{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:53:01Z","timestamp":1763196781741,"version":"3.45.0"},"publisher-location":"Singapore","reference-count":27,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819533480","type":"print"},{"value":"9789819533497","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,16]],"date-time":"2025-11-16T00:00:00Z","timestamp":1763251200000},"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\/978-981-95-3349-7_46","type":"book-chapter","created":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:49:37Z","timestamp":1763196577000},"page":"602-614","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["MAGI: Modality-Aligned Geometry-Aware Integration for Robust Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0009-0008-2439-4952","authenticated-orcid":false,"given":"Bohan","family":"Hu","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0009-0006-6524-7436","authenticated-orcid":false,"given":"Yuhang","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,11,16]]},"reference":[{"issue":"12","key":"46_CR1","doi-asserted-by":"publisher","first-page":"8703","DOI":"10.1109\/TCSVT.2022.3197420","volume":"32","author":"R Chen","year":"2022","unstructured":"Chen, R., Zhou, W., Li, Y., Zhou, H.: Video-based cross-modal auxiliary network for multimodal sentiment analysis. IEEE Trans. Circuits Syst. Video Technol. 32(12), 8703\u20138716 (2022)","journal-title":"IEEE Trans. Circuits Syst. Video Technol."},{"key":"46_CR2","doi-asserted-by":"crossref","unstructured":"Chudasama, V., Kar, P., Gudmalwar, A., Shah, N., Wasnik, P., Onoe, N.: M2FNet: multi-modal fusion network for emotion recognition in conversation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 4652\u20134661 (2022)","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"46_CR3","unstructured":"Cicchetti, G., Grassucci, E., Sigillo, L., Comminiello, D.: Gramian multimodal representation learning and alignment. arXiv preprint arXiv:2412.11959 (2024)"},{"key":"46_CR4","doi-asserted-by":"publisher","first-page":"102306","DOI":"10.1016\/j.inffus.2024.102306","volume":"106","author":"C Fan","year":"2024","unstructured":"Fan, C., Lin, J., Mao, R., Cambria, E.: Fusing pairwise modalities for emotion recognition in conversations. Inf. Fus. 106, 102306 (2024)","journal-title":"Inf. Fus."},{"key":"46_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 28th ACM International Conference on Multimedia, pp. 1122\u20131131 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"46_CR6","doi-asserted-by":"crossref","unstructured":"Kuhnke, F., Rumberg, L., Ostermann, J.: Two-stream aural-visual affect analysis in the wild. In: 2020 15th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2020), pp. 600\u2013605. IEEE (2020)","DOI":"10.1109\/FG47880.2020.00056"},{"issue":"1","key":"46_CR7","doi-asserted-by":"publisher","first-page":"102141","DOI":"10.1016\/j.ipm.2019.102141","volume":"57","author":"A Kumar","year":"2020","unstructured":"Kumar, A., Srinivasan, K., Cheng, W.H., Zomaya, A.Y.: Hybrid context enriched deep learning model for fine-grained sentiment analysis in textual and visual semiotic modality social data. Inf. Process. Manag. 57(1), 102141 (2020)","journal-title":"Inf. Process. Manag."},{"issue":"2","key":"46_CR8","first-page":"19","volume":"3","author":"S Kumar","year":"2024","unstructured":"Kumar, S., Rani, H.: Study of multimodal emotion recognition: integrating facial expressions, voice, and physiological signals for enhanced accuracy. GLIMPSE 3(2), 19\u201323 (2024)","journal-title":"GLIMPSE"},{"issue":"11","key":"46_CR9","doi-asserted-by":"publisher","first-page":"2069","DOI":"10.3390\/electronics13112069","volume":"13","author":"H Li","year":"2024","unstructured":"Li, H., Lu, Y., Zhu, H.: Multi-modal sentiment analysis based on image and text fusion based on cross-attention mechanism. Electronics 13(11), 2069 (2024)","journal-title":"Electronics"},{"key":"46_CR10","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"},{"key":"46_CR11","doi-asserted-by":"crossref","unstructured":"Li, Z., Tang, F., Zhao, M., Zhu, Y.: EmoCaps: emotion capsule based model for conversational emotion recognition. arXiv preprint arXiv:2203.13504 (2022)","DOI":"10.18653\/v1\/2022.findings-acl.126"},{"key":"46_CR12","doi-asserted-by":"publisher","first-page":"110008","DOI":"10.1016\/j.jneumeth.2023.110008","volume":"401","author":"K Lin","year":"2024","unstructured":"Lin, K., Zhang, L., Cai, J., Sun, J., Cui, W., Liu, G.: DSE-Mixer: a pure multilayer perceptron network for emotion recognition from EEG feature maps. J. Neurosci. Methods 401, 110008 (2024)","journal-title":"J. Neurosci. Methods"},{"key":"46_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.dsp.2023.104265","volume":"145","author":"F Liu","year":"2024","unstructured":"Liu, F., et al.: STP-MFM: semi-tensor product-based multi-modal factorized multilinear pooling for information fusion in sentiment analysis. Digital Sig. Process. 145, 104265 (2024)","journal-title":"Digital Sig. Process."},{"key":"46_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.bspc.2024.106620","volume":"96","author":"K Lu","year":"2024","unstructured":"Lu, K., Gu, Z., Qi, F., Sun, C., Guo, H., Sun, L.: CMLP-Net: a convolution-multilayer perceptron network for EEG-based emotion recognition. Biomed. Sig. Process. Control 96, 106620 (2024)","journal-title":"Biomed. Sig. Process. Control"},{"key":"46_CR15","doi-asserted-by":"crossref","unstructured":"Mu, G., Chen, C., Li, X., Li, J., Ju, X., Dai, J.: Multimodal sentiment analysis of government information comments based on contrastive learning and cross-attention fusion networks. IEEE Access (2024)","DOI":"10.1109\/ACCESS.2024.3493933"},{"key":"46_CR16","doi-asserted-by":"publisher","first-page":"172948","DOI":"10.1109\/ACCESS.2019.2955637","volume":"7","author":"S Nemati","year":"2019","unstructured":"Nemati, S., Rohani, R., Basiri, M.E., Abdar, M., Yen, N.Y., Makarenkov, V.: A hybrid latent space data fusion method for multimodal emotion recognition. IEEE Access 7, 172948\u2013172964 (2019)","journal-title":"IEEE Access"},{"key":"46_CR17","doi-asserted-by":"publisher","first-page":"0076","DOI":"10.34133\/icomputing.0076","volume":"3","author":"G Pei","year":"2024","unstructured":"Pei, G., Li, H., Lu, Y., Wang, Y., Hua, S., Li, T.: Affective computing: recent advances, challenges, and future trends. Intell. Comput. 3, 0076 (2024)","journal-title":"Intell. Comput."},{"issue":"11","key":"46_CR18","doi-asserted-by":"publisher","first-page":"6965","DOI":"10.1109\/TCSVT.2023.3273577","volume":"33","author":"M Ren","year":"2023","unstructured":"Ren, M., Huang, X., Liu, J., Liu, M., Li, X., Liu, A.A.: MALN: multimodal adversarial learning network for conversational emotion recognition. IEEE Trans. Circ. Syst. Video Technol. 33(11), 6965\u20136980 (2023)","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"46_CR19","first-page":"48875","volume":"37","author":"R Shi","year":"2024","unstructured":"Shi, R., et al.: Decoding-time language model alignment with multiple objectives. Adv. Neural. Inf. Process. Syst. 37, 48875\u201348920 (2024)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"issue":"9","key":"46_CR20","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3652149","volume":"56","author":"U Singh","year":"2024","unstructured":"Singh, U., Abhishek, K., Azad, H.K.: A survey of cutting-edge multimodal sentiment analysis. ACM Comput. Surv. 56(9), 1\u201338 (2024)","journal-title":"ACM Comput. Surv."},{"issue":"1","key":"46_CR21","doi-asserted-by":"publisher","first-page":"1989706","DOI":"10.1155\/2024\/1989706","volume":"2024","author":"C Wang","year":"2024","unstructured":"Wang, C., Hu, W., Wang, J., Qian, P., Wang, S.: Consistency and complementarity jointly regularized subspace support vector data description for multimodal data. Int. J. Intell. Syst. 2024(1), 1989706 (2024)","journal-title":"Int. J. Intell. Syst."},{"issue":"3","key":"46_CR22","first-page":"2430","volume":"35","author":"H Wang","year":"2021","unstructured":"Wang, H., Lian, D., Tong, H., Liu, Q., Huang, Z., Chen, E.: Decoupled representation learning for attributed networks. IEEE Trans. Knowl. Data Eng. 35(3), 2430\u20132444 (2021)","journal-title":"IEEE Trans. Knowl. Data Eng."},{"key":"46_CR23","doi-asserted-by":"crossref","unstructured":"Wang, X., Chen, H., Tang, S., Wu, Z., Zhu, W.: Disentangled representation learning. IEEE Trans. Pattern Anal. Mach. Intell. (2024)","DOI":"10.1109\/TPAMI.2024.3420937"},{"key":"46_CR24","doi-asserted-by":"crossref","unstructured":"Xu, N., Mao, W., Chen, G.: A co-memory network for multimodal sentiment analysis. In: The 41st International ACM SIGIR Conference on Research & Development in Information Retrieval, pp. 929\u2013932 (2018)","DOI":"10.1145\/3209978.3210093"},{"issue":"6","key":"46_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":"46_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 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2236\u20132246 (2018)","DOI":"10.18653\/v1\/P18-1208"},{"key":"46_CR27","doi-asserted-by":"crossref","unstructured":"Zhao, K., Zheng, M., Li, Q., Liu, J.: Multimodal sentiment analysis-a comprehensive survey from a fusion methods perspective. IEEE Access (2025)","DOI":"10.1109\/ACCESS.2025.3554665"}],"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\/978-981-95-3349-7_46","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,11,15]],"date-time":"2025-11-15T08:49:39Z","timestamp":1763196579000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3349-7_46"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,16]]},"ISBN":["9789819533480","9789819533497"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3349-7_46","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,16]]},"assertion":[{"value":"16 November 2025","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":"Urumqi","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":"7 August 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9 August 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2025\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}