{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,5,31]],"date-time":"2025-05-31T05:09:13Z","timestamp":1748668153420,"version":"3.40.3"},"publisher-location":"Cham","reference-count":34,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783031171192"},{"type":"electronic","value":"9783031171208"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-031-17120-8_44","type":"book-chapter","created":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T13:02:58Z","timestamp":1663938178000},"page":"564-576","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Unimodal and\u00a0Multimodal Integrated Representation Learning via\u00a0Improved Information Bottleneck for\u00a0Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Tonghui","family":"Zhang","sequence":"first","affiliation":[]},{"given":"Changfei","family":"Dong","sequence":"additional","affiliation":[]},{"given":"Jinsong","family":"Su","sequence":"additional","affiliation":[]},{"given":"Haiying","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Yuzheng","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2022,9,24]]},"reference":[{"key":"44_CR1","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 2359\u20132369 (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"issue":"2","key":"44_CR2","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2018","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"44_CR3","unstructured":"Belghazi, M.I., et al.: Mutual information neural estimation. In: International Conference on Machine Learning, pp. 531\u2013540. PMLR (2018)"},{"key":"44_CR4","doi-asserted-by":"crossref","unstructured":"Chen, M., Wang, S., Liang, P.P., Baltru\u0161aitis, T., Zadeh, A., Morency, L.P.: Multimodal sentiment analysis with word-level fusion and reinforcement learning. In: Proceedings of the 19th ACM International Conference on Multimodal Interaction, pp. 163\u2013171 (2017)","DOI":"10.1145\/3136755.3136801"},{"key":"44_CR5","unstructured":"Cheng, P., Hao, W., Dai, S., Liu, J., Gan, Z., Carin, L.: CLUB: a contrastive log-ratio upper bound of mutual information. In: Proceedings of the 37th International Conference on Machine Learning, pp. 1779\u20131788 (2020)"},{"key":"44_CR6","doi-asserted-by":"crossref","unstructured":"Colombo, P., Chapuis, E., Labeau, M., Clavel, C.: Improving multimodal fusion via mutual dependency maximisation. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 231\u2013245 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.21"},{"key":"44_CR7","doi-asserted-by":"crossref","unstructured":"Degottex, G., Kane, J., Drugman, T., Raitio, T., Scherer, S.: COVAREP-a collaborative voice analysis repository for speech technologies. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 960\u2013964. IEEE (2014)","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"44_CR8","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers), pp. 4171\u20134186 (2019)"},{"key":"44_CR9","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: Proceedings of the 2021 International Conference on Multimodal Interaction, pp. 6\u201315 (2021)","DOI":"10.1145\/3462244.3479919"},{"key":"44_CR10","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Poria, S.: Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp. 9180\u20139192 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"44_CR11","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":"44_CR12","unstructured":"Jaegle, A., Gimeno, F., Brock, A., Vinyals, O., Zisserman, A., Carreira, J.: Perceiver: general perception with iterative attention. In: International Conference on Machine Learning, pp. 4651\u20134664. PMLR (2021)"},{"key":"44_CR13","unstructured":"Khosla, P., et al.: Supervised contrastive learning. Adv. Neural. Inf. Process. Syst. 33, 18661\u201318673 (2020)"},{"key":"44_CR14","doi-asserted-by":"crossref","unstructured":"Mai, S., Hu, H., Xing, S.: Modality to modality translation: an adversarial representation learning and graph fusion network for multimodal fusion. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 164\u2013172 (2020)","DOI":"10.1609\/aaai.v34i01.5347"},{"key":"44_CR15","doi-asserted-by":"crossref","unstructured":"Mai, S., Zeng, Y., Zheng, S., Hu, H.: Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis. IEEE Trans. Affective Comput. (2022)","DOI":"10.1109\/TAFFC.2022.3172360"},{"key":"44_CR16","unstructured":"McAllester, D., Stratos, K.: Formal limitations on the measurement of mutual information. In: International Conference on Artificial Intelligence and Statistics, pp. 875\u2013884. PMLR (2020)"},{"key":"44_CR17","first-page":"14200","volume":"34","author":"A Nagrani","year":"2021","unstructured":"Nagrani, A., Yang, S., Arnab, A., Jansen, A., Schmid, C., Sun, C.: Attention bottlenecks for multimodal fusion. Adv. Neural. Inf. Process. Syst. 34, 14200\u201314213 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"44_CR18","unstructured":"Oord, A.V.d., Li, Y., Vinyals, O.: Representation learning with contrastive predictive coding. arXiv preprint arXiv:1807.03748 (2018)"},{"key":"44_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":"44_CR20","doi-asserted-by":"crossref","unstructured":"Pham, H., Manzini, T., Liang, P.P., P\u00f3czos, B.: Seq2Seq2Sentiment: multimodal sequence to sequence models for sentiment analysis. In: Proceedings of Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML), pp. 53\u201363 (2018)","DOI":"10.18653\/v1\/W18-3308"},{"key":"44_CR21","unstructured":"Poole, B., Ozair, S., van den Oord, A., Alemi, A., Tucker, G.: On variational bounds of mutual information. In: ICML (2019)"},{"key":"44_CR22","unstructured":"Shankar, S.: Neural dependency coding inspired multimodal fusion. arXiv preprint arXiv:2110.00385 (2021)"},{"key":"44_CR23","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 8992\u20138999 (2020)","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"44_CR24","unstructured":"Tishby, N., Pereira, F.C., Bialek, W.: The information bottleneck method. arXiv preprint physics\/0004057 (2000)"},{"key":"44_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. Adv. Neural Inf. Process. Syst. 30 (2017)"},{"key":"44_CR26","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shen, Y., Liu, Z., Liang, P.P., Zadeh, A., Morency, L.P.: Words can shift: dynamically adjusting word representations using nonverbal behaviors. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 7216\u20137223 (2019)","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"44_CR27","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 2020, pp. 2514\u20132520 (2020)","DOI":"10.1145\/3366423.3380000"},{"key":"44_CR28","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: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 35, pp. 10790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"issue":"5","key":"44_CR29","doi-asserted-by":"publisher","first-page":"3878","DOI":"10.1121\/1.2935783","volume":"123","author":"J Yuan","year":"2008","unstructured":"Yuan, J., Liberman, M.: Speaker identification on the scotus corpus. J. Acoust. Soc. Am. Impact Factor 123(5), 3878 (2008)","journal-title":"J. Acoust. Soc. Am. Impact Factor"},{"key":"44_CR30","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. In: Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1103\u20131114 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"44_CR31","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Mazumder, N., Poria, S., Cambria, E., Morency, L.P.: Memory fusion network for multi-view sequential learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"44_CR32","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Poria, S., Vij, P., Cambria, E., Morency, L.P.: Multi-attention recurrent network for human communication comprehension. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"44_CR33","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":"44_CR34","unstructured":"Zadeh, A.B., 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: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2236\u20132246 (2018)"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-031-17120-8_44","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2022,9,23]],"date-time":"2022-09-23T13:08:56Z","timestamp":1663938536000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-031-17120-8_44"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783031171192","9783031171208"],"references-count":34,"URL":"https:\/\/doi.org\/10.1007\/978-3-031-17120-8_44","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"24 September 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Guilin","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":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"25 September 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"11","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2022","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2022\/","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":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"327","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":"73","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":"22% - 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":"1.5","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)"}}]}}