{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,12,6]],"date-time":"2025-12-06T16:48:54Z","timestamp":1765039734707,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":23,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819984282"},{"type":"electronic","value":"9789819984299"}],"license":[{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T00:00:00Z","timestamp":1703376000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2024]]},"DOI":"10.1007\/978-981-99-8429-9_22","type":"book-chapter","created":{"date-parts":[[2023,12,23]],"date-time":"2023-12-23T08:02:17Z","timestamp":1703318537000},"page":"271-283","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["An Efficient Momentum Framework for\u00a0Face-Voice Association Learning"],"prefix":"10.1007","author":[{"given":"Yuanyuan","family":"Qiu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenning","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zhenguo","family":"Gao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,24]]},"reference":[{"issue":"3","key":"22_CR1","doi-asserted-by":"publisher","first-page":"367","DOI":"10.1016\/j.cortex.2010.03.003","volume":"47","author":"F Joassin","year":"2011","unstructured":"Joassin, F., Pesenti, M., Maurage, P., Verreckt, E., Bruyer, R., Campanella, S.: Cross-modal interactions between human faces and voices involved in person recognition. Cortex 47(3), 367\u2013376 (2011)","journal-title":"Cortex"},{"issue":"19","key":"22_CR2","doi-asserted-by":"publisher","first-page":"1709","DOI":"10.1016\/j.cub.2003.09.005","volume":"13","author":"M Kamachi","year":"2003","unstructured":"Kamachi, M., Hill, H., Lander, K., Vatikiotis-Bateson, E.: Putting the face to the voice\u2019: matching identity across modality. Curr. Biol. 13(19), 1709\u20131714 (2003)","journal-title":"Curr. Biol."},{"issue":"3","key":"22_CR3","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1207\/s15326969eco1603_1","volume":"16","author":"L Lachs","year":"2004","unstructured":"Lachs, L., Pisoni, D.B.: Crossmodal source identification in speech perception. Ecol. Psychol. 16(3), 159\u2013187 (2004)","journal-title":"Ecol. Psychol."},{"key":"22_CR4","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Look, listen and learn. In: Proceedings of the IEEE International Conference on Computer Vision, pp. 609\u2013617 (2017)","DOI":"10.1109\/ICCV.2017.73"},{"key":"22_CR5","doi-asserted-by":"crossref","unstructured":"Arandjelovic, R., Zisserman, A.: Objects that sound. In: Proceedings of the European Conference on Computer Vision, pp. 435\u2013451 (2018)","DOI":"10.1007\/978-3-030-01246-5_27"},{"key":"22_CR6","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Albanie, S., Zisserman, A.: Seeing voices and hearing faces: cross-modal biometric matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 8427\u20138436 (2018)","DOI":"10.1109\/CVPR.2018.00879"},{"key":"22_CR7","unstructured":"Wen, Y., Ismail, M.A., Liu, W., Raj, B., Singh, R.: Disjoint mapping network for cross-modal matching of voices and faces. In: Proceedings of the International Conference on Learning Representations (2018)"},{"key":"22_CR8","doi-asserted-by":"crossref","unstructured":"Kim, C., Shin, H.V., Oh, T.-H., Kaspar, A., Elgharib, M., Matusik, W.: On learning associations of faces and voices. In: Proceedings of the Asian Conference on Computer Vision, pp. 276\u2013292 (2019)","DOI":"10.1007\/978-3-030-20873-8_18"},{"key":"22_CR9","doi-asserted-by":"crossref","unstructured":"Nagrani, A., Albanie, S., Zisserman, A.: Learnable pins: cross-modal embeddings for person identity. In: Proceedings of the European Conference on Computer Vision, pp. 71\u201388 (2018)","DOI":"10.1007\/978-3-030-01261-8_5"},{"key":"22_CR10","doi-asserted-by":"crossref","unstructured":"Wang, R., Liu, X., Cheung, Y.-M., Cheng, K., Wang, N., Fan, W.: Learning discriminative joint embeddings for efficient face and voice association. In: Proceedings of the International ACM SIGIR Conference on Research and Development in Information Retrieval, pp. 1881\u20131884 (2020)","DOI":"10.1145\/3397271.3401302"},{"key":"22_CR11","doi-asserted-by":"crossref","unstructured":"Wen, P., Xu, Q., Jiang, Y., Yang, Z., He, Y., Huang, Q.: Seeking the shape of sound: an adaptive framework for learning voice-face association. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 16347\u201316356 (2021)","DOI":"10.1109\/CVPR46437.2021.01608"},{"key":"22_CR12","doi-asserted-by":"crossref","unstructured":"Horiguchi, S., Kanda, N., Nagamatsu, K.: Face-voice matching using cross-modal embeddings. In: Proceedings of the ACM International Conference on Multimedia, pp. 1011\u20131019 (2018)","DOI":"10.1145\/3240508.3240601"},{"key":"22_CR13","doi-asserted-by":"crossref","unstructured":"Hadsell, R., Chopra, S., LeCun, Y.: Dimensionality reduction by learning an invariant mapping. In: Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, pp. 1735\u20131742 (2006)","DOI":"10.1109\/CVPR.2006.100"},{"issue":"2","key":"22_CR14","first-page":"207","volume":"10","author":"KQ Weinberger","year":"2009","unstructured":"Weinberger, K.Q., Saul, L.K.: Distance metric learning for large margin nearest neighbor classification. J. Mach. Learn. Res. 10(2), 207\u2013244 (2009)","journal-title":"J. Mach. Learn. Res."},{"key":"22_CR15","unstructured":"Sohn, K.: Improved deep metric learning with multi-class n-pair loss objective. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"22_CR16","doi-asserted-by":"crossref","unstructured":"Han, T., Xie, W., Zisserman, A.: Memory-augmented dense predictive coding for video representation learning. In: Proceedings of the European Conference on Computer Vision, pp. 312\u2013329 (2020)","DOI":"10.1007\/978-3-030-58580-8_19"},{"key":"22_CR17","doi-asserted-by":"crossref","unstructured":"Pan, T., Song, Y., Yang, T., Jiang, W., Liu, W.: Videomoco: contrastive video representation learning with temporally adversarial examples. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 205\u2013214 (2021)","DOI":"10.1109\/CVPR46437.2021.01105"},{"key":"22_CR18","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"22_CR19","doi-asserted-by":"publisher","DOI":"10.1016\/j.csl.2019.101027","volume":"60","author":"A Nagrani","year":"2020","unstructured":"Nagrani, A., Chung, J.S., Xie, W., Zisserman, A.: Voxceleb: large-scale speaker verification in the wild. Comput. Speech Lang. 60, 101027 (2020)","journal-title":"Comput. Speech Lang."},{"key":"22_CR20","doi-asserted-by":"crossref","unstructured":"Parkhi, O.M., Vedaldi, A., Zisserman, A.: Deep face recognition. In: Proceedings of the British Machine Vision Conference, pp. 41.1\u201341.12 (2015)","DOI":"10.5244\/C.29.41"},{"key":"22_CR21","doi-asserted-by":"crossref","unstructured":"Guo, Y., Zhang, L., Hu, Y., He, X., Gao, J.: Ms-celeb-1m: a dataset and benchmark for large-scale face recognition. In: Proceedings of the European Conference on Computer Vision, pp. 87\u2013102 (2016)","DOI":"10.1007\/978-3-319-46487-9_6"},{"key":"22_CR22","doi-asserted-by":"crossref","unstructured":"Chung, J.S., Nagrani, A., Zisserman, A.: Voxceleb2: deep speaker recognition. In: Interspeech, pp. 1086\u20131090 (2018)","DOI":"10.21437\/Interspeech.2018-1929"},{"key":"22_CR23","first-page":"2579","volume":"9","author":"L van der Maaten","year":"2008","unstructured":"van der Maaten, L., Hinton, G.: Visualizing data using t-sne. J. Mach. Learn. Res. 9, 2579\u20132605 (2008)","journal-title":"J. Mach. Learn. Res."}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-8429-9_22","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,6]],"date-time":"2024-11-06T19:34:37Z","timestamp":1730921677000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8429-9_22"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,24]]},"ISBN":["9789819984282","9789819984299"],"references-count":23,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8429-9_22","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,24]]},"assertion":[{"value":"24 December 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"PRCV","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Chinese Conference on Pattern Recognition and Computer Vision (PRCV)","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xiamen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2023","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13 October 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"15 October 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"ccprcv2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/prcv2023.xmu.edu.cn\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Microsoft CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1420","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"532","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"0","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"37% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,78","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3,69","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}