{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T03:05:32Z","timestamp":1779419132304,"version":"3.53.1"},"publisher-location":"Singapore","reference-count":29,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819500086","type":"print"},{"value":"9789819500093","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-95-0009-3_23","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T13:24:38Z","timestamp":1753363478000},"page":"267-278","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Sentiment Perception from Tokens: A Multitask Learning Framework with Entropy-Driven Fusion"],"prefix":"10.1007","author":[{"given":"Jingshan","family":"Yan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ao","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Longwei","family":"Xu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Pengwei","family":"Wang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"23_CR1","unstructured":"Chen, Z., et al.: Internvl: scaling up vision foundation models and aligning for generic visual-linguistic tasks (2024). https:\/\/arxiv.org\/abs\/2312.14238"},{"key":"23_CR2","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding (2019). https:\/\/arxiv.org\/abs\/1810.04805"},{"key":"23_CR3","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":"23_CR4","unstructured":"He, K., Chen, X., Xie, S., Li, Y., Doll\u00e1r, P., Girshick, R.: Masked autoencoders are scalable vision learners (2021). https:\/\/arxiv.org\/abs\/2111.06377"},{"key":"23_CR5","doi-asserted-by":"publisher","first-page":"3451","DOI":"10.1109\/TASLP.2021.3122291","volume":"29","author":"WN Hsu","year":"2021","unstructured":"Hsu, W.N., Bolte, B., Tsai, Y.H.H., Lakhotia, K., Salakhutdinov, R., Mohamed, A.: Hubert: self-supervised speech representation learning by masked prediction of hidden units. IEEE\/ACM Trans. Audio Speech Lang. Process. 29, 3451\u20133460 (2021)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"23_CR6","doi-asserted-by":"crossref","unstructured":"Jiang, X., et al.: Dfew: a large scale database for recognizing dynamic facial expressions in the wild. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 2881\u20132889 (2020)","DOI":"10.1145\/3394171.3413620"},{"key":"23_CR7","unstructured":"Lei, S., Dong, G., Wang, X., Wang, K., Wang, S.: Instructerc: reforming emotion recognition in conversation with a retrieval multi-task llms framework. arXiv preprint arXiv:2309.11911 (2023)"},{"key":"23_CR8","doi-asserted-by":"crossref","unstructured":"Li, A., Xu, L., Ling, C., Zhang, J., Wang, P.: Emoverse: exploring multimodal large language models for sentiment and emotion understanding (2025). https:\/\/arxiv.org\/abs\/2412.0804912","DOI":"10.1016\/j.neucom.2025.130810"},{"key":"23_CR9","unstructured":"Liu, Y., et al.: Roberta: A robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"23_CR10","doi-asserted-by":"crossref","unstructured":"Ma, B., Zhang, W., Qiu, F., Ding, Y.: A unified approach to facial affect analysis: The mae-face visual representation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition (CVPR) Workshops, pp. 5924\u20135933 (2023)","DOI":"10.1109\/CVPRW59228.2023.00630"},{"issue":"6","key":"23_CR11","first-page":"2123","volume":"10","author":"Y Mao","year":"2019","unstructured":"Mao, Y., Xu, J., Zhang, L.: Weighted fusion of emotion recognition from text and speech. J. Ambient. Intell. Humaniz. Comput. 10(6), 2123\u20132133 (2019)","journal-title":"J. Ambient. Intell. Humaniz. Comput."},{"key":"23_CR12","unstructured":"Poria, S., Cambria, E., Huang, G.: Multimodal sentiment analysis using voting mechanism. In: 2017 International Joint Conference on Neural Networks (IJCNN), pp. 2460\u20132467. IEEE (2017)"},{"key":"23_CR13","doi-asserted-by":"publisher","unstructured":"Poria, S., et al.: Multimodal sentiment analysis: a review and a new model. IEEE Trans. Affect. Comput. 10(3), 360\u2013373 (2018). https:\/\/doi.org\/10.1109\/TAFFC.2018.2883277","DOI":"10.1109\/TAFFC.2018.2883277"},{"key":"23_CR14","unstructured":"Radford, A., et al.: Learning transferable visual models from natural language supervision (2021). https:\/\/arxiv.org\/abs\/2103.00020"},{"key":"23_CR15","doi-asserted-by":"publisher","unstructured":"Sharma, R., Le Tan, N., Sadat, F.: Multimodal sentiment analysis using deep learning. In: 2018 17th IEEE International Conference on Machine Learning and Applications (ICMLA), pp. 1475\u20131478 (2018). https:\/\/doi.org\/10.1109\/ICMLA.2018.00240","DOI":"10.1109\/ICMLA.2018.00240"},{"key":"23_CR16","doi-asserted-by":"crossref","unstructured":"Tong, Z., Song, Y., Wang, J., Wang, L.: Videomae: masked autoencoders are data-efficient learners for self-supervised video pre-training (2022). https:\/\/arxiv.org\/abs\/2203.12602","DOI":"10.52202\/068431-0732"},{"key":"23_CR17","doi-asserted-by":"publisher","unstructured":"Truong, Q.T., Lau, H.W.: Vistanet: visual aspect attention network for multimodal sentiment analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 305\u2013312 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.3301305","DOI":"10.1609\/aaai.v33i01.3301305"},{"key":"23_CR18","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 (2019). https:\/\/arxiv.org\/abs\/1906.00295","DOI":"10.18653\/v1\/P19-1656"},{"key":"23_CR19","doi-asserted-by":"crossref","unstructured":"Wang, Z., Wang, W., Zhu, H., Liu, M., Qin, B., Wei, F.: Distilled dual-encoder model for vision-language understanding. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 8901\u20138913. Association for Computational Linguistics, Abu Dhabi (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.608"},{"key":"23_CR20","doi-asserted-by":"crossref","unstructured":"Yang, K., Xu, H., Gao, K.: Cm-bert: cross-modal bert for text-audio sentiment analysis. In: Proceedings of the 28th ACM International Conference on Multimedia, pp. 521\u2013528 (2020)","DOI":"10.1145\/3394171.3413690"},{"key":"23_CR21","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Ziqi, Y., Jiele, W.: Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. In: Proceedings of the AAAI Conference on Artificial Intelligence (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"23_CR22","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. arXiv (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"23_CR23","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 Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence. AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"23_CR24","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 Thirty-Second AAAI Conference on Artificial Intelligence and Thirtieth Innovative Applications of Artificial Intelligence Conference and Eighth AAAI Symposium on Educational Advances in Artificial Intelligence. AAAI\u201918\/IAAI\u201918\/EAAI\u201918, AAAI Press (2018)","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"23_CR25","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":"23_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, vol. 1: Long Papers, pp. 2236\u20132246 (2018)","DOI":"10.18653\/v1\/P18-1208"},{"key":"23_CR27","unstructured":"Zhang, Y., Xu, S., Zhao, H.: Mag-bert: a graph neural network-based approach for multi-modal sentiment analysis. In: Proceedings of the 2020 Conference on Neural Information Processing Systems. NeurIPS (2020)"},{"key":"23_CR28","unstructured":"Zhang, Y., et al.: Video instruction tuning with synthetic data. arXiv preprint arXiv:2410.02713 (2024)"},{"key":"23_CR29","doi-asserted-by":"publisher","unstructured":"Zou, W., Ding, J., Wang, C.: Utilizing bert intermediate layers for multimodal sentiment analysis. In: 2022 IEEE International Conference on Multimedia and Expo (ICME), pp. 1\u20136 (2022). https:\/\/doi.org\/10.1109\/ICME52920.2022.9860014","DOI":"10.1109\/ICME52920.2022.9860014"}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0009-3_23","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,5,22]],"date-time":"2026-05-22T02:24:29Z","timestamp":1779416669000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0009-3_23"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500086","9789819500093"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0009-3_23","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"21","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}