, Weiyang Liu, et al. 2018. Disjoint Mapping Network for Cross-modal Matching of Voices and Faces. In Proceedings of the International Conference on Learning Representations (ICLR)."},{"key":"e_1_3_2_1_36_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00393"},{"key":"e_1_3_2_1_37_1","volume-title":"Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast. arXiv preprint arXiv:2204.14057","author":"Zhu Boqing","year":"2022","unstructured":"Boqing Zhu, Kele Xu, Changjian Wang, Zheng Qin, Tao Sun, Huaimin Wang, and Yuxing Peng. 2022. Unsupervised Voice-Face Representation Learning by Cross-Modal Prototype Contrast. arXiv preprint arXiv:2204.14057 (2022)."}],"event":{"name":"MM '23: The 31st ACM International Conference on Multimedia","sponsor":["SIGMM ACM Special Interest Group on Multimedia"],"location":"Ottawa ON Canada","acronym":"MM '23"},"container-title":["Proceedings of the 31st ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611938","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3581783.3611938","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,8,22]],"date-time":"2025-08-22T00:04:19Z","timestamp":1755821059000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3581783.3611938"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,10,26]]},"references-count":37,"alternative-id":["10.1145\/3581783.3611938","10.1145\/3581783"],"URL":"https:\/\/doi.org\/10.1145\/3581783.3611938","relation":{},"subject":[],"published":{"date-parts":[[2023,10,26]]},"assertion":[{"value":"2023-10-27","order":3,"name":"published","label":"Published","group":{"name":"publication_history","label":"Publication History"}}]}}