{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:47:48Z","timestamp":1742914068726,"version":"3.40.3"},"publisher-location":"Cham","reference-count":21,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031278174"},{"type":"electronic","value":"9783031278181"}],"license":[{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,1,1]],"date-time":"2023-01-01T00:00:00Z","timestamp":1672531200000},"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":[[2023]]},"DOI":"10.1007\/978-3-031-27818-1_43","type":"book-chapter","created":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:20:17Z","timestamp":1680171617000},"page":"523-535","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Audio-Visual Sensor Fusion Framework Using Person Attributes Robust to\u00a0Missing Visual Modality for\u00a0Person Recognition"],"prefix":"10.1007","author":[{"given":"Vijay","family":"John","sequence":"first","affiliation":[]},{"given":"Yasutomo","family":"Kawanishi","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2023,3,31]]},"reference":[{"key":"43_CR1","first-page":"1","volume":"10","author":"K Bayoudh","year":"2021","unstructured":"Bayoudh, K., Knani, R., Hamdaoui, F., Mtibaa, A.: A survey on deep multimodal learning for computer vision: advances, trends, applications, and datasets. Visual Comput. 10, 1\u201332 (2021)","journal-title":"Visual Comput."},{"key":"43_CR2","doi-asserted-by":"crossref","unstructured":"Cai, L., Wang, Z., Gao, H., Shen, D., Ji, S.: Deep adversarial learning for multi-modality missing data completion. In: Proceedings of the 24th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp. 1158\u20131166 (2018)","DOI":"10.1145\/3219819.3219963"},{"issue":"4","key":"43_CR3","doi-asserted-by":"publisher","first-page":"377","DOI":"10.1109\/TAFFC.2014.2336244","volume":"5","author":"H Cao","year":"2014","unstructured":"Cao, H., Cooper, D.G., Keutmann, M.K., Gur, R.C., Nenkova, A., Verma, R.: CREMA-D: crowd-sourced emotional multimodal actors dataset. IEEE Trans. Affect. Comput. 5(4), 377\u2013390 (2014)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"43_CR4","unstructured":"Das, R.K., Tao, R., Yang, J., Rao, W., Yu, C., Li, H.: HLT-NUS submission for 2019 NIST multimedia speaker recognition evaluation. In: Proceedings of the APSIPA, Annual Summit and Conference, pp. 605\u2013609, December 2020"},{"key":"43_CR5","doi-asserted-by":"crossref","unstructured":"Du, C., et al.: Semi-supervised deep generative modelling of incomplete multi-modality emotional data. In: Proceedings of the 26th ACM International Conference on Multimedia, pp. 108\u2013116, October 2018","DOI":"10.1145\/3240508.3240528"},{"key":"43_CR6","doi-asserted-by":"crossref","unstructured":"Geng, J., Liu, X., Cheung, Y.M.: Audio-visual speaker recognition via multi-modal correlated neural networks. In: Proceedings of 2016 IEEE\/WIC\/ACM International Conference on Web Intelligence Workshops (WIW), pp. 123\u2013128, October 2016","DOI":"10.1109\/WIW.2016.043"},{"key":"43_CR7","unstructured":"Guo, J., Deng, J., Lattas, A., Zafeiriou, S.: Sample and computation redistribution for efficient face detection. arXiv preprint arXiv:2105.04714, May 2021"},{"key":"43_CR8","doi-asserted-by":"crossref","unstructured":"Han, J., Zhang, Z., Ren, Z., Schuller, B.: Implicit fusion by joint audiovisual training for emotion recognition in mono modality. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5861\u20135865, May 2019","DOI":"10.1109\/ICASSP.2019.8682773"},{"key":"43_CR9","doi-asserted-by":"crossref","unstructured":"Li, Q., Wan, Q., Lee, S.H., Choe, Y.: Video face recognition with audio-visual aggregation network. In: Proceedings of the International Conference on Neural Information Processing, pp. 150\u2013161, December 2021","DOI":"10.1007\/978-3-030-92273-3_13"},{"key":"43_CR10","doi-asserted-by":"crossref","unstructured":"Ma, M., Ren, J., Zhao, L., Tulyakov, S., Wu, C., Peng, X.: SMIL: multimodal learning with severely missing modality. CoRR abs\/2103.05677 (2021)","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"43_CR11","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"73","DOI":"10.1007\/978-3-030-01261-8_5","volume-title":"Computer Vision \u2013 ECCV 2018","author":"A Nagrani","year":"2018","unstructured":"Nagrani, A., Albanie, S., Zisserman, A.: Learnable PINs: cross-modal embeddings for person identity. In: Ferrari, V., Hebert, M., Sminchisescu, C., Weiss, Y. (eds.) ECCV 2018. LNCS, vol. 11217, pp. 73\u201389. Springer, Cham (2018). https:\/\/doi.org\/10.1007\/978-3-030-01261-8_5"},{"key":"43_CR12","doi-asserted-by":"crossref","unstructured":"Nawaz, S., Janjua, M.K., Gallo, I., Mahmood, A., Calefati, A.: Deep latent space learning for cross-modal mapping of audio and visual signals. In: Proceedings of the Digital Image Computing: Techniques and Applications (DICTA), pp. 1\u20137, December 2019","DOI":"10.1109\/DICTA47822.2019.8945863"},{"key":"43_CR13","doi-asserted-by":"crossref","unstructured":"Parthasarathy, S., Sundaram., S.: Training strategies to handle missing modalities for audio-visual expression recognition. In: Proceedings of the 2020 International Conference on Multimodal Interaction, pp. 400\u2013404, October 2020","DOI":"10.1145\/3395035.3425202"},{"key":"43_CR14","doi-asserted-by":"crossref","unstructured":"Pham, H., Liang, P.P., Manzini, T., Morency, L.P., P\u00f3czos, B.: Found in translation: learning robust joint representations by cyclic translations between modalities. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp. 6892\u20136899, February 2019","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"43_CR15","doi-asserted-by":"crossref","unstructured":"Sadjadi, S., Greenberg, C., Singer, E., Olson, D., Mason, L., Hernandez-Cordero, J.: The 2019 NIST audio-visual speaker recognition evaluation. In: Proceedings of the Speaker and Language Recognition Workshop: Odyssey 2020, pp. 266\u2013272 (2020)","DOI":"10.21437\/Odyssey.2020-37"},{"key":"43_CR16","doi-asserted-by":"crossref","unstructured":"Sell, G., Duh, K., Snyder, D., Etter, D., Garcia-Romero, D.: Audio-visual person recognition in multimedia data from the Iarpa Janus program. In: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 3031\u20133035, April 2018","DOI":"10.1109\/ICASSP.2018.8462122"},{"key":"43_CR17","doi-asserted-by":"crossref","unstructured":"Tao, R., Das, R.K., Li, H.: Audio-visual speaker recognition with a cross-modal discriminative network. In: Proceedings of Annual Conference of the International Speech Communication Association, (INTERSPEECH), pp. 2242\u20132246, October 2020","DOI":"10.21437\/Interspeech.2020-1814"},{"key":"43_CR18","first-page":"1","volume":"8","author":"S Vegad","year":"2017","unstructured":"Vegad, S., Patel, H.P.R., Zhuang, H., Naik, M.R.: Audio-visual person recognition using deep convolutional neural networks. J. Biometrics Biostatistics 8, 1\u20137 (2017)","journal-title":"J. Biometrics Biostatistics"},{"key":"43_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wan, Z., Wan, X.: TransModality: an End2End fusion method with transformer for multimodal sentiment analysis. In: Proceedings of the Web Conference, pp. 2514\u20132520, April 2020","DOI":"10.1145\/3366423.3380000"},{"key":"43_CR20","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 (ICLR), pp. 1\u201317, May 2019"},{"key":"43_CR21","doi-asserted-by":"crossref","unstructured":"Zhao, J., Li, R., Jin, Q.: Missing modality imagination network for emotion recognition with uncertain missing modalities. In: Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 2608\u20132618, August 2021","DOI":"10.18653\/v1\/2021.acl-long.203"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-27818-1_43","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,3,30]],"date-time":"2023-03-30T10:31:49Z","timestamp":1680172309000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-27818-1_43"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031278174","9783031278181"],"references-count":21,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-27818-1_43","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"31 March 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bergen","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Norway","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":"9 January 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 January 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2023","order":10,"name":"conference_id","label":"Conference ID","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":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"267","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":"86","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":"32% - 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","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":"4","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)"}}]}}