{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,9,11]],"date-time":"2025-09-11T21:03:09Z","timestamp":1757624589910,"version":"3.44.0"},"publisher-location":"Cham","reference-count":27,"publisher":"Springer Nature Switzerland","isbn-type":[{"value":"9783032045485","type":"print"},{"value":"9783032045492","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,9,10]],"date-time":"2025-09-10T00:00:00Z","timestamp":1757462400000},"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\/978-3-032-04549-2_17","type":"book-chapter","created":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T13:47:47Z","timestamp":1757425667000},"page":"205-216","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Early Acoustic and\u00a0Vision Cross-Modal Interaction Learning for\u00a0Multimal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Xiongjian","family":"Lv","sequence":"first","affiliation":[]},{"given":"Yimin","family":"Wen","sequence":"additional","affiliation":[]},{"given":"Yi","family":"Qian","sequence":"additional","affiliation":[]},{"given":"Xiaoyu","family":"Li","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,9,10]]},"reference":[{"key":"17_CR1","doi-asserted-by":"crossref","unstructured":"Li, M., et al.: A unified self-distillation framework for multimodal sentiment analysis with uncertain missing modalities. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp.\u00a010074\u201310082 (2024)","DOI":"10.1609\/aaai.v38i9.28871"},{"key":"17_CR2","doi-asserted-by":"crossref","unstructured":"Huang, J., Ji, Y., Yang, Y., Shen, H.T.: Cross-modality representation interactive learning for multimodal sentiment analysis. In: Proceedings of the 31st ACM International Conference on Multimedia, pp. 426\u2013434 (2023)","DOI":"10.1145\/3581783.3612295"},{"key":"17_CR3","doi-asserted-by":"crossref","unstructured":"Zong, D., Ding, C., Li, B., Li, J., Zheng, K., Zhou, Q.: Acformer: an aligned and compact transformer for multimodal sentiment analysis. In: Proceedings of the 31st ACM International Conference on Multimedia, pp.\u00a0833\u2013842 (2023)","DOI":"10.1145\/3581783.3611974"},{"key":"17_CR4","doi-asserted-by":"crossref","unstructured":"Guo, Z., Jin, T., Zhao, Z.: Multimodal prompt learning with missing modalities for sentiment analysis and emotion recognition. In: Ku, L.-W., Martins, A., Srikumar, V. (eds.) Proceedings of the 62nd Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), Bangkok, Thailand, pp.\u00a01726\u20131736, Association for Computational Linguistics (Aug. 2024)","DOI":"10.18653\/v1\/2024.acl-long.94"},{"key":"17_CR5","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: Jurafsky, D., Chai, J., Schluter, N., Tetreault, J. (eds.) Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics (Online), pp.\u00a02359\u20132369. Association for Computational Linguistics (July 2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"17_CR6","doi-asserted-by":"crossref","unstructured":"Hwang, Y., Kim, J.-H.: Easum: enhancing affective state understanding through joint sentiment and emotion modeling for multimodal tasks. In: Proceedings of the IEEE\/CVF Winter Conference on Applications of Computer Vision, pp.\u00a05668\u20135678 (2024)","DOI":"10.1109\/WACV57701.2024.00557"},{"key":"17_CR7","unstructured":"Devlin, J., Chang, M.-W., Lee, K., Toutanova, K.: BERT: Pre-training of deep bidirectional transformers for language understanding. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp.\u00a04171\u20134186 (2019)"},{"key":"17_CR8","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21, 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"17_CR9","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2023.101973","volume":"101","author":"Z Liu","year":"2024","unstructured":"Liu, Z., Zhou, B., Chu, D., Sun, Y., Meng, L.: Modality translation-based multimodal sentiment analysis under uncertain missing modalities. Inform. Fusion 101, 101973 (2024)","journal-title":"Inform. Fusion"},{"key":"17_CR10","doi-asserted-by":"crossref","unstructured":"Hu, G., Lin, T.-E., Zhao, Y., Lu, G., Wu, Y., Li, Y.: Unimse: Towards unified multimodal sentiment analysis and emotion recognition. In: Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp.\u00a07837\u20137851 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"17_CR11","doi-asserted-by":"crossref","unstructured":"Han, W., Chen, H., Poria, S.: Improving multimodal fusion with hierarchical mutual information maximization for multimodal sentiment analysis. In: Proceedings of the 2021 Conference on Empirical Methods in Natural Language Processing, pp.\u00a09180\u20139192 (2021)","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"17_CR12","doi-asserted-by":"crossref","unstructured":"Kaya, U., Kafaligonul, H.: Audiovisual interactions in speeded discrimination of a visual event. Psychophysiology, 13777 (2021)","DOI":"10.1111\/psyp.13777"},{"key":"17_CR13","doi-asserted-by":"publisher","first-page":"132188","DOI":"10.1109\/ACCESS.2020.3010066","volume":"8","author":"H Zhang","year":"2020","unstructured":"Zhang, H., Zhang, Q., Shao, S., Niu, T., Yang, X.: Attention-based lstm network for rotatory machine remaining useful life prediction. IEEE Access 8, 132188\u2013132199 (2020)","journal-title":"IEEE Access"},{"key":"17_CR14","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2022.118710","volume":"212","author":"M Arbane","year":"2023","unstructured":"Arbane, M., Benlamri, R., Brik, Y., Alahmar, A.D.: Social media-based covid-19 sentiment classification model using bi-lstm. Expert Syst. Appl. 212, 118710 (2023)","journal-title":"Expert Syst. Appl."},{"key":"17_CR15","doi-asserted-by":"publisher","first-page":"1665","DOI":"10.1111\/bjet.13204","volume":"53","author":"G Lu","year":"2022","unstructured":"Lu, G., Xie, K., Liu, Q.: What influences student situational engagement in smart classrooms: perception of the learning environment and students\u2019 motivation. Br. J. Edu. Technol. 53, 1665\u20131687 (2022)","journal-title":"Br. J. Edu. Technol."},{"key":"17_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, pp.\u00a010790\u201310797 (2021)","DOI":"10.1609\/aaai.v35i12.17289"},{"key":"17_CR17","doi-asserted-by":"crossref","unstructured":"Yang, D., Huang, S., Kuang, H., Du, Y., Zhang, L.: Disentangled representation learning for multimodal emotion recognition. In: Proceedings of the 30th ACM International Conference on Multimedia, pp.\u00a01642\u20131651 (2022)","DOI":"10.1145\/3503161.3547754"},{"key":"17_CR18","doi-asserted-by":"publisher","first-page":"309","DOI":"10.1109\/TAFFC.2023.3274829","volume":"15","author":"L Sun","year":"2023","unstructured":"Sun, L., Lian, Z., Liu, B., Tao, J.: Efficient multimodal transformer with dual-level feature restoration for robust multimodal sentiment analysis. IEEE Trans. Affect. Comput. 15, 309\u2013325 (2023)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"17_CR19","doi-asserted-by":"crossref","unstructured":"Liu, P.: Improving the modality representation with multi-view contrastive learning for multimodal sentiment analysis. In: ICASSP 2023 - 2023 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096470"},{"key":"17_CR20","doi-asserted-by":"publisher","first-page":"2276","DOI":"10.1109\/TAFFC.2022.3172360","volume":"14","author":"S Mai","year":"2022","unstructured":"Mai, S., Zeng, Y., Zheng, S., Hu, H.: Hybrid contrastive learning of tri-modal representation for multimodal sentiment analysis. IEEE Trans. Affect. Comput. 14, 2276\u20132289 (2022)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"17_CR21","doi-asserted-by":"crossref","unstructured":"Zhang, H., Wang, Y., Yin, G., Liu, K., Liu, Y., Yu, T.: Learning language-guided adaptive hyper-modality representation for multimodal sentiment analysis. In: Proceedings of the 2023 Conference on Empirical Methods in Natural Language Processing, pp.\u00a0756\u2013767, 2023","DOI":"10.18653\/v1\/2023.emnlp-main.49"},{"key":"17_CR22","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.111982","volume":"299","author":"C Gan","year":"2024","unstructured":"Gan, C., Tang, Y., Fu, X., Zhu, Q., Jain, D.K., Garc\u00eda, S.: Video multimodal sentiment analysis using cross-modal feature translation and dynamical propagation. Knowl.-Based Syst. 299, 111982 (2024)","journal-title":"Knowl.-Based Syst."},{"key":"17_CR23","doi-asserted-by":"publisher","first-page":"207","DOI":"10.1109\/TAFFC.2024.3423671","volume":"16","author":"C Fan","year":"2025","unstructured":"Fan, C., Zhu, K., Tao, J., Yi, G., Xue, J., Lv, Z.: Multi-level contrastive learning: hierarchical alleviation of heterogeneity in multimodal sentiment analysis. IEEE Trans. Affect. Comput. 16, 207\u2013222 (2025)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"17_CR24","doi-asserted-by":"crossref","unstructured":"Zhu, A., Hu, M., Wang, X., Yang, J., Tang, Y., Ren, F.: Kebr: knowledge enhanced self-supervised balanced representation for multimodal sentiment analysis. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp.\u00a05732\u20135741 (2024)","DOI":"10.1145\/3664647.3681163"},{"key":"17_CR25","doi-asserted-by":"crossref","unstructured":"Zhuang, Y., Zhang, Y., Hu, Z., Zhang, X., Deng, J., Ren, F.:Glomo: global-local modal fusion for multimodal sentiment analysis. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp.\u00a01800\u20131809 (2024)","DOI":"10.1145\/3664647.3681527"},{"key":"17_CR26","doi-asserted-by":"crossref","unstructured":"Wu, Z., Zhang, Q., Miao, D., Yi, K., Fan, W., Hu, L.: Hydiscgan: a hybrid distributed cgan for audio-visual privacy preservation in multimodal sentiment analysis. In: Proceedings of the 33rd International Joint Conference on Artificial Intelligence (IJCAI), pp.\u00a06550\u20136558 (2024)","DOI":"10.24963\/ijcai.2024\/724"},{"key":"17_CR27","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2024.112220","volume":"300","author":"J Hou","year":"2024","unstructured":"Hou, J., Omar, N., Tiun, S., Saad, S., He, Q.: Tchfn: multimodal sentiment analysis based on text-centric hierarchical fusion network. Knowl.-Based Syst. 300, 112220 (2024)","journal-title":"Knowl.-Based Syst."}],"container-title":["Lecture Notes in Computer Science","Artificial Neural Networks and Machine Learning \u2013 ICANN 2025"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-032-04549-2_17","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,9,9]],"date-time":"2025-09-09T13:48:01Z","timestamp":1757425681000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-032-04549-2_17"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,9,10]]},"ISBN":["9783032045485","9783032045492"],"references-count":27,"URL":"https:\/\/doi.org\/10.1007\/978-3-032-04549-2_17","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,9,10]]},"assertion":[{"value":"10 September 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICANN","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Artificial Neural Networks","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kaunas","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Lithuania","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":"9 September 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"12 September 2025","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"34","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icann2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/e-nns.org\/icann2025\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}