{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,13]],"date-time":"2026-05-13T17:43:26Z","timestamp":1778694206407,"version":"3.51.4"},"publisher-location":"Singapore","reference-count":31,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819534586","type":"print"},{"value":"9789819534593","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,10,19]],"date-time":"2025-10-19T00:00:00Z","timestamp":1760832000000},"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\/978-981-95-3459-3_37","type":"book-chapter","created":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T02:23:07Z","timestamp":1760754187000},"page":"467-481","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":2,"title":["Mamba-Enhanced Text-Audio-Video Alignment Network for\u00a0Emotion Recognition in\u00a0Conversations"],"prefix":"10.1007","author":[{"given":"Xinran","family":"Li","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaomao","family":"Fan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qingyang","family":"Wu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiaojiang","family":"Peng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ye","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,10,19]]},"reference":[{"key":"37_CR1","doi-asserted-by":"crossref","unstructured":"Ai, W., Shou, Y., Meng, T., Li, K.: Der-gcn: dialog and event relation-aware graph convolutional neural network for multimodal dialog emotion recognition. IEEE Trans. Neural Netw. Learn. Syst. (2024)","DOI":"10.1109\/TNNLS.2024.3367940"},{"key":"37_CR2","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/s10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., et al.: Iemocap: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"issue":"2","key":"37_CR3","doi-asserted-by":"publisher","first-page":"2099","DOI":"10.1007\/s10586-023-04073-z","volume":"27","author":"D Chen","year":"2024","unstructured":"Chen, D., Zhengwei, H., Yiting, T., Jintao, M., Khanal, R.: Emotion and sentiment analysis for intelligent customer service conversation using a multi-task ensemble framework. Clust. Comput. 27(2), 2099\u20132115 (2024)","journal-title":"Clust. Comput."},{"issue":"6","key":"37_CR4","doi-asserted-by":"publisher","first-page":"1505","DOI":"10.1109\/JSTSP.2022.3188113","volume":"16","author":"S Chen","year":"2022","unstructured":"Chen, S., et al.: Wavlm: Large-scale self-supervised pre-training for full stack speech processing. IEEE J Selected Topics Signal Process. 16(6), 1505\u20131518 (2022)","journal-title":"IEEE J Selected Topics Signal Process."},{"key":"37_CR5","doi-asserted-by":"crossref","unstructured":"Dutta, S., Ganapathy, S.: LLM supervised pre-training for multimodal emotion recognition in conversations. arXiv preprint arXiv:2501.11468 (2025)","DOI":"10.2139\/ssrn.5496422"},{"key":"37_CR6","unstructured":"Gu, A., Dao, T.: Mamba: Linear-time sequence modeling with selective state spaces. arXiv preprint arXiv:2312.00752 (2023)"},{"key":"37_CR7","unstructured":"Gu, A., Goel, K., R\u00e9, C.: Efficiently modeling long sequences with structured state spaces. In: International Conference on Learning Representations (ICLR) (2022). https:\/\/arxiv.org\/abs\/2111.00396"},{"key":"37_CR8","volume":"282","author":"X Guo","year":"2023","unstructured":"Guo, X., Liu, F.: Transformer-based emotion recognition with contextual information. Knowl.-Based Syst. 282, 110151 (2023)","journal-title":"Knowl.-Based Syst."},{"key":"37_CR9","doi-asserted-by":"crossref","unstructured":"He, K., Fan, H., Wu, Y., Xie, S., Girshick, R.: Momentum contrast for unsupervised visual representation learning. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 9729\u20139738 (2020)","DOI":"10.1109\/CVPR42600.2020.00975"},{"key":"37_CR10","first-page":"127","volume":"166","author":"Y He","year":"2023","unstructured":"He, Y., Lu, Y.: Multi-attention fusion network for multimodal emotion recognition. Pattern Recogn. Lett. 166, 127\u2013134 (2023)","journal-title":"Pattern Recogn. Lett."},{"key":"37_CR11","doi-asserted-by":"crossref","unstructured":"Hu, J., Liu, Y., Zhao, J., Jin, Q.: Mmgcn: Multimodal fusion via deep graph convolution network for emotion recognition in conversation. arXiv preprint arXiv:2107.06779 (2021)","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"37_CR12","doi-asserted-by":"crossref","unstructured":"Jiang, Z., et al.: Multimodal mental health digital biomarker analysis from remote interviews using facial, vocal, linguistic, and cardiovascular patterns. IEEE J. Biomed. Health Inform. (2024)","DOI":"10.1109\/JBHI.2024.3352075"},{"key":"37_CR13","unstructured":"Kim, T., Vossen, P.: Emoberta: Speaker-aware emotion recognition in conversation with roberta. arXiv preprint arXiv:2108.12009 (2021)"},{"key":"37_CR14","first-page":"55035","volume":"10","author":"A Kumar","year":"2022","unstructured":"Kumar, A., Sharma, N.: Bert-based emotion recognition from text conversations. IEEE Access 10, 55035\u201355046 (2022)","journal-title":"IEEE Access"},{"key":"37_CR15","doi-asserted-by":"crossref","unstructured":"Li, J., Wang, X., Lv, G., Zeng, Z.: Ga2mif: graph and attention based two-stage multi-source information fusion for conversational emotion detection. IEEE Trans. affective Comput. (2023)","DOI":"10.1109\/TAFFC.2023.3261279"},{"key":"37_CR16","first-page":"9694","volume":"34","author":"J Li","year":"2021","unstructured":"Li, J., Selvaraju, R., Gotmare, A., Joty, S., Xiong, C., Hoi, S.C.H.: Align before fuse: vision and language representation learning with momentum distillation. Adv. Neural. Inf. Process. Syst. 34, 9694\u20139705 (2021)","journal-title":"Adv. Neural. Inf. Process. Syst."},{"key":"37_CR17","unstructured":"Li, X., Fan, X., Wu, Q., Peng, X., Li, Y.: Mamba-enhanced text-audio-video alignment network for emotion recognition in conversations. arXiv preprint arXiv:2409.05243 (2024)"},{"key":"37_CR18","doi-asserted-by":"crossref","unstructured":"Li, Y., Zhang, W., Chen, M.: Multi-modal emotion recognition in conversation based on prompt learning with text-audio fusion features. Sci. Rep. 15(1), 1234 (2025). https:\/\/www.nature.com\/articles\/s41598-025-89758-8","DOI":"10.1038\/s41598-025-89758-8"},{"key":"37_CR19","unstructured":"Li, Y., Sun, Q., Murthy, S.M.K., Alturki, E., Schuller, B.W.: GatedxLSTM: a multimodal affective computing approach for emotion recognition in conversations. arXiv preprint arXiv:2503.20919 (2025)"},{"key":"37_CR20","unstructured":"Liang, B., Wang, T., Zhang, H.: Multimodal emotion recognition calibration in conversations. OpenReview (2025). https:\/\/openreview.net\/forum?id=9KJsCWEJVe"},{"key":"37_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2023.107575","volume":"129","author":"W Liu","year":"2024","unstructured":"Liu, W., Gong, Y., Zhang, G., Lu, J., Zhou, Y., Liao, J.: Glmdrivenet: global-local multimodal fusion driving behavior classification network. Eng. Appl. Artif. Intell. 129, 107575 (2024)","journal-title":"Eng. Appl. Artif. Intell."},{"key":"37_CR22","doi-asserted-by":"crossref","unstructured":"Liu, W., et\u00a0al.: Mmtl-uniad: A unified framework for multimodal and multi-task learning in assistive driving perception. arXiv preprint arXiv:2504.02264 (2025)","DOI":"10.1109\/CVPR52734.2025.00644"},{"key":"37_CR23","doi-asserted-by":"crossref","first-page":"34","DOI":"10.17743\/jaes.2022.0060","volume":"71","author":"M Park","year":"2023","unstructured":"Park, M., Kim, T.: Enhanced acoustic features for emotion recognition in speech. J. Audio Eng. Soc. 71, 34\u201345 (2023)","journal-title":"J. Audio Eng. Soc."},{"key":"37_CR24","doi-asserted-by":"crossref","unstructured":"Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., Mihalcea, R.: Meld: A multimodal multi-party dataset for emotion recognition in conversations. arXiv preprint arXiv:1810.02508 (2018)","DOI":"10.18653\/v1\/P19-1050"},{"key":"37_CR25","doi-asserted-by":"publisher","first-page":"4422","DOI":"10.1109\/TMM.2021.3117062","volume":"24","author":"M Ren","year":"2021","unstructured":"Ren, M., Huang, X., Li, W., Song, D., Nie, W.: Lr-gcn: latent relation-aware graph convolutional network for conversational emotion recognition. IEEE Trans. Multimedia 24, 4422\u20134432 (2021)","journal-title":"IEEE Trans. Multimedia"},{"key":"37_CR26","doi-asserted-by":"crossref","unstructured":"Shi, T., Huang, S.L.: Multiemo: An attention-based correlation-aware multimodal fusion framework for emotion recognition in conversations. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 14752\u201314766 (2023)","DOI":"10.18653\/v1\/2023.acl-long.824"},{"key":"37_CR27","doi-asserted-by":"crossref","first-page":"2465","DOI":"10.1007\/s11042-022-13326-9","volume":"82","author":"Y Wang","year":"2023","unstructured":"Wang, Y., Li, H.: Facial expression recognition using convolutional neural networks and attention mechanisms. Multimedia Tools Appli. 82, 2465\u20132481 (2023)","journal-title":"Multimedia Tools Appli."},{"key":"37_CR28","doi-asserted-by":"crossref","unstructured":"Yang, Z., Ma, J., Chen, H., Zhang, Y., Chang, Y.: Hitrans: a hierarchical transformer network for nested named entity recognition. In: Findings of the Association for Computational Linguistics: EMNLP 2021, pp. 124\u2013132 (2021)","DOI":"10.18653\/v1\/2021.findings-emnlp.12"},{"key":"37_CR29","unstructured":"Yu, X., Wang, F., Qiao, Z.: SpikEmo: enhancing emotion recognition with spiking temporal dynamics in conversations. arXiv preprint arXiv:2411.13917 (2024)"},{"key":"37_CR30","unstructured":"Zhang, W., Liu, M., Chen, L.: Enhanced multimodal emotion recognition in conversations via contextual filtering and multi-frequency graph propagation. ResearchGate (2025). https:\/\/www.researchgate.net\/publication\/390537542"},{"issue":"18","key":"37_CR31","doi-asserted-by":"publisher","first-page":"56039","DOI":"10.1007\/s11042-023-17347-w","volume":"83","author":"X Zhu","year":"2024","unstructured":"Zhu, X., Huang, Y., Wang, X., Wang, R.: Emotion recognition based on brain-like multimodal hierarchical perception. Multimedia Tools Appli. 83(18), 56039\u201356057 (2024)","journal-title":"Multimedia Tools Appli."}],"container-title":["Lecture Notes in Computer Science","Advanced Data Mining and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-3459-3_37","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,18]],"date-time":"2025-10-18T02:23:17Z","timestamp":1760754197000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-3459-3_37"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,10,19]]},"ISBN":["9789819534586","9789819534593"],"references-count":31,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-3459-3_37","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,10,19]]},"assertion":[{"value":"19 October 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ADMA","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Advanced Data Mining and Applications","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Kyoto","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Japan","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":"22 October 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"24 October 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":"adma2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"https:\/\/adma2025.github.io\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}