{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,6,11]],"date-time":"2025-06-11T07:32:49Z","timestamp":1749627169625,"version":"3.37.3"},"reference-count":17,"publisher":"Springer Science and Business Media LLC","issue":"12","license":[{"start":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T00:00:00Z","timestamp":1726704000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T00:00:00Z","timestamp":1726704000000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"Natural Science Foundation of Xiamen, China","award":["3502Z202373040"],"award-info":[{"award-number":["3502Z202373040"]}]},{"DOI":"10.13039\/501100001809","name":"National Natural Science Foundation of China","doi-asserted-by":"crossref","award":["61871196"],"award-info":[{"award-number":["61871196"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["SIViP"],"published-print":{"date-parts":[[2024,12]]},"DOI":"10.1007\/s11760-024-03563-w","type":"journal-article","created":{"date-parts":[[2024,9,19]],"date-time":"2024-09-19T11:22:39Z","timestamp":1726744959000},"page":"9505-9513","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Visual audio and textual triplet fusion network for multi-modal sentiment analysis"],"prefix":"10.1007","volume":"18","author":[{"given":"Cai-Chao","family":"Lv","sequence":"first","affiliation":[]},{"given":"Xuan","family":"Zhang","sequence":"additional","affiliation":[]},{"given":"Hong-Bo","family":"Zhang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2024,9,19]]},"reference":[{"key":"3563_CR1","doi-asserted-by":"crossref","unstructured":"Song, H., Li, J., Xia, Z., Yang, Z., Du, X.: Multimodal sentiment analysis based on pre-ln transformer interaction. In: 2022 IEEE 6th Information Technology and Mechatronics Engineering Conference 6, pp. 1609\u20131613 (2022)","DOI":"10.1109\/ITOEC53115.2022.9734328"},{"key":"3563_CR2","unstructured":"Devlin, J.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint arXiv:1810.04805 (2018)"},{"key":"3563_CR3","doi-asserted-by":"crossref","unstructured":"Yang, X., Feng, S., Wang, D., Hong, P., Poria, S.: Multiple contrastive learning for multimodal sentiment analysis. In: 2023 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 1\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096777"},{"key":"3563_CR4","doi-asserted-by":"publisher","first-page":"2015","DOI":"10.1109\/TASLP.2022.3178204","volume":"30","author":"B Yang","year":"2022","unstructured":"Yang, B., Wu, L., Zhu, J., Shao, B., Lin, X., Liu, T.-Y.: Multimodal sentiment analysis with two-phase multi-task learning. IEEE\/ACM Trans. Audio Speech Lang. Process. 30, 2015\u20132024 (2022)","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process."},{"key":"3563_CR5","doi-asserted-by":"publisher","first-page":"7956","DOI":"10.1109\/TNNLS.2022.3147546","volume":"34","author":"Y Zhang","year":"2022","unstructured":"Zhang, Y., Zhang, Y., Guo, W., Cai, X., Yuan, X.: Learning disentangled representation for multimodal cross-domain sentiment analysis. IEEE Trans. Neural Netw. Learn. Syst. 34, 7956\u20137966 (2022)","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"issue":"3","key":"3563_CR6","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/2897739","volume":"6","author":"S Park","year":"2016","unstructured":"Park, S., Shim, H.S., Chatterjee, M., Sagae, K., Morency, L.-P.: Multimodal analysis and prediction of persuasiveness in online social multimedia. ACM Trans. Interact. Intell. Syst. 6(3), 1\u201325 (2016)","journal-title":"ACM Trans. Interact. Intell. Syst."},{"key":"3563_CR7","doi-asserted-by":"crossref","unstructured":"Fu, Z., Liu, F., Xu, Q., Qi, J., Fu, X., Zhou, A., Li, Z.: Nhfnet: A non-homogeneous fusion network for multimodal sentiment analysis. In: 2022 IEEE International Conference on Multimedia and Expo, pp. 1\u20136. IEEE (2022)","DOI":"10.1109\/ICME52920.2022.9859836"},{"key":"3563_CR8","doi-asserted-by":"crossref","unstructured":"Ke, P., Ji, H., Liu, S., Zhu, X., Huang, M.: Sentilare: sentiment-aware language representation learning with linguistic knowledge. arXiv preprint arXiv:1911.02493 (2019)","DOI":"10.18653\/v1\/2020.emnlp-main.567"},{"key":"3563_CR9","doi-asserted-by":"crossref","unstructured":"Degottex, G., Kane, J., Drugman, T., Raitio, T., Scherer, S.: Covarep\u2014a collaborative voice analysis repository for speech technologies. In: 2014 IEEE International Conference on Acoustics, Speech and Signal Processing, pp. 960\u2013964 (2014)","DOI":"10.1109\/ICASSP.2014.6853739"},{"key":"3563_CR10","doi-asserted-by":"publisher","first-page":"1446","DOI":"10.3758\/s13428-017-0996-1","volume":"50","author":"S St\u00f6ckli","year":"2018","unstructured":"St\u00f6ckli, S., Schulte-Mecklenbeck, M., Borer, S., Samson, A.C.: Facial expression analysis with AFFDEX and FACET: a validation study. Behav. Res. Methods 50, 1446\u20131460 (2018)","journal-title":"Behav. Res. Methods"},{"key":"3563_CR11","doi-asserted-by":"crossref","unstructured":"Woo, S., Park, J., Lee, J.-Y., Kweon, I.S.: Cbam: Convolutional block attention module. In: Proceedings of the European Conference on Computer Vision, pp. 3\u201319 (2018)","DOI":"10.1007\/978-3-030-01234-2_1"},{"key":"3563_CR12","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":"3563_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 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"3563_CR14","doi-asserted-by":"crossref","unstructured":"Rahman, W., Hasan, M.K., Lee, S., Zadeh, A., Mao, C., Morency, L.-P., Hoque, E.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the Conference. Association for Computational Linguistics. Meeting, vol. 2020, p. 2359. NIH Public Access (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"3563_CR15","doi-asserted-by":"crossref","unstructured":"Yu, T., Gao, H., Lin, T.-E., Yang, M., Wu, Y., Ma, W., Wang, C., Huang, F., Li, Y.: Speech-text dialog pre-training for spoken dialog understanding with explicit cross-modal alignment. arXiv preprint arXiv:2305.11579 (2023)","DOI":"10.18653\/v1\/2023.acl-long.438"},{"key":"3563_CR16","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. 35, pp. 10790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"3563_CR17","unstructured":"Wu, Z., Gong, Z., Koo, J., Hirschberg, J.: Multi-modality multi-loss fusion network. arXiv preprint arXiv:2308.00264 (2023)"}],"container-title":["Signal, Image and Video Processing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03563-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s11760-024-03563-w\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s11760-024-03563-w.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,11,4]],"date-time":"2024-11-04T07:27:18Z","timestamp":1730705238000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s11760-024-03563-w"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,9,19]]},"references-count":17,"journal-issue":{"issue":"12","published-print":{"date-parts":[[2024,12]]}},"alternative-id":["3563"],"URL":"https:\/\/doi.org\/10.1007\/s11760-024-03563-w","relation":{},"ISSN":["1863-1703","1863-1711"],"issn-type":[{"type":"print","value":"1863-1703"},{"type":"electronic","value":"1863-1711"}],"subject":[],"published":{"date-parts":[[2024,9,19]]},"assertion":[{"value":"17 April 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"23 August 2024","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"2 September 2024","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"19 September 2024","order":4,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"order":1,"name":"Ethics","group":{"name":"EthicsHeading","label":"Declarations"}},{"value":"All authors declare that they have no conflict of interest.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Conflict of interest"}}]}}