{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:23:38Z","timestamp":1778693018554,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819991181","type":"print"},{"value":"9789819991198","type":"electronic"}],"license":[{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,1]],"date-time":"2024-01-01T00:00:00Z","timestamp":1704067200000},"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\/978-981-99-9119-8_18","type":"book-chapter","created":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T13:03:04Z","timestamp":1706878984000},"page":"189-200","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":26,"title":["Text-Oriented Modality Reinforcement Network for\u00a0Multimodal Sentiment Analysis from\u00a0Unaligned Multimodal Sequences"],"prefix":"10.1007","author":[{"given":"Yuxuan","family":"Lei","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Dingkang","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Mingcheng","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Shunli","family":"Wang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jiawei","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Lihua","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,2,3]]},"reference":[{"key":"18_CR1","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":"18_CR2","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: BERT: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"18_CR3","doi-asserted-by":"crossref","unstructured":"Du, Y., Yang, D., Zhai, P., Li, M., Zhang, L.: Learning associative representation for facial expression recognition. In: IEEE International Conference on Image Processing, pp. 889\u2013893 (2021)","DOI":"10.1109\/ICIP42928.2021.9506181"},{"key":"18_CR4","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"},{"issue":"8","key":"18_CR5","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"18_CR6","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"key":"18_CR7","doi-asserted-by":"crossref","unstructured":"Liang, T., Lin, G., Feng, L., Zhang, Y., Lv, F.: Attention is not enough: mitigating the distribution discrepancy in asynchronous multimodal sequence fusion. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 8148\u20138156 (2021)","DOI":"10.1109\/ICCV48922.2021.00804"},{"key":"18_CR8","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":"18_CR9","doi-asserted-by":"crossref","unstructured":"Lv, F., Chen, X., Huang, Y., Duan, L., Lin, G.: Progressive modality reinforcement for human multimodal emotion recognition from unaligned multimodal sequences. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 2554\u20132562 (2021)","DOI":"10.1109\/CVPR46437.2021.00258"},{"key":"18_CR10","doi-asserted-by":"crossref","unstructured":"Mittal, T., Guhan, P., Bhattacharya, U., Chandra, R., Bera, A., Manocha, D.: EmotiCon: context-aware multimodal emotion recognition using Frege\u2019s principle. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14234\u201314243 (2020)","DOI":"10.1109\/CVPR42600.2020.01424"},{"key":"18_CR11","unstructured":"Paszke, A., et al.: PyTorch: an imperative style, high-performance deep learning library. In: Advances in Neural Information Processing Systems, vol. 32 (2019)"},{"key":"18_CR12","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the Conference Association for Computational Linguistics. Meeting, vol. 2020, p. 2359. NIH Public Access (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"18_CR13","doi-asserted-by":"crossref","unstructured":"Strubell, E., Verga, P., Andor, D., Weiss, D., McCallum, A.: Linguistically-informed self-attention for semantic role labeling. arXiv preprint arXiv:1804.08199 (2018)","DOI":"10.18653\/v1\/D18-1548"},{"key":"18_CR14","doi-asserted-by":"crossref","unstructured":"Tang, G., M\u00fcller, M., Rios, A., Sennrich, R.: Why self-attention? A targeted evaluation of neural machine translation architectures. arXiv preprint arXiv:1808.08946 (2018)","DOI":"10.18653\/v1\/D18-1458"},{"key":"18_CR15","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the Conference Association for Computational Linguistics. Meeting, vol. 2019, p. 6558. NIH Public Access (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"18_CR16","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":"18_CR17","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, vol. 30 (2017)"},{"key":"18_CR18","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, pp. 7216\u20137223 (2019)","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"18_CR19","doi-asserted-by":"crossref","unstructured":"Wu, Y., Lin, Z., Zhao, Y., Qin, B., Zhu, L.N.: A text-centered shared-private framework via cross-modal prediction for multimodal sentiment analysis. In: Findings of the Association for Computational Linguistics: ACL-IJCNLP 2021, pp. 4730\u20134738 (2021)","DOI":"10.18653\/v1\/2021.findings-acl.417"},{"key":"18_CR20","doi-asserted-by":"crossref","unstructured":"Yang, D., et al.: Context de-confounded emotion recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 19005\u201319015, June 2023","DOI":"10.1109\/CVPR52729.2023.01822"},{"key":"18_CR21","doi-asserted-by":"crossref","unstructured":"Yang, D., Huang, S., Kuang, H., Du, Y., Zhang, L.: Disentangled representation learning for multimodal emotion recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1642\u20131651 (2022)","DOI":"10.1145\/3503161.3547754"},{"key":"18_CR22","doi-asserted-by":"publisher","first-page":"2093","DOI":"10.1109\/LSP.2022.3210836","volume":"29","author":"D Yang","year":"2022","unstructured":"Yang, D., Huang, S., Liu, Y., Zhang, L.: Contextual and cross-modal interaction for multi-modal speech emotion recognition. IEEE Signal Process. Lett. 29, 2093\u20132097 (2022)","journal-title":"IEEE Signal Process. Lett."},{"key":"18_CR23","doi-asserted-by":"publisher","unstructured":"Yang, D., et al.: Emotion recognition for multiple context awareness. In: Avidan, S., Brostow, G., Ciss\u00e9, M., Farinella, G.M., Hassner, T. (eds.) Proceedings of the European Conference on Computer Vision, vol. 13697, pp. 144\u2013162. Springer, Cham (2022). https:\/\/doi.org\/10.1007\/978-3-031-19836-6_9","DOI":"10.1007\/978-3-031-19836-6_9"},{"key":"18_CR24","doi-asserted-by":"crossref","unstructured":"Yang, D., Kuang, H., Huang, S., Zhang, L.: Learning modality-specific and -agnostic representations for asynchronous multimodal language sequences. In: Proceedings of the 30th ACM International Conference on Multimedia, pp. 1708\u20131717 (2022)","DOI":"10.1145\/3503161.3547755"},{"key":"18_CR25","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2023.110370","volume":"265","author":"D Yang","year":"2023","unstructured":"Yang, D., et al.: Target and source modality co-reinforcement for emotion understanding from asynchronous multimodal sequences. Knowl.-Based Syst. 265, 110370 (2023)","journal-title":"Knowl.-Based Syst."},{"key":"18_CR26","doi-asserted-by":"crossref","unstructured":"Yu, W., et al.: 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":"18_CR27","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, pp. 10790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"18_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":"18_CR29","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":"18_CR30","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, pp. 2236\u20132246 (2018)"}],"container-title":["Lecture Notes in Computer Science","Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-99-9119-8_18","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,2]],"date-time":"2024-02-02T13:06:14Z","timestamp":1706879174000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-99-9119-8_18"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024]]},"ISBN":["9789819991181","9789819991198"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-99-9119-8_18","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024]]},"assertion":[{"value":"3 February 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"CICAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CAAI International Conference on Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Fuzhou","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 July 2023","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 July 2023","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"cicai2023","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/cicai.caai.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":"CMT","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"376","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":"101","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":"16","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":"27% - 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":"2.9","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":"1.9","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)"}}]}}