{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T17:39:34Z","timestamp":1775324374582,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533923","type":"print"},{"value":"9789819533930","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,1]],"date-time":"2025-11-01T00:00:00Z","timestamp":1761955200000},"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":[[2026]]},"DOI":"10.1007\/978-981-95-3393-0_8","type":"book-chapter","created":{"date-parts":[[2025,10,31]],"date-time":"2025-10-31T09:49:57Z","timestamp":1761904197000},"page":"92-104","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Feature Decoupling with\u00a0Modality Modulation for\u00a0Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Yongbo","family":"Wang","sequence":"first","affiliation":[]},{"given":"Jiaxiang","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Aihua","family":"Zheng","sequence":"additional","affiliation":[]},{"given":"Wenjuan","family":"Cheng","sequence":"additional","affiliation":[]},{"given":"Xiaofei","family":"Sheng","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,1]]},"reference":[{"key":"8_CR1","doi-asserted-by":"crossref","unstructured":"Baltru\u0161aitis, T., Robinson, P., Morency, L.P.: OpenFace: an open source facial behavior analysis toolkit. In: Proceedings of the IEEE Winter Conference on Applications of Computer Vision, pp. 1\u201310 (2016)","DOI":"10.1109\/WACV.2016.7477553"},{"key":"8_CR2","unstructured":"Dai, W., et al.: MinD: improving multimodal sentiment analysis via multimodal information disentanglement. arXiv preprint arXiv:2401.11818 (2024)"},{"key":"8_CR3","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: Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 960\u2013964 (2014)","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"8_CR4","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1016\/j.inffus.2022.09.025","volume":"91","author":"A Gandhi","year":"2023","unstructured":"Gandhi, A., Adhvaryu, K., Poria, S., Cambria, E., Hussain, A.: Multimodal sentiment analysis: a systematic review of history, datasets, multimodal fusion methods, applications, challenges and future directions. Info. Fusion 91, 424\u2013444 (2023)","journal-title":"Info. Fusion"},{"key":"8_CR5","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 ACM International Conference on Multimedia, pp. 1122\u20131131 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"8_CR6","unstructured":"Kenton, J.D.M.W.C., Toutanova, L.K.: BERT: pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the Association for Computational Linguistics: Human Language Technologies, vol.\u00a01, pp. 4171\u20134186 (2019)"},{"key":"8_CR7","doi-asserted-by":"crossref","unstructured":"Li, Y., Wang, Y., Cui, Z.: Decoupled multimodal distilling for emotion recognition. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 6631\u20136640 (2023)","DOI":"10.1109\/CVPR52729.2023.00641"},{"issue":"2","key":"8_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.ipm.2022.103229","volume":"60","author":"H Lin","year":"2023","unstructured":"Lin, H., Zhang, P., Ling, J., Yang, Z., Lee, L.K., Liu, W.: PS-Mixer: a polar-vector and strength-vector mixer model for multimodal sentiment analysis. Info. Process. Manag. 60(2), 103229 (2023)","journal-title":"Info. Process. Manag."},{"key":"8_CR9","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. In: Proceedings of the Annual Meeting of the Association for Computational Linguistics, pp. 2247\u20132256 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"key":"8_CR10","doi-asserted-by":"crossref","unstructured":"Peng, X., Wei, Y., Deng, A., Wang, D., Hu, D.: Balanced multimodal learning via on-the-fly gradient modulation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 8238\u20138247 (2022)","DOI":"10.1109\/CVPR52688.2022.00806"},{"key":"8_CR11","doi-asserted-by":"crossref","unstructured":"Siriwardhana, S., Reis, A., Weerasekera, R., Nanayakkara, S.: Jointly fine-tuning \"BERT-like\" self supervised models to improve multimodal speech emotion recognition. In: Proceedings of the Annual Conference of the International Speech Communication Association, pp. 3755\u20133759 (2020)","DOI":"10.21437\/Interspeech.2020-1212"},{"key":"8_CR12","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.\u00a034, pp. 8992\u20138999 (2020)","DOI":"10.1609\/aaai.v34i05.6431"},{"key":"8_CR13","doi-asserted-by":"crossref","unstructured":"Tan, Q., Shen, X., Bai, Z., Sun, Y.: Cross-modality fused graph convolutional network for image-text sentiment analysis. In: International Conference on Image and Graphics, pp. 397\u2013411 (2023)","DOI":"10.1007\/978-3-031-46314-3_32"},{"key":"8_CR14","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.\u00a02019, p.\u00a06558 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"8_CR15","unstructured":"Tsai, Y.H.H., Liang, P.P., Zadeh, A., Morency, L.P., Salakhutdinov, R.: Learning factorized multimodal representations. In: Proceedings of the International Conference on Learning Representations (2019)"},{"issue":"6","key":"8_CR16","first-page":"282","volume":"2","author":"G Vinodhini","year":"2012","unstructured":"Vinodhini, G., Chandrasekaran, R.: Sentiment analysis and opinion mining: a survey. Int. J. 2(6), 282\u2013292 (2012)","journal-title":"Int. J."},{"key":"8_CR17","doi-asserted-by":"crossref","unstructured":"Wang, W., Tran, D., Feiszli, M.: What makes training multi-modal classification networks hard? In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 12695\u201312705 (2020)","DOI":"10.1109\/CVPR42600.2020.01271"},{"key":"8_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, vol.\u00a033, pp. 7216\u20137223 (2019)","DOI":"10.1609\/aaai.v33i01.33017216"},{"issue":"7","key":"8_CR19","doi-asserted-by":"publisher","first-page":"5731","DOI":"10.1007\/s10462-022-10144-1","volume":"55","author":"M Wankhade","year":"2022","unstructured":"Wankhade, M., Rao, A.C.S., Kulkarni, C.: A survey on sentiment analysis methods, applications, and challenges. Artif. Intell. Rev. 55(7), 5731\u20135780 (2022)","journal-title":"Artif. Intell. Rev."},{"key":"8_CR20","doi-asserted-by":"crossref","unstructured":"Wei, Y., Li, S., Feng, R., Hu, D.: Diagnosing and re-learning for balanced multimodal learning. In: Proceedings of the European Conference on Computer Vision, pp. 71\u201386 (2025)","DOI":"10.1007\/978-3-031-73039-9_5"},{"key":"8_CR21","doi-asserted-by":"crossref","unstructured":"Xu, W., Jiang, H., Liang, X.: Leveraging knowledge of modality experts for incomplete multimodal learning. In: Proceedings of the ACM International Conference on Multimedia, pp. 438\u2013446 (2024)","DOI":"10.1145\/3664647.3681683"},{"key":"8_CR22","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 ACM International Conference on Multimedia, pp. 1642\u20131651 (2022)","DOI":"10.1145\/3503161.3547754"},{"key":"8_CR23","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.\u00a035, pp. 10790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"8_CR24","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 Conference on Empirical Methods in Natural Language Processing, pp. 1103\u20131114 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"issue":"6","key":"8_CR25","doi-asserted-by":"publisher","first-page":"82","DOI":"10.1109\/MIS.2016.94","volume":"31","author":"A Zadeh","year":"2016","unstructured":"Zadeh, A., Zellers, R., Pincus, E., Morency, L.P.: Multimodal sentiment intensity analysis in videos: facial gestures and verbal messages. IEEE Intell. Syst. 31(6), 82\u201388 (2016)","journal-title":"IEEE Intell. Syst."},{"key":"8_CR26","doi-asserted-by":"crossref","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 Annual Meeting of the Association for Computational Linguistics, pp. 2236\u20132246 (2018)","DOI":"10.18653\/v1\/P18-1208"},{"key":"8_CR27","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)"}],"container-title":["Lecture Notes in Computer Science","Image and Graphics"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3393-0_8","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,4,4]],"date-time":"2026-04-04T16:29:14Z","timestamp":1775320154000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3393-0_8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,1]]},"ISBN":["9789819533923","9789819533930"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3393-0_8","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,1]]},"assertion":[{"value":"1 November 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIG","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Image and Graphics","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Xuzhou","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":"2025","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"31 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icig2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/icig.csig.org.cn\/2025\/index.html","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}