{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,23]],"date-time":"2026-07-23T00:25:52Z","timestamp":1784766352011,"version":"3.55.0"},"reference-count":42,"publisher":"Springer Science and Business Media LLC","issue":"4","license":[{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T00:00:00Z","timestamp":1753488000000},"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":["62372111"],"award-info":[{"award-number":["62372111"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"DOI":"10.13039\/501100003392","name":"Natural Science Foundation of Fujian Province","doi-asserted-by":"publisher","award":["2023J01267"],"award-info":[{"award-number":["2023J01267"]}],"id":[{"id":"10.13039\/501100003392","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["CCF Trans. Pervasive Comp. Interact."],"published-print":{"date-parts":[[2025,12]]},"DOI":"10.1007\/s42486-025-00195-y","type":"journal-article","created":{"date-parts":[[2025,7,26]],"date-time":"2025-07-26T15:49:17Z","timestamp":1753544957000},"page":"474-493","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Multimodal sentiment analysis based on slice aggregation and dynamic fusion"],"prefix":"10.1007","volume":"7","author":[{"given":"Zhouwen","family":"Zhan","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Dongtao","family":"Cao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zheyi","family":"Chen","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Hongju","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhiyong","family":"Yu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2025,7,26]]},"reference":[{"key":"195_CR1","unstructured":"Andrew, G., Arora, R., Bilmes, J., and Livescu, K., Deep canonical correlation analysis. In Int. Conf. Mach. Learn. 1247-1255 (2013)"},{"key":"195_CR2","doi-asserted-by":"crossref","unstructured":"Baltrusaitis, T., Zadeh, A., Lim, Y., et al.: OpenFace 2.0: Facial behavior analysis toolkit. In 2018 13th IEEE Int. Conf. Autom. Face Gesture Recognit. (FG 2018). 59-66 (2018)","DOI":"10.1109\/FG.2018.00019"},{"key":"195_CR3","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1145\/1210596.1210599","volume":"2","author":"DR Bobbarjung","year":"2006","unstructured":"Bobbarjung, D.R., Jagannathan, S., Dubnicki, C.: Improving duplicate elimination in storage systems. ACM Trans. Storage (TOS) 2, 424\u2013448 (2006)","journal-title":"ACM Trans. Storage (TOS)"},{"key":"195_CR4","doi-asserted-by":"crossref","unstructured":"Chen, C., Si, J., Li, H., et al.: A high stability clustering scheme for the internet of vehicles. IEEE Trans. Netw. Serv, Manag (2024)","DOI":"10.1109\/TNSM.2024.3390117"},{"key":"195_CR5","doi-asserted-by":"publisher","first-page":"3149","DOI":"10.1109\/TAFFC.2023.3265653","volume":"14","author":"H Cheng","year":"2023","unstructured":"Cheng, H., Yang, Z., Zhang, X., Yang, Y.: Multimodal sentiment analysis based on attentional temporal convolutional network and multi-layer feature fusion. IEEE Trans. Affect. Comput. 14, 3149\u20133163 (2023)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"195_CR6","doi-asserted-by":"crossref","unstructured":"Degottex, G., Kane, J., Drugman, T., et al.: COVAREP?A collaborative voice analysis repository for speech technologies. In: 2014 IEEE Int, pp. 960\u2013964. Conf. Acoust, Speech Signal Process (2014)","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"195_CR7","doi-asserted-by":"crossref","unstructured":"Devlin, J., Chang, M., Lee, K., Toutanova, K., 2019. BERT: Pre-training of deep bidirectional transformers for language understanding. In Proc. 2019 Conf. North Am. Chapter Assoc. Comput. Linguist.: Hum. Lang. Technol. 4171-4186","DOI":"10.18653\/v1\/N19-1423"},{"key":"195_CR8","doi-asserted-by":"crossref","unstructured":"Ekman, P., Rosenberg, E.L., 1997. What the face reveals: basic and applied studies of spontaneous expression using the facial action coding system (FACS). In SciPy","DOI":"10.1093\/oso\/9780195104462.001.0001"},{"key":"195_CR9","unstructured":"Eshghi, K., Tang, H.K.: A framework for analyzing and improving content-based chunking algorithms. Hewlett-Packard Labs Tech. Rep, TR, p. 30. (2005)"},{"key":"195_CR10","doi-asserted-by":"crossref","unstructured":"Fan, Y., Xu, M., Wu, Z., and Cai, L., 2014. Automatic emotion variation detection using multi-scaled sliding window. In 2014 Int. Conf. Orange Technol. 232-236","DOI":"10.1109\/ICOT.2014.6956642"},{"key":"195_CR11","doi-asserted-by":"crossref","unstructured":"Fan, C., Zhu, K., Tao, J., et al.: Multi-level contrastive learning: hierarchical alleviation of heterogeneity in multimodal sentiment analysis. IEEE Trans. Affect, Comput (2024)","DOI":"10.1109\/TAFFC.2024.3423671"},{"key":"195_CR12","doi-asserted-by":"crossref","unstructured":"Gou, J., Chen, Y., Yu, B., et al.: Reciprocal teacher-student learning via forward and feedback knowledge distillation. IEEE Trans, Multimedia (2024)","DOI":"10.1109\/TMM.2024.3372833"},{"key":"195_CR13","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Zimmermann, R., Poria, S., 2020. Misa: Modality-invariant and specific representations for multimodal sentiment analysis. In Proc. 28th ACM Int. Conf. Multimedia. 1122-1131","DOI":"10.1145\/3394171.3413678"},{"key":"195_CR14","doi-asserted-by":"crossref","unstructured":"He, L., Jiang, D., Yang, L., et al. 2015. Multimodal affective dimension prediction using deep bidirectional long short-term memory recurrent neural networks. In Proc. 5th Int Workshop Audio\/Visual Emotion Challenge. 73\u201380","DOI":"10.1145\/2808196.2811641"},{"key":"195_CR15","doi-asserted-by":"crossref","unstructured":"He, K., Zhang, X., Ren, S., Sun, J., 2016. Deep residual learning for image recognition. In Proc. IEEE Conf. Comput. Vis. Pattern Recognit. 770-778","DOI":"10.1109\/CVPR.2016.90"},{"key":"195_CR16","doi-asserted-by":"crossref","unstructured":"Jiang, P., Deng, X., Wu, W., et al.: Weather-aware collaborative perception with uncertainty reduction. IEEE Trans. Intell. Transp, Syst (2024)","DOI":"10.1109\/TITS.2024.3479720"},{"key":"195_CR17","doi-asserted-by":"crossref","unstructured":"Kampman, O., Barezi, E.J., Bertero, D., et al.: Investigating audio, video, and text fusion methods for end-to-end automatic personality prediction. In Proc. 56th Annu. Meet. Assoc. Comput. Linguist. 2, 606\u2013611 (2018)","DOI":"10.18653\/v1\/P18-2096"},{"issue":"3","key":"195_CR18","doi-asserted-by":"publisher","first-page":"228","DOI":"10.1007\/s42486-024-00154-z","volume":"6","author":"H Li","year":"2024","unstructured":"Li, H., Yu, Z., Luo, Y., et al.: ContinuousSensing: a task allocation algorithm for human?robot collaborative mobile crowdsensing with task migration. CCF Trans. Pervasive Comput. Interact. 6(3), 228\u2013243 (2024)","journal-title":"CCF Trans. Pervasive Comput. Interact."},{"key":"195_CR19","doi-asserted-by":"crossref","unstructured":"Mai, S., Hu, H., and Xing, S., 2019. Divide, conquer and combine: Hierarchical feature fusion network with local and global perspectives for multimodal affective computing. In Proc. 57th Annu. Meet. Assoc. Comput. Linguist. 481-492","DOI":"10.18653\/v1\/P19-1046"},{"key":"195_CR20","doi-asserted-by":"crossref","unstructured":"McFee, B., Raffel, C., Liang, D., et al., 2015. librosa: Audio and music signal analysis in Python. In SciPy. 18-24","DOI":"10.25080\/Majora-7b98e3ed-003"},{"key":"195_CR21","doi-asserted-by":"publisher","first-page":"eaax7421","DOI":"10.1126\/scirobotics.aax7421","volume":"4","author":"RR Murphy","year":"2019","unstructured":"Murphy, R.R.: Computer vision and machine learning in science fiction. Sci. Robot. 4, eaax7421 (2019)","journal-title":"Sci. Robot."},{"key":"195_CR22","doi-asserted-by":"crossref","unstructured":"Nojavanasghari, B., Gopinath, D., Koushik, J., et al., 2016. Deep multimodal fusion for persuasiveness prediction. In Proc. 18th ACM Int. Conf. Multimodal Interact. 284-288","DOI":"10.1145\/2993148.2993176"},{"key":"195_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.asoc.2023.111206","volume":"152","author":"A Pandey","year":"2024","unstructured":"Pandey, A., Vishwakarma, D.K.: Progress, achievements, and challenges in multimodal sentiment analysis using deep learning: a survey. Appl. Soft Comput. 152, 111206 (2024)","journal-title":"Appl. Soft Comput."},{"issue":"1","key":"195_CR24","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3634704","volume":"23","author":"H Qi","year":"2024","unstructured":"Qi, H., Ren, F., Wang, L., et al.: Multi-compression scale DNN inference acceleration based on cloud-edge-end collaboration. ACM Trans. Embed. Comput. Syst. 23(1), 1\u201325 (2024)","journal-title":"ACM Trans. Embed. Comput. Syst."},{"key":"195_CR25","first-page":"100790","volume":"27","author":"J Sangeetha","year":"2023","unstructured":"Sangeetha, J., Kumaran, U.: Sentiment analysis of Amazon user reviews using a hybrid approach. Meas.: Sens. 27, 100790 (2023)","journal-title":"Meas.: Sens."},{"key":"195_CR26","doi-asserted-by":"crossref","unstructured":"Sun, H., Chen, Y., Lin, L.: Tensorformer: a tensor-based multimodal transformer for multimodal sentiment analysis and depression detection. IEEE Trans. on Affect, Comput (2022)","DOI":"10.1109\/TAFFC.2022.3233070"},{"key":"195_CR27","doi-asserted-by":"crossref","unstructured":"Sun, L., Liu, B., Tao, J., et al., 2021. Multimodal cross-and self-attention network for speech emotion recognition. In IEEE Int. Conf. Acoust., Speech Signal Process. (ICASSP). 4275-4279","DOI":"10.1109\/ICASSP39728.2021.9414654"},{"key":"195_CR28","doi-asserted-by":"crossref","unstructured":"Tellamekala, M.K., Amiriparian, S., Schuller, B.W., et al.: COLD fusion: Calibrated and ordinal latent distribution fusion for uncertainty-aware multimodal emotion recognition. IEEE Trans. Pattern Anal. Mach, Intell (2023)","DOI":"10.1109\/TPAMI.2023.3325770"},{"key":"195_CR29","doi-asserted-by":"crossref","unstructured":"Tsai, Y., Bai, S., Liang, P.P., et al.: Multimodal transformer for unaligned multimodal language sequences, p. 6558. In Proc. Conf. Assoc. Comput. Linguist, Meet (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"195_CR30","doi-asserted-by":"publisher","first-page":"127181","DOI":"10.1016\/j.neucom.2023.127181","volume":"572","author":"Y Wang","year":"2024","unstructured":"Wang, Y., He, J., Wang, D., et al.: Multimodal transformer with adaptive modality weighting for multimodal sentiment analysis. Neurocomputing 572, 127181 (2024)","journal-title":"Neurocomputing"},{"key":"195_CR31","doi-asserted-by":"crossref","unstructured":"Williams, J., Kleinegesse, S., Comanescu, R., et al., 2018. Recognizing emotions in video using multimodal DNN feature fusion. In Proc. Grand Challenge Workshop Hum. Multimodal Lang. (Challenge-HML). 11-19","DOI":"10.18653\/v1\/W18-3302"},{"key":"195_CR32","doi-asserted-by":"crossref","unstructured":"Xue, Z., and Marculescu, R., 2023. Dynamic multimodal fusion. In Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. 2574-2583","DOI":"10.1109\/CVPRW59228.2023.00256"},{"issue":"2","key":"195_CR33","doi-asserted-by":"publisher","first-page":"182","DOI":"10.1007\/s42486-024-00152-1","volume":"6","author":"Y Yang","year":"2024","unstructured":"Yang, Y., Guo, B., Zhao, K., et al.: MELPD-Detector: Multi-level ensemble learning method based on adaptive data augmentation for Parkinson disease detection via free-KD. CCF Trans. Pervasive Comput. Interact. 6(2), 182\u2013198 (2024)","journal-title":"CCF Trans. Pervasive Comput. Interact."},{"key":"195_CR34","doi-asserted-by":"crossref","unstructured":"Yu, W., Xu, H., Meng, F., et al., 2020. Ch-sims: A Chinese multimodal sentiment analysis dataset with fine-grained annotation of modality. In Proc. 58th Annu. Meet. Assoc. Comput. Linguist. 3718-3727","DOI":"10.18653\/v1\/2020.acl-main.343"},{"key":"195_CR35","first-page":"10790","volume":"35","author":"W Yu","year":"2021","unstructured":"Yu, W., Xu, H., Yuan, Z., Wu, J.: Learning modality-specific representations with self-supervised multi-task learning for multimodal sentiment analysis. In Proc. AAAI Conf. Artif. Intell. 35, 10790\u201310797 (2021)","journal-title":"In Proc. AAAI Conf. Artif. Intell."},{"key":"195_CR36","doi-asserted-by":"publisher","first-page":"3878","DOI":"10.1121\/1.2935783","volume":"123","author":"J Yuan","year":"2008","unstructured":"Yuan, J., Liberman, M.: Speaker identification on the SCOTUS corpus. J. Acoust. Soc. Am. 123, 3878 (2008)","journal-title":"J. Acoust. Soc. Am."},{"key":"195_CR37","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., et al., 2017. Tensor fusion network for multimodal sentiment analysis. In Proc. 2017 Conf. Empir. Methods Nat. Lang. Process. 1103-1114","DOI":"10.18653\/v1\/D17-1115"},{"key":"195_CR38","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P., Mazumder, N., et al.: Memory fusion network for multi-view sequential learning, p. 32. In Proc. AAAI Conf. Artif, Intell (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"195_CR39","doi-asserted-by":"crossref","unstructured":"Zadeh, A.A.B., Liang, P.P., Poria, S., et al.: Multimodal language analysis in the wild: Cmu-mosei dataset and interpretable dynamic fusion graph. In Proc. 56th Annu. Meet. Assoc. Comput. Linguist. 1, 2236\u20132246 (2018)","DOI":"10.18653\/v1\/P18-1208"},{"key":"195_CR40","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.: Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. IEEE Intell. Syst. 31, 82\u201388 (2016)","journal-title":"IEEE Intell. Syst."},{"key":"195_CR41","unstructured":"Zhang, Q., Wei, Y., Han, Z., et al., 2024. Multimodal fusion on low-quality data: a comprehensive survey. arXiv preprint arXiv:2404.18947"},{"key":"195_CR42","doi-asserted-by":"crossref","unstructured":"Zhang, W., L.Qin, W., Zhong, W., et al., 2019. Framework of sequence chunking for human activity recognition using wearables. In Proc. 2019 Int. Conf. Image, Video Signal Process. 93-98","DOI":"10.1145\/3317640.3317647"}],"container-title":["CCF Transactions on Pervasive Computing and Interaction"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42486-025-00195-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s42486-025-00195-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s42486-025-00195-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,12,15]],"date-time":"2025-12-15T13:31:59Z","timestamp":1765805519000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s42486-025-00195-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,7,26]]},"references-count":42,"journal-issue":{"issue":"4","published-print":{"date-parts":[[2025,12]]}},"alternative-id":["195"],"URL":"https:\/\/doi.org\/10.1007\/s42486-025-00195-y","relation":{},"ISSN":["2524-521X","2524-5228"],"issn-type":[{"value":"2524-521X","type":"print"},{"value":"2524-5228","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,7,26]]},"assertion":[{"value":"21 March 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"27 May 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2025","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}