{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,11,15]],"date-time":"2026-11-15T14:02:23Z","timestamp":1794751343123,"version":"4.9.1"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819959709","type":"print"},{"value":"9789819959716","type":"electronic"}],"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\/978-981-99-5971-6_21","type":"book-chapter","created":{"date-parts":[[2023,9,14]],"date-time":"2023-09-14T19:04:42Z","timestamp":1694718282000},"page":"285-303","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Modal Interactive Feature Encoder for Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Xiaowei","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jie","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xiujuan","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2023,9,15]]},"reference":[{"key":"21_CR1","doi-asserted-by":"crossref","unstructured":"Bronstein, M.M., Bronstein, A.M., Michel, E.: Data fusion through cross-modality metric learning using similarity-sensitive hashing. In: CVPR, pp. 3594\u20133601 (2010)","DOI":"10.1109\/CVPR.2010.5539928"},{"key":"21_CR2","doi-asserted-by":"crossref","unstructured":"Peters, M.E., Neumann, M., Iyyer, M.: Deep contextualized word representations. In: NAACL (2018)","DOI":"10.18653\/v1\/N18-1202"},{"key":"21_CR3","unstructured":"Radford, A., Narasimhan, K., Salimans, T.: In: Improving language understanding by generative pre-training (2018)"},{"key":"21_CR4","unstructured":"Devlin, J., Chang, M.W., Lee, K.: Bert: Pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"21_CR5","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S.: Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"21_CR6","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B.: Efficient low-rank multimodal fusion with modality-specific factors. arXiv preprint arXiv:1806.00064 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"21_CR7","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Mazumder, N.: Memory fusion network for multi-view sequential learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32(1), (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"21_CR8","unstructured":"Zadeh, A.A.B., Liang, P.P., Poria, S.: 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)"},{"key":"21_CR9","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai. S., Liang. P.P.: Multimodal Transformer for unaligned multimodal language sequences. In: Proceedings of the Conference. Association for Computational Linguistics. Meeting. NIH Public Accessm vol. 2019, p. 6558 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"21_CR10","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":"21_CR11","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Yuan, Z.: Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. arXiv preprint arXiv:2102.04830 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"issue":"11","key":"21_CR12","first-page":"3201","volume":"35","author":"J He","year":"2018","unstructured":"He, J., Liu, Y., He, Z.: Research progress in multimodal emotion recognition. Appli. Res. Comput. 35(11), 3201\u20133205 (2018)","journal-title":"Appli. Res. Comput."},{"key":"21_CR13","doi-asserted-by":"crossref","unstructured":"Morency, L.P., Mihalcea, R., Doshi, P.: Towards multimodal sentiment analysis: Harvesting opinions from the web. In: Proceedings of the 13th International Conference on Multimodal Interfaces, pp. 169\u2013176 (2011)","DOI":"10.1145\/2070481.2070509"},{"key":"21_CR14","doi-asserted-by":"crossref","unstructured":"Poria S, Cambria E, Hazarika D.: Context-dependent sentiment analysis in user-generated videos. In: Proceedings of the 55th annual meeting of the association for computational linguistics, Volume 1: Long papers, pp. 873\u2013883 (2017)","DOI":"10.18653\/v1\/P17-1081"},{"key":"21_CR15","doi-asserted-by":"crossref","unstructured":"Chen, M., Wang, S,, Liang, P.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":"21_CR16","doi-asserted-by":"publisher","first-page":"124","DOI":"10.1016\/j.knosys.2018.07.041","volume":"161","author":"N Majumder","year":"2018","unstructured":"Majumder, N., Hazarika, D., Gelbukh, A.: Multimodal sentiment analysis using hierarchical fusion with context modeling. Knowl.-Based Syst. 161, 124\u2013133 (2018)","journal-title":"Knowl.-Based Syst."},{"key":"21_CR17","doi-asserted-by":"publisher","first-page":"429","DOI":"10.1109\/TASLP.2019.2957872","volume":"28","author":"J Yu","year":"2019","unstructured":"Yu, J., Jiang, J., Xia, R.: Entity-sensitive attention and fusion network for entity-level multimodal sentiment classification. IEEE\/ACM Trans, Audio, Speech,\u00a0 Language Process. 28, 429\u2013439 (2019)","journal-title":"IEEE\/ACM Trans, Audio, Speech,\u00a0 Language Process."},{"key":"21_CR18","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Poria, S.: Multi-attention recurrent network for human communication comprehension. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32(1) (2018)","DOI":"10.1609\/aaai.v32i1.12024"},{"issue":"2","key":"21_CR19","doi-asserted-by":"publisher","first-page":"103","DOI":"10.1007\/s13735-019-00185-8","volume":"9","author":"MG Huddar","year":"2020","unstructured":"Huddar, M.G., Sannakki, S.S., Rajpurohit, V.S.: Multi-level context extraction and attention-based contextual inter-modal fusion for multimodal sentiment analysis and emotion classification. Inter. J. Multimedia Inform. Retrieval 9(2), 103\u2013112 (2020)","journal-title":"Inter. J. Multimedia Inform. Retrieval"},{"key":"21_CR20","unstructured":"Baevski, A., Zhou, Y., Mohamed, A.: wav2vec 2.0: A framework for self-supervised learning of speech representations. In: Advances in Neural Information Processing Systems 33, 12449\u201312460 (2020)"},{"issue":"146","key":"21_CR21","first-page":"10","volume":"2006","author":"S Tomar","year":"2006","unstructured":"Tomar, S.: Converting video formats with FFmpeg. Linux J. 2006(146), 10 (2006)","journal-title":"Linux J."},{"issue":"10","key":"21_CR22","doi-asserted-by":"publisher","first-page":"1499","DOI":"10.1109\/LSP.2016.2603342","volume":"23","author":"K Zhang","year":"2016","unstructured":"Zhang, K., Zhang, Z., Li, Z.: Joint face detection and alignment using multi-task cascaded convolutional networks. IEEE Signal Process. Lett. 23(10), 1499\u20131503 (2016)","journal-title":"IEEE Signal Process. Lett."},{"key":"21_CR23","doi-asserted-by":"crossref","unstructured":"Baltrusaitis, T., Zadeh, A., Lim, Y.C.: Openface 2.0: Facial behavior analysis toolkit. In: 2018 13th IEEE international Conference on Automatic Face & Gesture Recognition (FG 2018), pp. 59\u201366.\u00a0IEEE (2018)","DOI":"10.1109\/FG.2018.00019"},{"key":"21_CR24","doi-asserted-by":"crossref","unstructured":"Yu W, Xu H, Meng F.: Ch-sims: a Chinese multimodal sentiment analysis dataset with fine-grained annotation of modality. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics, pp. 3718\u20133727 (2020)","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"21_CR25","unstructured":"Zadeh A, Zellers R, Pincus E.: Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv preprint arXiv:1606.06259 (2016)"},{"key":"21_CR26","doi-asserted-by":"crossref","unstructured":"Williams, J., Kleinegesse, S., Comanescu, R.: Recognizing emotions in video using multimodal dnn feature fusion. In: Proceedings of Grand Challenge and Workshop on Human Multimodal Language (Challenge-HML), pp. 11\u201319 (2018)","DOI":"10.18653\/v1\/W18-3302"},{"key":"21_CR27","doi-asserted-by":"crossref","unstructured":"Sun, Z., Sarma, P., Sethares, W.: 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(05), pp. 8992\u20138999 (2020)","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"21_CR28","doi-asserted-by":"crossref","unstructured":"Rahman, W., Hasan, M.K., Lee, S.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the conference. Association for Computational Linguistics. Meeting. NIH Public Access (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"21_CR29","unstructured":"Yang, Z., Dai, Z., Yang, Y.: Xlnet: Generalized autoregressive pretraining for language understanding. In: Advances in Neural Information Processing Systems 32 (2019)"},{"key":"21_CR30","doi-asserted-by":"crossref","unstructured":"Han. W., Chen, H., Poria, S.: Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. arXiv preprint arXiv: 2109.00412 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"21_CR31","unstructured":"Van der Maaten, L., Hinton, G.: Visualizing data using t-SNE. J. Mach. Learn. Res. 9(11) (2008)"}],"container-title":["Communications in Computer and Information Science","Data Science"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-5971-6_21","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T11:35:56Z","timestamp":1710243356000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-5971-6_21"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2023]]},"ISBN":["9789819959709","9789819959716"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-5971-6_21","relation":{"is-part-of":[{"id-type":"doi","id":"https:\/\/doi.org\/10.1007\/978-981-99-5971-6","asserted-by":"object"}]},"ISSN":["1865-0929","1865-0937"],"issn-type":[{"value":"1865-0929","type":"print"},{"value":"1865-0937","type":"electronic"}],"subject":[],"published":{"date-parts":[[2023]]},"assertion":[{"value":"15 September 2023","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPCSEE","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference of Pioneering Computer Scientists, Engineers and Educators","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Harbin","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":"22 September 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 September 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icpcsee2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/2023.icpcsee.org\/","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":"Easychair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"244","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":"52","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":"14","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":"21% - 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":"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)"}}]}}