{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,22]],"date-time":"2026-04-22T20:26:02Z","timestamp":1776889562295,"version":"3.51.2"},"publisher-location":"New York, NY, USA","reference-count":26,"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":[{"DOI":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["No. 62372151 and No.72188101"],"award-info":[{"award-number":["No. 62372151 and No.72188101"]}],"id":[{"id":"10.13039\/https:\/\/doi.org\/10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["dl.acm.org"],"crossmark-restriction":true},"short-container-title":[],"published-print":{"date-parts":[[2024,10,28]]},"DOI":"10.1145\/3664647.3688979","type":"proceedings-article","created":{"date-parts":[[2024,10,26]],"date-time":"2024-10-26T06:59:33Z","timestamp":1729925973000},"page":"11335-11341","update-policy":"https:\/\/doi.org\/10.1145\/crossmark-policy","source":"Crossref","is-referenced-by-count":2,"title":["Exploring Robust Face-Voice Matching in Multilingual Environments"],"prefix":"10.1145","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-5734-7618","authenticated-orcid":false,"given":"Jiehui","family":"Tang","sequence":"first","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0008-8400-2092","authenticated-orcid":false,"given":"Xiaofei","family":"Wang","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0003-9885-5217","authenticated-orcid":false,"given":"Zhen","family":"Xiao","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0009-0009-2380-1330","authenticated-orcid":false,"given":"Jiayi","family":"Liu","sequence":"additional","affiliation":[{"name":"Vanke Meisha Academy, Shenzhen, Guangdong, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-0077-9715","authenticated-orcid":false,"given":"Xueliang","family":"Liu","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-5461-3986","authenticated-orcid":false,"given":"Richang","family":"Hong","sequence":"additional","affiliation":[{"name":"Hefei University of Technology, Hefei, Anhui, China"}],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"320","published-online":{"date-parts":[[2024,10,28]]},"reference":[{"key":"e_1_3_2_1_1_1","volume-title":"Proceedings of the Advances in Neural Information Processing Systems (NeurIPS).","author":"Mohammadreza","unstructured":"Mohammadreza Akbari et al. 2021. VATT: Transformers for Multimodal Self-Supervised Learning from Raw Video, Audio and Text. In Proceedings of the Advances in Neural Information Processing Systems (NeurIPS)."},{"key":"e_1_3_2_1_2_1","volume-title":"Speech Communication","author":"Burkhardt Felix","unstructured":"Felix Burkhardt, Johannes Wagner, Hagen Wierstorf, Florian Eyben, and Bj\u00f6rn Schuller. 2023. Speech-based Age and Gender Prediction with Transformers. In Speech Communication; 15th ITG Conference. VDE, 46--50."},{"key":"e_1_3_2_1_3_1","doi-asserted-by":"publisher","DOI":"10.1145\/3394171.3413710"},{"key":"e_1_3_2_1_4_1","volume-title":"Deep Speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567","author":"Awni Hannun","year":"2014","unstructured":"Awni Hannun et al. 2014. Deep Speech: Scaling up end-to-end speech recognition. arXiv preprint arXiv:1412.5567 (2014)."},{"key":"e_1_3_2_1_5_1","doi-asserted-by":"publisher","DOI":"10.1145\/3240508.3240601"},{"key":"e_1_3_2_1_6_1","volume-title":"Tae-Hyun Oh, Alexandre Kaspar, Mohamed Elgharib, and Wojciech Matusik.","author":"Kim Changil","year":"2019","unstructured":"Changil Kim, Hijung Valentina Shin, Tae-Hyun Oh, Alexandre Kaspar, Mohamed Elgharib, and Wojciech Matusik. 2019. On learning associations of faces and voices. In Computer Vision--ACCV 2018: 14th Asian Conference on Computer Vision, Perth, Australia, December 2--6, 2018, Revised Selected Papers, Part V 14. Springer, 276--292."},{"key":"e_1_3_2_1_7_1","doi-asserted-by":"publisher","DOI":"10.1007\/978--3-030-01261--8_5"},{"key":"e_1_3_2_1_8_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR.2018.00879"},{"key":"e_1_3_2_1_9_1","doi-asserted-by":"publisher","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"e_1_3_2_1_10_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPRW53098.2021.00184"},{"key":"e_1_3_2_1_11_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3071243"},{"key":"e_1_3_2_1_12_1","doi-asserted-by":"crossref","unstructured":"Omkar M Parkhi Andrea Vedaldi and Andrew Zisserman. 2015. Deep face recognition. (2015).","DOI":"10.5244\/C.29.41"},{"key":"e_1_3_2_1_13_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52733.2024.00090"},{"key":"e_1_3_2_1_14_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP43922.2022.9747704"},{"key":"e_1_3_2_1_15_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49357.2023.10097207"},{"key":"e_1_3_2_1_16_1","volume-title":"Rohan Kumar Das, Muhammad Zaigham Zaheer, Marta Moscati, Markus Schedl, Muhammad Haris Khan, Karthik Nandakumar, and Muhammad Haroon Yousaf.","author":"Saeed Muhammad Saad","year":"2024","unstructured":"Muhammad Saad Saeed, Shah Nawaz, Muhammad Salman Tahir, Rohan Kumar Das, Muhammad Zaigham Zaheer, Marta Moscati, Markus Schedl, Muhammad Haris Khan, Karthik Nandakumar, and Muhammad Haroon Yousaf. 2024. Face-voice Association in Multilingual Environments (FAME) Challenge 2024 Evaluation Plan. CoRR, Vol. abs\/2404.09342 (2024). arxiv: 2404.09342 https:\/\/arxiv.org\/abs\/2404.09342"},{"key":"e_1_3_2_1_17_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICEET53442.2021.9659697"},{"key":"e_1_3_2_1_18_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICAI58407.2023.10136626"},{"key":"e_1_3_2_1_19_1","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL). 6558--6569","author":"Hubert Yao-Hung","unstructured":"Yao-Hung Hubert Tsai et al. 2019. Multimodal Transformer for Unaligned Multimodal Language Sequences. In Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (ACL). 6558--6569."},{"key":"e_1_3_2_1_20_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICMEW.2019.00-70"},{"key":"e_1_3_2_1_21_1","volume-title":"Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5022--5030","author":"Wang Xun","year":"2019","unstructured":"Xun Wang, Xintong Han, Weilin Huang, Dengke Dong, and Matthew R. Scott. 2019. Multi-Similarity Loss With General Pair Weighting for Deep Metric Learning. In Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR). 5022--5030. https:\/\/openaccess.thecvf.com\/content_CVPR_2019\/html\/Wang_Multi-Similarity_Loss_With_General_Pair_Weighting_for_Deep_Metric_Learning_CVPR_2019_paper.html"},{"key":"e_1_3_2_1_22_1","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR46437.2021.01608"},{"key":"e_1_3_2_1_23_1","volume-title":"Weiyang Liu, Bhiksha Raj, and Rita Singh.","author":"Wen Yandong","year":"2018","unstructured":"Yandong Wen, Mahmoud Al Ismail, Weiyang Liu, Bhiksha Raj, and Rita Singh. 2018. Disjoint mapping network for cross-modal matching of voices and faces. arXiv preprint arXiv:1807.04836 (2018)."},{"key":"e_1_3_2_1_24_1","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP.2019.8683120"},{"key":"e_1_3_2_1_25_1","doi-asserted-by":"publisher","DOI":"10.1109\/TMM.2021.3050089"},{"key":"e_1_3_2_1_26_1","doi-asserted-by":"publisher","DOI":"10.24963\/ijcai.2022\/526"}],"event":{"name":"MM '24: The 32nd ACM International Conference on Multimedia","location":"Melbourne VIC Australia","acronym":"MM '24","sponsor":["SIGMM ACM Special Interest Group on Multimedia"]},"container-title":["Proceedings of the 32nd ACM International Conference on Multimedia"],"original-title":[],"link":[{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688979","content-type":"unspecified","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/dl.acm.org\/doi\/pdf\/10.1145\/3664647.3688979","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,6,19]],"date-time":"2025-06-19T01:17:28Z","timestamp":1750295848000},"score":1,"resource":{"primary":{"URL":"https:\/\/dl.acm.org\/doi\/10.1145\/3664647.3688979"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,10,28]]},"references-count":26,"alternative-id":["10.1145\/3664647.3688979","10.1145\/3664647"],"URL":"https:\/\/doi.org\/10.1145\/3664647.3688979","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"}}]}}