{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,10]],"date-time":"2026-07-10T15:20:47Z","timestamp":1783696847500,"version":"3.55.0"},"reference-count":27,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T00:00:00Z","timestamp":1705104000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T00:00:00Z","timestamp":1705104000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672190"],"award-info":[{"award-number":["61672190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672190"],"award-info":[{"award-number":["61672190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672190"],"award-info":[{"award-number":["61672190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"publisher","award":["61672190"],"award-info":[{"award-number":["61672190"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2024,2]]},"DOI":"10.1007\/s00530-023-01208-5","type":"journal-article","created":{"date-parts":[[2024,1,13]],"date-time":"2024-01-13T02:02:19Z","timestamp":1705111339000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":9,"title":["Balanced sentimental information via multimodal interaction model"],"prefix":"10.1007","volume":"30","author":[{"given":"Yuanyi","family":"Luo","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Rui","family":"Wu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jiafeng","family":"Liu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xianglong","family":"Tang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2024,1,13]]},"reference":[{"issue":"4","key":"1208_CR1","doi-asserted-by":"publisher","first-page":"479","DOI":"10.1007\/s00530-014-0407-8","volume":"22","author":"D Cao","year":"2016","unstructured":"Cao, D., Ji, R., Lin, D., et al.: A cross-media public sentiment analysis system for microblog. Multimed. Syst. 22(4), 479\u2013486 (2016)","journal-title":"Multimed. Syst."},{"issue":"31","key":"1208_CR2","doi-asserted-by":"publisher","first-page":"22935","DOI":"10.1007\/s00521-022-06913-2","volume":"35","author":"A Sharma","year":"2023","unstructured":"Sharma, A., Sharma, K., Kumar, A.: Real-time emotional health detection using fine-tuned transfer networks with multimodal fusion. Neural Comput. Appl. 35(31), 22935\u201348 (2023)","journal-title":"Neural Comput. Appl."},{"issue":"2","key":"1208_CR3","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aiitis","year":"2018","unstructured":"Baltru\u0161aiitis, T., Ahuja, C., Morency, L.P.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intel. 41(2), 423\u2013443 (2018)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intel."},{"key":"1208_CR4","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Meng, F., 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":"1208_CR5","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., et al.: Tensor fusion network for multimodal sentiment analysis (2017). arXiv:1707.07250","DOI":"10.18653\/v1\/D17-1115"},{"key":"1208_CR6","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., et al.: Efficient low-rank multimodal fusion with modality-specific factors (2018). arXiv:1806.00064","DOI":"10.18653\/v1\/P18-1209"},{"key":"1208_CR7","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Mazumder, N., et al.: Memory fusion network for multi-view sequential learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol 32, no 1 (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"1208_CR8","doi-asserted-by":"crossref","unstructured":"Ghosal, D., Akhtar, M.S., Chauhan, D., et al.: Contextual inter-modal attention for multi-modal sentiment analysis. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 3454\u20133466 (2018)","DOI":"10.18653\/v1\/D18-1382"},{"key":"1208_CR9","doi-asserted-by":"crossref","unstructured":"Long, X., Gan, C., Melo, G., et al.: Multimodal keyless attention fusion for video classification. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)","DOI":"10.1609\/aaai.v32i1.12319"},{"key":"1208_CR10","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Ma, M.Q., Yang, M., et al.: Multimodal routing: improving local and global interpretability of multimodal language analysis. In: Proceedings of the Conference on Empirical Methods in Natural Language Processing, p. 1823. NIH Public Access (2020)","DOI":"10.18653\/v1\/2020.emnlp-main.143"},{"key":"1208_CR11","doi-asserted-by":"crossref","unstructured":"Sahay, S., Kumar, S.H., Xia, R., et al.: Multimodal relational tensor network for sentiment and emotion classification (2018). arXiv:1806.02923","DOI":"10.18653\/v1\/W18-3303"},{"key":"1208_CR12","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., et al.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the Conference Association for Computational Linguistics Meeting, p. 6558. NIH Public Access (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"1208_CR13","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":"1208_CR14","doi-asserted-by":"crossref","unstructured":"Rahman, W., Hasan, M.K., Lee, S., et al.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the conference Association for Computational Linguistics Meeting, p. 2359. NIH Public Access (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"1208_CR15","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Yuan, Z., et al.: Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis (2021). arXiv:2102.04830","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"1208_CR16","doi-asserted-by":"crossref","unstructured":"Nam, H., Ha, J.W., Kim, J.: Dual attention networks for multimodal reasoning and matching. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp 299\u2013307 (2017)","DOI":"10.1109\/CVPR.2017.232"},{"key":"1208_CR17","unstructured":"Tsai, Y.H.H, Liang, P.P., Zadeh, A., et al.: Learning factorized multimodal representations (2018). arXiv:1806.06176"},{"key":"1208_CR18","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P.: Poria S, et al.: Multi-attention recurrent network for human communication comprehension. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32, no. 1 (2018)","DOI":"10.1609\/aaai.v32i1.12024"},{"issue":"10","key":"1208_CR19","doi-asserted-by":"publisher","first-page":"8241","DOI":"10.1007\/s00521-022-06903-4","volume":"34","author":"J Yang","year":"2022","unstructured":"Yang, J., Zhang, C., Tang, Y., et al.: PAFM: pose-drive attention fusion mechanism for occluded person re-identification. Neural Comput. Appl. 34(10), 8241\u20138252 (2022)","journal-title":"Neural Comput. Appl."},{"key":"1208_CR20","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1016\/j.neucom.2018.03.033","volume":"299","author":"C Zhang","year":"2018","unstructured":"Zhang, C., Li, Z., Wang, Z.: Joint compressive representation for multi-feature tracking. Neurocomputing 299, 32\u201341 (2018)","journal-title":"Neurocomputing"},{"key":"1208_CR21","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate (2014). arXiv:1409.0473"},{"issue":"4","key":"1208_CR22","doi-asserted-by":"publisher","first-page":"431","DOI":"10.1007\/s00530-020-00656-7","volume":"26","author":"A Yadav","year":"2020","unstructured":"Yadav, A., Vishwakarma, D.K.: A deep learning architecture of RA-DLNet for visual sentiment analysis. Multimed. Syst. 26(4), 431\u2013451 (2020)","journal-title":"Multimed. Syst."},{"key":"1208_CR23","unstructured":"Xu, K., Ba. J., Kiros. R., et al.: Show, attend and tell: neural image caption generation with visual attention. In: International Conference on Machine Learning. PMLR, pp. 2048\u20132057 (2015)"},{"key":"1208_CR24","doi-asserted-by":"crossref","unstructured":"Peng, X., Wei, Y., Deng, A., et al.: 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"},{"issue":"6","key":"1208_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., et al.: 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":"1208_CR26","unstructured":"Zadeh, A., Pu, 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 (Long Papers) (2018)"},{"key":"1208_CR27","doi-asserted-by":"publisher","first-page":"159","DOI":"10.1016\/j.neucom.2020.10.021","volume":"430","author":"Y Li","year":"2021","unstructured":"Li, Y., Zhang, K., Wang, J., et al.: A cognitive brain model for multimodal sentiment analysis based on attention neural networks. Neurocomputing 430, 159\u2013173 (2021)","journal-title":"Neurocomputing"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01208-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-023-01208-5\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-023-01208-5.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,14]],"date-time":"2024-02-14T06:09:42Z","timestamp":1707890982000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-023-01208-5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,1,13]]},"references-count":27,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2024,2]]}},"alternative-id":["1208"],"URL":"https:\/\/doi.org\/10.1007\/s00530-023-01208-5","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2024,1,13]]},"assertion":[{"value":"25 August 2022","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"8 December 2023","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"13 January 2024","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"The authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}],"article-number":"10"}}