{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:30:41Z","timestamp":1742913041545,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819985395"},{"type":"electronic","value":"9789819985401"}],"license":[{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2023,12,25]],"date-time":"2023-12-25T00:00:00Z","timestamp":1703462400000},"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\/978-981-99-8540-1_14","type":"book-chapter","created":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:01:32Z","timestamp":1703440892000},"page":"170-182","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MetaSelection: A Learnable Masked AutoEncoder for\u00a0Multimodal Sentiment Feature Selection"],"prefix":"10.1007","author":[{"given":"Xuefeng","family":"Liang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Han","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Huijun","family":"Xuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ying","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2023,12,25]]},"reference":[{"key":"14_CR1","unstructured":"Andrew, G., Arora, R., Bilmes, J., Livescu, K.: Deep canonical correlation analysis. In: International Conference on Machine Learning, pp. 1247\u20131255 (2013)"},{"key":"14_CR2","doi-asserted-by":"crossref","unstructured":"Bagher Zadeh, A., Liang, P.P., Poria, S., Cambria, E., Morency, L.P.: Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph. In: Annual Meeting of the Association for Computational Linguistics, vol. 1, pp. 2236\u20132246 (2018)","DOI":"10.18653\/v1\/P18-1208"},{"key":"14_CR3","first-page":"1","volume":"38","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. Vis. Comput. 38, 1\u201332 (2021)","journal-title":"Vis. Comput."},{"key":"14_CR4","unstructured":"Bousmalis, K., Trigeorgis, G., Silberman, N., Krishnan, D., Erhan, D.: Domain separation networks. Adv. Neural Inf. Process. Syst. 29 (2016)"},{"key":"14_CR5","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Gelbukh, A., Zadeh, A., Morency, L.P., Poria, S.: Bi-bimodal modality fusion for correlation-controlled multimodal sentiment analysis. In: International Conference on Multimodal Interaction, pp. 6\u201315 (2021)","DOI":"10.1145\/3462244.3479919"},{"key":"14_CR6","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Poria, S.: Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. In: Conference on Empirical Methods in Natural Language Processing, pp. 9180\u20139192 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"14_CR7","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S.: MISA: modality-invariant and -specific representations for multimodal sentiment analysis. In: ACM International Conference on Multimedia, pp. 1122\u20131131 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"14_CR8","doi-asserted-by":"crossref","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 16000\u201316009 (2022)","DOI":"10.1109\/CVPR52688.2022.01553"},{"key":"14_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J.: Deep residual learning for image recognition. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 770\u2013778 (2016)","DOI":"10.1109\/CVPR.2016.90"},{"key":"14_CR10","doi-asserted-by":"crossref","unstructured":"Hotelling, H.: Relations between two sets of variates. In: Breakthroughs in Statistics: Methodology and Distribution, pp. 162\u2013190 (1992)","DOI":"10.1007\/978-1-4612-4380-9_14"},{"key":"14_CR11","doi-asserted-by":"crossref","unstructured":"Hu, G., Lin, T.E., Zhao, Y., Lu, G., Wu, Y., Li, Y.: UniMSE: towards unified multimodal sentiment analysis and emotion recognition. In: Conference on Empirical Methods in Natural Language Processing, pp. 7837\u20137851 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"14_CR12","doi-asserted-by":"crossref","unstructured":"Huang, X., Peng, Y.: Deep cross-media knowledge transfer. In: IEEE Conference on Computer Vision and Pattern Recognition, pp. 8837\u20138846 (2018)","DOI":"10.1109\/CVPR.2018.00921"},{"key":"14_CR13","first-page":"10944","volume":"34","author":"Y Huang","year":"2021","unstructured":"Huang, Y., Du, C., Xue, Z., Chen, X., Zhao, H., Huang, L.: What makes multi-modal learning better than single (provably). Adv. Neural. Inf. Process. Syst. 34, 10944\u201310956 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"14_CR14","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: North American Chapter of the Association for Computational Linguistics, vol. 1, pp. 4171\u20134186 (2019)"},{"key":"14_CR15","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. In: International Conference on Learning Representations, pp. 1\u20138 (2015)"},{"key":"14_CR16","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, Y., Cui, Z.: Decoupled multimodal distilling for emotion recognition. In: IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6631\u20136640 (2023)","DOI":"10.1109\/CVPR52729.2023.00641"},{"key":"14_CR17","doi-asserted-by":"crossref","unstructured":"Majumder, N., Poria, S., Hazarika, D., Mihalcea, R., Gelbukh, A., Cambria, E.: DialogueRNN: an attentive RNN for emotion detection in conversations. In: AAAI Conference on Artificial Intelligence, vol. 33, pp. 6818\u20136825 (2019)","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"14_CR18","doi-asserted-by":"crossref","unstructured":"Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., Manocha, D.: M3ER: multiplicative multimodal emotion recognition using facial, textual, and speech cues. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 1359\u20131367 (2020)","DOI":"10.1609\/aaai.v34i02.5492"},{"key":"14_CR19","unstructured":"Poria, S., Hazarika, D., Majumder, N., Mihalcea, R.: Beneath the tip of the iceberg: current challenges and new directions in sentiment analysis research. IEEE Trans. Affect. Comput. (2020)"},{"key":"14_CR20","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: Annual Meeting of the Association for Computational Linguistics, pp. 2359\u20132369 (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"14_CR21","doi-asserted-by":"crossref","unstructured":"Sun, Z., Sarma, P., Sethares, W., Liang, Y.: Learning relationships between text, audio, and video via deep canonical correlation for multimodal language analysis. In: AAAI Conference on Artificial Intelligence, vol. 34, pp. 8992\u20138999 (2020)","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"14_CR22","doi-asserted-by":"crossref","unstructured":"Tishby, N., Zaslavsky, N.: Deep learning and the information bottleneck principle. In: IEEE Information Theory Workshop, pp. 1\u20135 (2015)","DOI":"10.1109\/ITW.2015.7133169"},{"key":"14_CR23","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"14_CR24","doi-asserted-by":"crossref","unstructured":"Wang, Y., et al.: A systematic review on affective computing: emotion models, databases, and recent advances. Inf. Fusion 83\u201384, 19\u201352 (2022)","DOI":"10.1016\/j.inffus.2022.03.009"},{"key":"14_CR25","doi-asserted-by":"crossref","unstructured":"Yang, D., Huang, S., Kuang, H., Du, Y., Zhang, L.: Disentangled representation learning for multimodal emotion recognition. In: ACM International Conference on Multimedia, pp. 1642\u20131651 (2022)","DOI":"10.1145\/3503161.3547754"},{"key":"14_CR26","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Yuan, Z., Wu, J.: Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. In: AAAI Conference on Artificial Intelligence, vol. 35, pp. 10790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"14_CR27","unstructured":"Zadeh, A., Zellers, R., Pincus, E., Morency, L.P.: MOSI: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv preprint arXiv:1606.06259 (2016)"},{"key":"14_CR28","doi-asserted-by":"crossref","unstructured":"Zhang, Y., Chen, M., Shen, J., Wang, C.: Tailor versatile multi-modal learning for multi-label emotion recognition. In: AAAI Conference on Artificial Intelligence. vol. 36, pp. 9100\u20139108 (2022)","DOI":"10.1609\/aaai.v36i8.20895"},{"key":"14_CR29","doi-asserted-by":"crossref","unstructured":"Zhou, Y., Liang, X., Zheng, S., Xuan, H., Kumada, T.: Adaptive mask co-optimization for modal dependence in multimodal learning. In: IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135. IEEE (2023)","DOI":"10.1109\/ICASSP49357.2023.10096641"}],"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\/978-981-99-8540-1_14","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,12,24]],"date-time":"2023-12-24T18:03:27Z","timestamp":1703441007000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-8540-1_14"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023,12,25]]},"ISBN":["9789819985395","9789819985401"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-8540-1_14","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2023,12,25]]},"assertion":[{"value":"25 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)"}}]}}