{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T08:15:57Z","timestamp":1771229757430,"version":"3.50.1"},"reference-count":33,"publisher":"Springer Science and Business Media LLC","issue":"1","license":[{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T00:00:00Z","timestamp":1763424000000},"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":["62472059"],"award-info":[{"award-number":["62472059"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["J Intell Inf Syst"],"published-print":{"date-parts":[[2026,2]]},"DOI":"10.1007\/s10844-025-01005-8","type":"journal-article","created":{"date-parts":[[2025,11,18]],"date-time":"2025-11-18T03:34:47Z","timestamp":1763436887000},"page":"379-402","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["CMKF:Multimodal emotion recognition in conversations based on CoMamba and KAN-Fuse"],"prefix":"10.1007","volume":"64","author":[{"given":"Junxiang","family":"Min","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xianying","family":"Huang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yu","family":"Cheng","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,11,18]]},"reference":[{"key":"1005_CR1","doi-asserted-by":"publisher","unstructured":"Ai W, Zhang F, Meng T, et\u00a0al (2023) A two-stage multimodal emotion recognition model based on graph contrastive learning. In: 2023 IEEE 29th International Conference on Parallel and Distributed Systems (ICPADS), IEEE, pp 397\u2013404, https:\/\/doi.org\/10.1109\/ICPADS60453.2023.00067","DOI":"10.1109\/ICPADS60453.2023.00067"},{"key":"1005_CR2","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3367940","author":"W Ai","year":"2024","unstructured":"Ai, W., Shou, Y., Meng, T., et al. (2024). Der-gcn: Dialog and event relation-aware graph convolutional neural network for multimodal dialog emotion recognition. IEEE Transactions on Neural Networks and Learning Systems. https:\/\/doi.org\/10.1109\/TNNLS.2024.3367940","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"key":"1005_CR3","doi-asserted-by":"publisher","DOI":"10.1109\/TNNLS.2024.3367940","author":"W Ai","year":"2024","unstructured":"Ai, W., Shou, Y., Meng, T., et al. (2024). Der-gcn: Dialog and event relation-aware graph convolutional neural network for multimodal dialog emotion recognition. IEEE Transactions on Neural Networks and Learning Systems. https:\/\/doi.org\/10.1109\/TNNLS.2024.3367940","journal-title":"IEEE Transactions on Neural Networks and Learning Systems"},{"issue":"1","key":"1005_CR4","doi-asserted-by":"publisher","first-page":"51","DOI":"10.1007\/S10844-019-00591-8","volume":"55","author":"P Berka","year":"2020","unstructured":"Berka, P. (2020). Sentiment analysis using rule-based and case-based reasoning. Journal of Intelligent Information Systems, 55(1), 51\u201366. https:\/\/doi.org\/10.1007\/S10844-019-00591-8","journal-title":"Journal of Intelligent Information Systems"},{"key":"1005_CR5","doi-asserted-by":"publisher","first-page":"335","DOI":"10.1007\/S10579-008-9076-6","volume":"42","author":"C Busso","year":"2008","unstructured":"Busso, C., Bulut, M., Lee, C. C., et al. (2008). Iemocap: Interactive emotional dyadic motion capture database. Language Resources and Evaluation, 42, 335\u2013359. https:\/\/doi.org\/10.1007\/S10579-008-9076-6","journal-title":"Language Resources and Evaluation"},{"key":"1005_CR6","doi-asserted-by":"publisher","unstructured":"Cao, W., Zhang, K., Tao, H., et\u00a0al. (2021). Exploiting visual context and multi-grained semantics for social text emotion recognition. In: Artificial Intelligence: First CAAI International Conference, CICAI 2021, Hangzhou, China, June 5\u20136, 2021, Proceedings, Part I 1, Springer, pp 783\u2013795, https:\/\/doi.org\/10.1007\/978-3-030-93046-2_66","DOI":"10.1007\/978-3-030-93046-2_66"},{"key":"1005_CR7","doi-asserted-by":"publisher","unstructured":"Chudasama, V., Kar, P., Gudmalwar, A., et\u00a0al. (2022). M2fnet: Multi-modal fusion network for emotion recognition in conversation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp 4652\u20134661, https:\/\/doi.org\/10.1109\/CVPRW56347.2022.00511","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"1005_CR8","doi-asserted-by":"publisher","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B. (2010). Opensmile: the munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM International Conference on Multimedia, pp 1459\u20131462, https:\/\/doi.org\/10.1145\/1873951.1874246","DOI":"10.1145\/1873951.1874246"},{"issue":"22","key":"1005_CR9","doi-asserted-by":"publisher","first-page":"4714","DOI":"10.3390\/electronics12224714","volume":"12","author":"Y Fu","year":"2023","unstructured":"Fu, Y., Yuan, S., Zhang, C., et al. (2023). Emotion recognition in conversations: A survey focusing on context, speaker dependencies, and fusion methods. Electronics, 12(22), 4714. https:\/\/doi.org\/10.3390\/electronics12224714","journal-title":"Electronics"},{"key":"1005_CR10","doi-asserted-by":"publisher","unstructured":"Gan, X., Huang, X., & Zou, S. (2025). Intentional tendency-based dynamic heterogeneous graph network for emotion recognition in conversations. Journal of Intelligent Information Systems pp 1\u201322. https:\/\/doi.org\/10.1007\/S10844-025-00925-9","DOI":"10.1007\/S10844-025-00925-9"},{"key":"1005_CR11","doi-asserted-by":"publisher","unstructured":"Gu, A., & Dao, T. (2023). Mamba: Linear-time sequence modeling with selective state spaces. https:\/\/doi.org\/10.48550\/ARXIV.2312.00752","DOI":"10.48550\/ARXIV.2312.00752"},{"key":"1005_CR12","doi-asserted-by":"publisher","unstructured":"Gu, A., Goel, K., & R\u00e9, C. (2021). Efficiently modeling long sequences with structured state spaces. https:\/\/doi.org\/10.48550\/arXiv.2111.00396","DOI":"10.48550\/arXiv.2111.00396"},{"key":"1005_CR13","doi-asserted-by":"publisher","unstructured":"Hazarika, D., Poria, S., Zadeh, A., et\u00a0al. (2018). Conversational memory network for emotion recognition in dyadic dialogue videos. In: Proceedings of the Conference. Association for Computational Linguistics. North American Chapter. Meeting, p 2122, https:\/\/doi.org\/10.18653\/V1\/N18-1193","DOI":"10.18653\/V1\/N18-1193"},{"issue":"3","key":"1005_CR14","doi-asserted-by":"publisher","first-page":"673","DOI":"10.1007\/S10844-023-00789-X","volume":"61","author":"R Kumari","year":"2023","unstructured":"Kumari, R., Ashok, N., Agrawal, P. K., et al. (2023). Identifying multimodal misinformation leveraging novelty detection and emotion recognition. Journal of Intelligent Information Systems, 61(3), 673\u2013694. https:\/\/doi.org\/10.1007\/S10844-023-00789-X","journal-title":"Journal of Intelligent Information Systems"},{"key":"1005_CR15","doi-asserted-by":"publisher","unstructured":"Li, D., Wang, Y., Funakoshi, K., et\u00a0al. (2023). Joyful: Joint modality fusion and graph contrastive learning for multimodal emotion recognition. https:\/\/doi.org\/10.48550\/ARXIV.2311.11009","DOI":"10.48550\/ARXIV.2311.11009"},{"key":"1005_CR16","doi-asserted-by":"publisher","unstructured":"Liu, Y., Ott, M., Goyal, N., et\u00a0al. (2019). Roberta: A robustly optimized bert pretraining approach. arXiv e-prints https:\/\/doi.org\/10.48550\/arXiv.1907.11692","DOI":"10.48550\/arXiv.1907.11692"},{"key":"1005_CR17","doi-asserted-by":"publisher","unstructured":"Liu, Z., Wang, Y., Vaidya, S., et\u00a0al. (2024). Kan: Kolmogorov-arnold networks. https:\/\/doi.org\/10.48550\/ARXIV.2404.19756","DOI":"10.48550\/ARXIV.2404.19756"},{"key":"1005_CR18","doi-asserted-by":"publisher","DOI":"10.1016\/J.KNOSYS.2021.107751","volume":"236","author":"H Ma","year":"2022","unstructured":"Ma, H., Wang, J., Lin, H., et al. (2022). A multi-view network for real-time emotion recognition in conversations. Knowledge-Based Systems, 236, Article 107751. https:\/\/doi.org\/10.1016\/J.KNOSYS.2021.107751","journal-title":"Knowledge-Based Systems"},{"key":"1005_CR19","doi-asserted-by":"publisher","unstructured":"Majumder, N., Poria, S., Hazarika, D., et\u00a0al. (2019). Dialoguernn: An attentive rnn for emotion detection in conversations. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 6818\u20136825, https:\/\/doi.org\/10.1609\/AAAI.V33I01.33016818","DOI":"10.1609\/AAAI.V33I01.33016818"},{"key":"1005_CR20","doi-asserted-by":"publisher","unstructured":"Nguyen, C. V. T., Mai, A. T., Le, T. S., et\u00a0al. (2023). Conversation understanding using relational temporal graph neural networks with auxiliary cross-modality interaction. arXiv e-prints https:\/\/doi.org\/10.48550\/ARXIV.2311.04507","DOI":"10.48550\/ARXIV.2311.04507"},{"key":"1005_CR21","doi-asserted-by":"publisher","unstructured":"Nguyen, C. V. T., Le, T. S., Mai, A. T., et\u00a0al. (2024a). Ada2i: Enhancing modality balance for multimodal conversational emotion recognition. In: Proceedings of the 32nd ACM International Conference on Multimedia, pp 9330\u20139339, https:\/\/doi.org\/10.1145\/3664647.3681648","DOI":"10.1145\/3664647.3681648"},{"key":"1005_CR22","doi-asserted-by":"publisher","unstructured":"Nguyen, C. V. T., Nguyen, C. B., Ha, Q. T., et\u00a0al. (2024b). Curriculum learning meets directed acyclic graph for multimodal emotion recognition. https:\/\/doi.org\/10.48550\/ARXIV.2402.17269","DOI":"10.48550\/ARXIV.2402.17269"},{"key":"1005_CR23","doi-asserted-by":"publisher","unstructured":"Poria, S., Cambria, E., Hazarika, D., et\u00a0al. (2017). Context-dependent sentiment analysis in user-generated videos. In: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 873\u2013883, https:\/\/doi.org\/10.18653\/V1\/P17-1081","DOI":"10.18653\/V1\/P17-1081"},{"key":"1005_CR24","doi-asserted-by":"publisher","unstructured":"Poria, S., Hazarika, D., Majumder, N., et\u00a0al. (2018). Meld: A multimodal multi-party dataset for emotion recognition in conversations. https:\/\/doi.org\/10.48550\/arXiv.1810.02508","DOI":"10.48550\/arXiv.1810.02508"},{"key":"1005_CR25","doi-asserted-by":"publisher","unstructured":"Shi, T., & Huang, S. L. (2023). In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 14752\u201314766, https:\/\/doi.org\/10.18653\/V1\/2023.ACL-LONG.824","DOI":"10.18653\/V1\/2023.ACL-LONG.824"},{"issue":"3","key":"1005_CR26","doi-asserted-by":"publisher","first-page":"1803","DOI":"10.1109\/TAFFC.2022.3223517","volume":"14","author":"G Tu","year":"2022","unstructured":"Tu, G., Liang, B., Jiang, D., et al. (2022). Sentiment-emotion-and context-guided knowledge selection framework for emotion recognition in conversations. IEEE Transactions on Affective Computing, 14(3), 1803\u20131816. https:\/\/doi.org\/10.1109\/TAFFC.2022.3223517","journal-title":"IEEE Transactions on Affective Computing"},{"key":"1005_CR27","doi-asserted-by":"publisher","unstructured":"Wang, Y., Shen, Y., Liu, Z., et\u00a0al. (2019). Words can shift: Dynamically adjusting word representations using nonverbal behaviors. In: Proceedings of the AAAI Conference on Artificial Intelligence, pp 7216\u20137223, https:\/\/doi.org\/10.1609\/AAAI.V33I01.33017216","DOI":"10.1609\/AAAI.V33I01.33017216"},{"key":"1005_CR28","doi-asserted-by":"publisher","unstructured":"Wu, J., Wu, J., Zheng, Y., et\u00a0al. (2024). Mlgat: multi-layer graph attention networks for multimodal emotion recognition in conversations. Journal of Intelligent Information Systems pp 1\u201320. https:\/\/doi.org\/10.1007\/S10844-024-00879-4","DOI":"10.1007\/S10844-024-00879-4"},{"key":"1005_CR29","doi-asserted-by":"publisher","unstructured":"Zhang, X., & Li, Y. (2023). A cross-modality context fusion and semantic refinement network for emotion recognition in conversation. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp 13099\u201313110, https:\/\/doi.org\/10.18653\/V1\/2023.ACL-LONG.732","DOI":"10.18653\/V1\/2023.ACL-LONG.732"},{"key":"1005_CR30","doi-asserted-by":"publisher","unstructured":"Zhuang, X., Zhou, F., & Li, Z. (2024). Mv-bart: Multi-view bart for multi-modal sarcasm detection. In: Proceedings of the 33rd ACM International Conference on Information and Knowledge Management, pp 3602\u20133611, https:\/\/doi.org\/10.1145\/3627673.3679570","DOI":"10.1145\/3627673.3679570"},{"key":"1005_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/J.ENGAPPAI.2024.109884","volume":"142","author":"X Zhuang","year":"2025","unstructured":"Zhuang, X., Li, Z., Zhang, C., et al. (2025). A cross-modal collaborative guiding network for sarcasm explanation in multi-modal multi-party dialogues. Engineering Applications of Artificial Intelligence, 142, Article 109884. https:\/\/doi.org\/10.1016\/J.ENGAPPAI.2024.109884","journal-title":"Engineering Applications of Artificial Intelligence"},{"key":"1005_CR32","doi-asserted-by":"publisher","DOI":"10.1016\/J.KNOSYS.2025.113029","volume":"310","author":"X Zhuang","year":"2025","unstructured":"Zhuang, X., Li, Z., Zhou, F., et al. (2025). Dycr-net: A dynamic context-aware routing network for multi-modal sarcasm detection in conversation. Knowledge-Based Systems, 310, Article 113029. https:\/\/doi.org\/10.1016\/J.KNOSYS.2025.113029","journal-title":"Knowledge-Based Systems"},{"key":"1005_CR33","doi-asserted-by":"publisher","unstructured":"Zou, S., Huang, X., & Shen, X. (2023). Multimodal prompt transformer with hybrid contrastive learning for emotion recognition in conversation. In: Proceedings of the 31st ACM International Conference on Multimedia, pp 5994\u20136003, https:\/\/doi.org\/10.1145\/3581783.3611805","DOI":"10.1145\/3581783.3611805"}],"container-title":["Journal of Intelligent Information Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-01005-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s10844-025-01005-8","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s10844-025-01005-8.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,16]],"date-time":"2026-02-16T07:40:00Z","timestamp":1771227600000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s10844-025-01005-8"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,11,18]]},"references-count":33,"journal-issue":{"issue":"1","published-print":{"date-parts":[[2026,2]]}},"alternative-id":["1005"],"URL":"https:\/\/doi.org\/10.1007\/s10844-025-01005-8","relation":{},"ISSN":["0925-9902","1573-7675"],"issn-type":[{"value":"0925-9902","type":"print"},{"value":"1573-7675","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025,11,18]]},"assertion":[{"value":"30 July 2025","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"1 November 2025","order":2,"name":"revised","label":"Revised","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"4 November 2025","order":3,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 November 2025","order":4,"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 no competing interests.","order":2,"name":"Ethics","group":{"name":"EthicsHeading","label":"Competing interests"}}]}}