{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,13]],"date-time":"2025-10-13T01:29:17Z","timestamp":1760318957134,"version":"3.40.3"},"publisher-location":"Cham","reference-count":33,"publisher":"Springer Nature Switzerland","isbn-type":[{"type":"print","value":"9783031442094"},{"type":"electronic","value":"9783031442100"}],"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\/978-3-031-44210-0_23","type":"book-chapter","created":{"date-parts":[[2023,9,21]],"date-time":"2023-09-21T08:02:34Z","timestamp":1695283354000},"page":"283-294","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":1,"title":["Exploiting Multi-modal Fusion for\u00a0Robust Face Representation Learning with\u00a0Missing Modality"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-3686-4420","authenticated-orcid":false,"given":"Yizhe","family":"Zhu","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-3092-0583","authenticated-orcid":false,"given":"Xin","family":"Sun","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9943-5482","authenticated-orcid":false,"given":"Xi","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,9,22]]},"reference":[{"issue":"7","key":"23_CR1","doi-asserted-by":"publisher","first-page":"727","DOI":"10.1016\/j.imavis.2006.01.017","volume":"24","author":"G Bebis","year":"2006","unstructured":"Bebis, G., Gyaourova, A., Singh, S., Pavlidis, I.: Face recognition by fusing thermal infrared and visible imagery. Image Vision Comput. 24(7), 727\u2013742 (2006)","journal-title":"Image Vision Comput."},{"key":"23_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"},{"key":"23_CR3","doi-asserted-by":"crossref","unstructured":"Cui, J., Zhang, H., Han, H., Shan, S., Chen, X.: Improving 2D face recognition via discriminative face depth estimation. In: 2018 International Conference on Biometrics (ICB), pp. 140\u2013147. IEEE (2018)","DOI":"10.1109\/ICB2018.2018.00031"},{"key":"23_CR4","unstructured":"Dosovitskiy, A., et al.: An image is worth 16$$\\times $$16 words: transformers for image recognition at scale. arXiv preprint arXiv:2010.11929 (2020)"},{"key":"23_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 (2018)","DOI":"10.1145\/3240508.3240528"},{"issue":"11","key":"23_CR6","doi-asserted-by":"publisher","first-page":"139","DOI":"10.1145\/3422622","volume":"63","author":"I Goodfellow","year":"2020","unstructured":"Goodfellow, I.: Generative adversarial networks. Commun. ACM 63(11), 139\u2013144 (2020)","journal-title":"Commun. ACM"},{"key":"23_CR7","doi-asserted-by":"crossref","unstructured":"Guerrero, R., Pham, H.X., Pavlovic, V.: Cross-modal retrieval and synthesis (x-mrs): Closing the modality gap in shared subspace learning. In: Proceedings of the 29th ACM International Conference on Multimedia, pp. 3192\u20133201 (2021)","DOI":"10.1145\/3474085.3475465"},{"key":"23_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: ICASSP 2019\u20132019 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 5861\u20135865. IEEE (2019)","DOI":"10.1109\/ICASSP.2019.8682773"},{"key":"23_CR9","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: Misa: modality-invariant and-specific representations for multimodal sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 1122\u20131131 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"23_CR10","unstructured":"Kim, W., Son, B., Kim, I.: Vilt: vision-and-language transformer without convolution or region supervision. In: Proceedings of the 38th International Conference on Machine Learning, ICML. Proceedings of Machine Learning Research, vol. 139, pp. 5583\u20135594 (2021)"},{"key":"23_CR11","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"23_CR12","unstructured":"Lee, S., Yu, Y., Kim, G., Breuel, T.M., Kautz, J., Song, Y.: Parameter efficient multimodal transformers for video representation learning. In: 9th International Conference on Learning Representations, ICLR (2021)"},{"key":"23_CR13","doi-asserted-by":"crossref","unstructured":"Liu, A.H., Jin, S., Lai, C.I.J., Rouditchenko, A., Oliva, A., Glass, J.: Cross-modal discrete representation learning. arXiv preprint arXiv:2106.05438 (2021)","DOI":"10.18653\/v1\/2022.acl-long.215"},{"key":"23_CR14","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., Liang, P.P., Zadeh, A., Morency, L.P.: Efficient low-rank multimodal fusion with modality-specific factors. arXiv preprint arXiv:1806.00064 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"23_CR15","doi-asserted-by":"crossref","unstructured":"Ma, M., Ren, J., Zhao, L., Testuggine, D., Peng, X.: Are multimodal transformers robust to missing modality? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 18177\u201318186 (2022)","DOI":"10.1109\/CVPR52688.2022.01764"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Ma, M., Ren, J., Zhao, L., Tulyakov, S., Wu, C., Peng, X.: Smil: multimodal learning with severely missing modality. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 2302\u20132310 (2021)","DOI":"10.1609\/aaai.v35i3.16330"},{"key":"23_CR17","doi-asserted-by":"crossref","unstructured":"Mu, G., Huang, D., Hu, G., Sun, J., Wang, Y.: Led3d: a lightweight and efficient deep approach to recognizing low-quality 3D faces. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 5773\u20135782 (2019)","DOI":"10.1109\/CVPR.2019.00592"},{"key":"23_CR18","doi-asserted-by":"crossref","unstructured":"Nikisins, O., Nasrollahi, K., Greitans, M., Moeslund, T.B.: Rgb-dt based face recognition. In: 2014 22nd International Conference on Pattern Recognition, pp. 1716\u20131721. IEEE (2014)","DOI":"10.1109\/ICPR.2014.302"},{"key":"23_CR19","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, vol. 33, pp. 6892\u20136899 (2019)","DOI":"10.1609\/aaai.v33i01.33016892"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Poria, S., Chaturvedi, I., Cambria, E., Hussain, A.: Convolutional mkl based multimodal emotion recognition and sentiment analysis. In: 2016 IEEE 16th International Conference on Data Mining (ICDM), pp. 439\u2013448. IEEE (2016)","DOI":"10.1109\/ICDM.2016.0055"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Schroff, F., Kalenichenko, D., Philbin, J.: Facenet: a unified embedding for face recognition and clustering. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 815\u2013823 (2015)","DOI":"10.1109\/CVPR.2015.7298682"},{"issue":"04","key":"23_CR22","doi-asserted-by":"publisher","first-page":"1756005","DOI":"10.1142\/S0218001417560055","volume":"31","author":"A Seal","year":"2017","unstructured":"Seal, A., Bhattacharjee, D., Nasipuri, M., Gonzalo-Martin, C., Menasalvas, E.: Fusion of visible and thermal images using a directed search method for face recognition. Int. J. Pattern Recogn. Artif. Intell. 31(04), 1756005 (2017)","journal-title":"Int. J. Pattern Recogn. Artif. Intell."},{"key":"23_CR23","first-page":"1","volume":"32","author":"Y Shi","year":"2019","unstructured":"Shi, Y., Paige, B., Torr, P., et al.: Variational mixture-of-experts autoencoders for multi-modal deep generative models. Adv. Neural Inf. Process. Syst. 32, 1\u201312 (2019)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"23_CR24","doi-asserted-by":"crossref","unstructured":"Strudel, R., Pinel, R.G., Laptev, I., Schmid, C.: Segmenter: transformer for semantic segmentation. In: 2021 IEEE\/CVF International Conference on Computer Vision, ICCV 2021, Montreal, QC, Canada, 10\u201317 October 2021, pp. 7242\u20137252 (2021)","DOI":"10.1109\/ICCV48922.2021.00717"},{"key":"23_CR25","unstructured":"Tsai, Y.H.H., Liang, P.P., Zadeh, A., Morency, L.P., Salakhutdinov, R.: Learning factorized multimodal representations. arXiv preprint arXiv:1806.06176 (2018)"},{"key":"23_CR26","doi-asserted-by":"publisher","first-page":"2461","DOI":"10.1109\/TIFS.2021.3053458","volume":"16","author":"H Uppal","year":"2021","unstructured":"Uppal, H., Sepas-Moghaddam, A., Greenspan, M., Etemad, A.: Depth as attention for face representation learning. IEEE Trans. Inf. Forensics Secur. 16, 2461\u20132476 (2021)","journal-title":"IEEE Trans. Inf. Forensics Secur."},{"key":"23_CR27","first-page":"1","volume":"31","author":"M Wu","year":"2018","unstructured":"Wu, M., Goodman, N.: Multimodal generative models for scalable weakly-supervised learning. Adv. Neural Inf. Process. Syst. 31, 1\u201311 (2018)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"23_CR28","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"23_CR29","first-page":"23634","volume":"34","author":"R Zellers","year":"2021","unstructured":"Zellers, R., et al.: Merlot: multimodal neural script knowledge models. Adv. Neural Inf. Process. Syst. 34, 23634\u201323651 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"23_CR30","unstructured":"Zellinger, W., Grubinger, T., Lughofer, E., Natschl\u00e4ger, T., Saminger-Platz, S.: Central moment discrepancy (cmd) for domain-invariant representation learning. arXiv preprint arXiv:1702.08811 (2017)"},{"key":"23_CR31","doi-asserted-by":"crossref","unstructured":"Zhang, J., Huang, D., Wang, Y., Sun, J.: Lock3dface: a large-scale database of low-cost kinect 3d faces. In: 2016 International Conference on Biometrics (ICB), pp. 1\u20138. IEEE (2016)","DOI":"10.1109\/ICB.2016.7550062"},{"key":"23_CR32","first-page":"27196","volume":"34","author":"Z Zhang","year":"2021","unstructured":"Zhang, Z., et al.: Ufc-bert: unifying multi-modal controls for conditional image synthesis. Adv. Neural Inf. Process. Syst. 34, 27196\u201327208 (2021)","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"23_CR33","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, vol. 1: Long Papers, pp. 2608\u20132618 (2021)","DOI":"10.18653\/v1\/2021.acl-long.203"}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2023"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-44210-0_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,28]],"date-time":"2024-10-28T15:29:21Z","timestamp":1730129361000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-44210-0_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9783031442094","9783031442100"],"references-count":33,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-44210-0_23","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":"22 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Heraklion","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Greece","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":"26 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"32","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2023\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"easyacademia.org","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"947","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":"426","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":"22","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":"45% - 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":"2.4","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)"}},{"value":"type of other papers accepted : 9 Abstract","order":10,"name":"additional_info_on_review_process","label":"Additional Info on Review Process","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}