{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T10:42:32Z","timestamp":1789468952293,"version":"build-2803163510"},"reference-count":44,"publisher":"Springer Science and Business Media LLC","issue":"8","license":[{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T00:00:00Z","timestamp":1787011200000},"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":["No. 12171114"],"award-info":[{"award-number":["No. 12171114"]}],"id":[{"id":"10.13039\/501100001809","id-type":"DOI","asserted-by":"publisher"}]},{"name":"Guangdong Provincial Natural Science Foundation of China","award":["No. 2024A1515011976"],"award-info":[{"award-number":["No. 2024A1515011976"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2026,9]]},"DOI":"10.1007\/s00530-026-02592-4","type":"journal-article","created":{"date-parts":[[2026,8,18]],"date-time":"2026-08-18T07:07:16Z","timestamp":1787036836000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["GraphDREAM: graph-based decoupled representation and evolution-assisted multi-task network for multimodal emotion recognition"],"prefix":"10.1007","volume":"32","author":[{"given":"Yue","family":"Wu","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Ruping","family":"Hu","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Yuchun","family":"Li","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Zhixin","family":"Luo","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Linjie","family":"Pan","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Lingxi","family":"Peng","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2026,8,18]]},"reference":[{"issue":"22","key":"2592_CR1","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., Cao, J.: Emotion recognition in conversations: a survey focusing on context, speaker dependencies, and fusion methods. Electronics 12(22), 4714 (2023). https:\/\/doi.org\/10.3390\/electronics12224714","journal-title":"Electronics"},{"key":"2592_CR2","doi-asserted-by":"publisher","DOI":"10.32604\/cmc.2026.076411","author":"A-S Moon","year":"2026","unstructured":"Moon, A.-S., Kim, H., Park, Y.-C., Lee, J.: A survey on multimodal emotion recognition: methods, datasets, and future directions. Comput. Mater. Contin. (2026). https:\/\/doi.org\/10.32604\/cmc.2026.076411","journal-title":"Comput. Mater. Contin."},{"key":"2592_CR3","doi-asserted-by":"publisher","first-page":"1898","DOI":"10.1109\/LSP.2021.3112314","volume":"28","author":"K Zhang","year":"2021","unstructured":"Zhang, K., Li, Y., Wang, J., Wang, Z., Li, X.: Feature fusion for multimodal emotion recognition based on deep canonical correlation analysis. IEEE Signal Process. Lett. 28, 1898\u20131902 (2021). https:\/\/doi.org\/10.1109\/LSP.2021.3112314","journal-title":"IEEE Signal Process. Lett."},{"key":"2592_CR4","doi-asserted-by":"publisher","first-page":"102","DOI":"10.47577\/technium.v26i.12398","volume":"26","author":"I Krzemi\u0144ska","year":"2025","unstructured":"Krzemi\u0144ska, I.: Multimodal recognition of users states at human-AI interaction adaptation. Technium Rom. J. Appl. Sci. Tech. 26, 102 (2025). https:\/\/doi.org\/10.47577\/technium.v26i.12398","journal-title":"Technium Rom. J. Appl. Sci. Tech."},{"key":"2592_CR5","doi-asserted-by":"publisher","DOI":"10.1109\/ISMSIT67332.2025.11267892","author":"Q Wei","year":"2025","unstructured":"Wei, Q., Xie, Y.: Multimodal learning affect recognition and adaptive teaching strategy adjustment for online education scenarios. Ninth Int. Symp. Multidiscip. Stud. Innov. Technol. (ISMSIT) (2025). https:\/\/doi.org\/10.1109\/ISMSIT67332.2025.11267892","journal-title":"Ninth Int. Symp. Multidiscip. Stud. Innov. Technol. (ISMSIT)"},{"issue":"2","key":"2592_CR6","doi-asserted-by":"publisher","first-page":"1630","DOI":"10.1109\/JBHI.2025.3604933","volume":"30","author":"H-Y Chang","year":"2026","unstructured":"Chang, H.-Y., Liu, A.-S., Lin, Y.-T., Liu, C.-C., Lee, L.-E., Chen, F.-Y., Hung, S.-H., Fu, L.-C.: Self-supervised guided modality disentangled representation learning for multimodal sentiment analysis and schizophrenia assessment. IEEE J. Biomed. Health Inform. 30(2), 1630\u20131641 (2026). https:\/\/doi.org\/10.1109\/JBHI.2025.3604933","journal-title":"IEEE J. Biomed. Health Inform."},{"key":"2592_CR7","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. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 5666\u20135675. Association for Computational Linguistics (2021)","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"2592_CR8","doi-asserted-by":"publisher","first-page":"1046","DOI":"10.1109\/LSP.2021.3078698","volume":"28","author":"M Ren","year":"2021","unstructured":"Ren, M., Huang, X., Shi, X., Nie, W.: Interactive multimodal attention network for emotion recognition in conversation. IEEE Signal Process. Lett. 28, 1046\u20131050 (2021). https:\/\/doi.org\/10.1109\/LSP.2021.3078698","journal-title":"IEEE Signal Process. Lett."},{"key":"2592_CR9","doi-asserted-by":"publisher","first-page":"6818","DOI":"10.1609\/aaai.v33i01.33016818","volume":"33","author":"N Majumder","year":"2019","unstructured":"Majumder, N., Poria, S., Hazarika, D., Mihalcea, R., Gelbukh, A., Cambria, E.: Dialoguernn: an attentive RNN for emotion detection in conversations. Proc. AAAI Conf. Artif. Intell. 33, 6818\u20136825 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33016818","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"2592_CR10","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2024.102663","volume":"114","author":"Y Zhou","year":"2025","unstructured":"Zhou, Y., Liang, X., Chen, H., Zhao, Y., Chen, X., Yu, L.: Triple disentangled representation learning for multimodal affective analysis. Inform. Fusion 114, 102663 (2025). https:\/\/doi.org\/10.1016\/j.inffus.2024.102663","journal-title":"Inform. Fusion"},{"key":"2592_CR11","doi-asserted-by":"publisher","DOI":"10.1109\/ICASSP49660.2025.10889156","author":"X Wang","year":"2025","unstructured":"Wang, X., Zhao, S., Sun, H., Wang, H., Zhou, J., Qin, Y.: Enhancing multimodal emotion recognition through multi-granularity cross-modal alignment. IEEE Int. Conf. Acoust. Speech Signal Process. (2025). https:\/\/doi.org\/10.1109\/ICASSP49660.2025.10889156","journal-title":"IEEE Int. Conf. Acoust. Speech Signal Process."},{"key":"2592_CR12","doi-asserted-by":"publisher","first-page":"154","DOI":"10.18653\/v1\/D19-1015","volume-title":"Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP)","author":"D Ghosal","year":"2019","unstructured":"Ghosal, D., Majumder, N., Poria, S., Chhaya, N., Gelbukh, A., Inui, K., Jiang, J., Ng, V.: DialogueGCN: a graph convolutional neural network for emotion recognition in conversation. In: Wan, X. (ed.) Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP), pp. 154\u2013164. Association for Computational Linguistics, Hong Kong (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1015"},{"key":"2592_CR13","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.108861","volume":"248","author":"Q Gao","year":"2022","unstructured":"Gao, Q., Cao, B., Guan, X., Gu, T., Bao, X., Wu, J., Liu, B., Cao, J.: Emotion recognition in conversations with emotion shift detection based on multi-task learning. Knowl. Based Syst. 248, 108861 (2022). https:\/\/doi.org\/10.1016\/j.knosys.2022.108861","journal-title":"Knowl. Based Syst."},{"key":"2592_CR14","doi-asserted-by":"publisher","first-page":"1895","DOI":"10.1109\/LSP.2025.3562827","volume":"32","author":"N Jia","year":"2025","unstructured":"Jia, N., Bai, Z., Xiong, T., Guo, M.: Multilevel representation disentanglement framework for multimodal sentiment analysis. IEEE Signal Process. Lett. 32, 1895\u20131899 (2025). https:\/\/doi.org\/10.1109\/LSP.2025.3562827","journal-title":"IEEE Signal Process. Lett."},{"key":"2592_CR15","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52729.2023.00643","author":"Y Li","year":"2023","unstructured":"Li, Y., Wang, Y., Cui, Z.: Decoupled multimodal distilling for emotion recognition. Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn. (2023). https:\/\/doi.org\/10.1109\/CVPR52729.2023.00643","journal-title":"Proc. IEEE\/CVF Conf. Comput. Vis. Pattern Recogn."},{"key":"2592_CR16","doi-asserted-by":"publisher","first-page":"1103","DOI":"10.18653\/v1\/D17-1115","volume-title":"Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing","author":"A Zadeh","year":"2017","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.-P.: Tensor fusion network for multimodal sentiment analysis. In: Palmer, M., Hwa, R., Riedel, S. (eds.) Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, pp. 1103\u20131114. Association for Computational Linguistics, Copenhagen (2017). https:\/\/doi.org\/10.18653\/v1\/D17-1115"},{"key":"2592_CR17","doi-asserted-by":"publisher","first-page":"2247","DOI":"10.18653\/v1\/P18-1209","volume-title":"Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"Z Liu","year":"2018","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., Liang, P.P., Bagher-Zadeh, A., Morency, L.-P.: Efficient low-rank multimodal fusion with modality-specific factors. In: Gurevych, I., Miyao, Y. (eds.) Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 2247\u20132256. Association for Computational Linguistics, Melbourne (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1209"},{"key":"2592_CR18","doi-asserted-by":"publisher","first-page":"6558","DOI":"10.18653\/v1\/P19-1656","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"Y-HH Tsai","year":"2019","unstructured":"Tsai, Y.-H.H., Bai, S., Liang, P.P., Kolter, J.Z., Morency, L.-P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 6558\u20136569. Association for Computational Linguistics, Florence (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1656"},{"key":"2592_CR19","doi-asserted-by":"publisher","first-page":"7042","DOI":"10.18653\/v1\/2021.acl-long.547","volume-title":"Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers)","author":"D Hu","year":"2021","unstructured":"Hu, D., Wei, L., Huai, X.: DialogueCRN: contextual reasoning networks for emotion recognition in conversations. In: Zong, C., Xia, F., Li, W., Navigli, R. (eds.) Proceedings of the 59th Annual Meeting of the Association for Computational Linguistics and the 11th International Joint Conference on Natural Language Processing (Volume 1: Long Papers), pp. 7042\u20137052. Association for Computational Linguistics (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.547"},{"key":"2592_CR20","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2311.11009","author":"D Li","year":"2023","unstructured":"Li, D., Wang, Y., Funakoshi, K., Okumura, M.: Joyful: joint modality fusion and graph contrastive learning for multimodal emotion recognition. Arxiv (2023). https:\/\/doi.org\/10.48550\/arXiv.2311.11009","journal-title":"Arxiv"},{"key":"2592_CR21","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106764","volume":"181","author":"C Fu","year":"2025","unstructured":"Fu, C., Qian, F., Su, K., Su, Y., Wang, Z., Shi, J., Liu, Z., Liu, C., Ishi, C.T.: Himul-lgg: a hierarchical decision fusion-based local-global graph neural network for multimodal emotion recognition in conversation. Neural Netw. 181, 106764 (2025). https:\/\/doi.org\/10.1016\/j.neunet.2024.106764","journal-title":"Neural Netw."},{"key":"2592_CR22","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2407.21536","author":"J Li","year":"2025","unstructured":"Li, J., Wang, X., Zeng, Z.: Tracing intricate cues in dialogue: joint graph structure and sentiment dynamics for multimodal emotion recognition. Arxiv (2025). https:\/\/doi.org\/10.48550\/arXiv.2407.21536","journal-title":"Arxiv"},{"key":"2592_CR23","doi-asserted-by":"publisher","DOI":"10.1016\/j.inffus.2026.104436","author":"X Zhuang","year":"2026","unstructured":"Zhuang, X., Li, Z., Zhou, F., Zhang, C., Ma, H.: Mpf: a multi-level perceiving framework for multimodal sarcasm detection. Inform. Fusion (2026). https:\/\/doi.org\/10.1016\/j.inffus.2026.104436","journal-title":"Inform. Fusion"},{"key":"2592_CR24","doi-asserted-by":"publisher","first-page":"1122","DOI":"10.1145\/3394171.3413678","volume-title":"Proceedings of the 28th ACM International Conference on Multimedia MM 20","author":"D Hazarika","year":"2020","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 MM 20, pp. 1122\u20131131. Association for Computing Machinery, New York (2020). https:\/\/doi.org\/10.1145\/3394171.3413678"},{"key":"2592_CR25","doi-asserted-by":"crossref","unstructured":"Che, X., Wang, W., Guan, J., Zhao, Q.: Orthogonal disentanglement with projected feature alignment for multimodal emotion recognition in conversation (2026). arXiv. 2511.22463","DOI":"10.1109\/CISAT71030.2026.11682622"},{"issue":"12","key":"2592_CR26","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1145\/3627806","volume":"22","author":"Z Jia","year":"2023","unstructured":"Jia, Z., Shi, Y., Liu, W., Huang, Z., Sun, X.: Speaker-aware interactive graph attention network for emotion recognition in conversation. ACM Trans. Asian Low-Resour. Lang. Inf. Process. 22(12), 1\u201318 (2023). https:\/\/doi.org\/10.1145\/3627806","journal-title":"ACM Trans. Asian Low-Resour. Lang. Inf. Process."},{"issue":"2","key":"2592_CR27","doi-asserted-by":"publisher","first-page":"81","DOI":"10.1007\/s00530-024-01618-z","volume":"31","author":"J Peng","year":"2025","unstructured":"Peng, J., Tang, H., Zheng, W.: Hierarchical heterogeneous graph network based multimodal emotion recognition in conversation. Multimed. Syst. 31(2), 81 (2025). https:\/\/doi.org\/10.1007\/s00530-024-01618-z","journal-title":"Multimed. Syst."},{"key":"2592_CR28","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2026.115484","author":"B Yu","year":"2026","unstructured":"Yu, B., Wang, J., Li, C., Xi, Z., Zhao, X., Li, Y.: Graph-prototype distillation with prototype-guided contrastive training for multimodal emotion recognition in conversations. Knowl. Based Syst. (2026). https:\/\/doi.org\/10.1016\/j.knosys.2026.115484","journal-title":"Knowl. Based Syst."},{"key":"2592_CR29","doi-asserted-by":"publisher","first-page":"7837","DOI":"10.18653\/v1\/2022.emnlp-main.534","volume-title":"Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing","author":"G Hu","year":"2022","unstructured":"Hu, G., Lin, T.-E., Zhao, Y., Lu, G., Wu, Y., Li, Y.: UniMSE: towards unified multimodal sentiment analysis and emotion recognition. In: Goldberg, Y., Kozareva, Z., Zhang, Y. (eds.) Proceedings of the 2022 Conference on Empirical Methods in Natural Language Processing, pp. 7837\u20137851. Association for Computational Linguistics, Abu Dhabi (2022). https:\/\/doi.org\/10.18653\/v1\/2022.emnlp-main.534"},{"key":"2592_CR30","doi-asserted-by":"publisher","first-page":"5723","DOI":"10.63317\/3ko93pgsaxw7","volume-title":"Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024)","author":"Z Jian","year":"2024","unstructured":"Jian, Z., Wang, A., Su, J., Yao, J., Wang, M., Wu, Q.: EmoTrans: emotional transition-based model for emotion recognition in conversation. In: Calzolari, N., Kan, M.-Y., Hoste, V., Lenci, A., Sakti, S., Xue, N. (eds.) Proceedings of the 2024 Joint International Conference on Computational Linguistics, Language Resources and Evaluation (LREC-COLING 2024), pp. 5723\u20135733. ELRA and ICCL, Torino (2024)"},{"key":"2592_CR31","doi-asserted-by":"publisher","DOI":"10.48550\/arxiv.2409.00143","author":"G Xu","year":"2024","unstructured":"Xu, G., Song, Z., Xue, J., Liu, Y., Wang, Z., Zhang, Z.: Invariant representation guided multimodal sentiment decoding with sequential variation regularization. Arxiv (2024). https:\/\/doi.org\/10.48550\/arxiv.2409.00143","journal-title":"Arxiv"},{"issue":"4","key":"2592_CR32","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., Kazemzadeh, A., Mower, E., Kim, S., Chang, J.N., Lee, S., Narayanan, S.S.: Iemocap: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42(4), 335\u2013359 (2008). https:\/\/doi.org\/10.1007\/s10579-008-9076-6","journal-title":"Lang. Resour. Eval."},{"key":"2592_CR33","doi-asserted-by":"publisher","first-page":"527","DOI":"10.18653\/v1\/P19-1050","volume-title":"Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics","author":"S Poria","year":"2019","unstructured":"Poria, S., Hazarika, D., Majumder, N., Naik, G., Cambria, E., Mihalcea, R.: MELD: a multimodal multi-party dataset for emotion recognition in conversations. In: Korhonen, A., Traum, D., M\u00e0rquez, L. (eds.) Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, pp. 527\u2013536. Association for Computational Linguistics, Florence (2019). https:\/\/doi.org\/10.18653\/v1\/P19-1050"},{"key":"2592_CR34","doi-asserted-by":"publisher","DOI":"10.18653\/v1\/P18-1208","author":"A Zadeh","year":"2018","unstructured":"Zadeh, A., Liang, P.P., Poria, S., Cambria, E., Morency, L.-P.: Multimodal language analysis in the wild: CMU-MOSEI dataset and interpretable dynamic fusion graph. Annu. Meet. Assoc. Comput. Linguist. (2018). https:\/\/doi.org\/10.18653\/v1\/P18-1208","journal-title":"Annu. Meet. Assoc. Comput. Linguist."},{"key":"2592_CR35","doi-asserted-by":"publisher","first-page":"247","DOI":"10.1145\/3536221.3556630","volume-title":"Proceedings of the 2022 International Conference on Multimodal Interaction ICMI","author":"Y Liu","year":"2022","unstructured":"Liu, Y., Yuan, Z., Mao, H., Liang, Z., Yang, W., Qiu, Y., Cheng, T., Li, X., Xu, H., Gao, K.: Make acoustic and visual cues matter: Ch-sims v.20 dataset and av-mixup consistent module. In: Proceedings of the 2022 International Conference on Multimodal Interaction ICMI, pp. 247\u2013258. Association for Computing Machinery, New York (2022). https:\/\/doi.org\/10.1145\/3536221.3556630"},{"key":"2592_CR36","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2102.04830","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. CoRR (2021). https:\/\/doi.org\/10.48550\/arXiv.2102.04830","journal-title":"CoRR"},{"key":"2592_CR37","doi-asserted-by":"publisher","first-page":"4148","DOI":"10.18653\/v1\/2022.naacl-main.306","volume-title":"Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies","author":"A Joshi","year":"2022","unstructured":"Joshi, A., Bhat, A., Jain, A., Singh, A., Modi, A.: COGMEN: contextualized GNN based multimodal emotion recognition. In: Carpuat, M., Marneffe, M.-C., Meza Ruiz, I.V. (eds.) Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4148\u20134164. Association for Computational Linguistics, Seattle (2022). https:\/\/doi.org\/10.18653\/v1\/2022.naacl-main.306"},{"key":"2592_CR38","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/TMM.2023.3260635","volume":"26","author":"J Li","year":"2024","unstructured":"Li, J., Wang, X., Lv, G., Zeng, Z.: Graphcfc: a directed graph based cross-modal feature complementation approach for multimodal conversational emotion recognition. IEEE Trans. Multimed. 26, 77\u201389 (2024). https:\/\/doi.org\/10.1109\/TMM.2023.3260635","journal-title":"IEEE Trans. Multimed."},{"key":"2592_CR39","doi-asserted-by":"publisher","first-page":"10835","DOI":"10.18653\/v1\/2023.acl-long.606","volume-title":"Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers)","author":"D Hu","year":"2023","unstructured":"Hu, D., Bao, Y., Wei, L., Zhou, W., Hu, S.: Supervised adversarial contrastive learning for emotion recognition in conversations. In: Rogers, A., Boyd-Graber, J., Okazaki, N. (eds.) Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (Volume 1: Long Papers), pp. 10835\u201310852. Association for Computational Linguistics, Toronto (2023). https:\/\/doi.org\/10.18653\/v1\/2023.acl-long.606"},{"key":"2592_CR40","doi-asserted-by":"publisher","DOI":"10.48550\/arXiv.2203.02385","author":"D Hu","year":"2022","unstructured":"Hu, D., Hou, X., Wei, L., Jiang, L., Mo, Y.: MM-DFN: multimodal dynamic fusion network for emotion recognition in conversations. Arxiv (2022). https:\/\/doi.org\/10.48550\/arXiv.2203.02385","journal-title":"Arxiv"},{"issue":"3","key":"2592_CR41","doi-asserted-by":"publisher","first-page":"4908","DOI":"10.1109\/TNNLS.2024.3367940","volume":"36","author":"W Ai","year":"2025","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. 36(3), 4908\u20134921 (2025). https:\/\/doi.org\/10.1109\/TNNLS.2024.3367940","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"2592_CR42","doi-asserted-by":"publisher","DOI":"10.1109\/CVPR52734.2025.01335","author":"Y Fang","year":"2025","unstructured":"Fang, Y., Huang, W., Wan, G., Su, K., Ye, M.: Emoe: modality-specific enhanced dynamic emotion experts. IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR) (2025). https:\/\/doi.org\/10.1109\/CVPR52734.2025.01335","journal-title":"IEEE\/CVF Conf. Comput. Vis. Pattern Recognit. (CVPR)"},{"key":"2592_CR43","doi-asserted-by":"publisher","DOI":"10.1016\/j.patcog.2022.109259","volume":"136","author":"D Wang","year":"2023","unstructured":"Wang, D., Guo, X., Tian, Y., Liu, J., He, L., Luo, X.: Tetfn: a text enhanced transformer fusion network for multimodal sentiment analysis. Pattern Recognit. 136, 109259 (2023). https:\/\/doi.org\/10.1016\/j.patcog.2022.109259","journal-title":"Pattern Recognit."},{"key":"2592_CR44","doi-asserted-by":"publisher","first-page":"4909","DOI":"10.1109\/TMM.2022.3183830","volume":"25","author":"D Wang","year":"2023","unstructured":"Wang, D., Liu, S., Wang, Q., Tian, Y., He, L., Gao, X.: Cross-modal enhancement network for multimodal sentiment analysis. IEEE Trans. Multimed. 25, 4909\u20134921 (2023). https:\/\/doi.org\/10.1109\/TMM.2022.3183830","journal-title":"IEEE Trans. Multimed."}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02592-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-026-02592-4","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-026-02592-4.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,9,15]],"date-time":"2026-09-15T09:13:18Z","timestamp":1789463598000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-026-02592-4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,8,18]]},"references-count":44,"journal-issue":{"issue":"8","published-print":{"date-parts":[[2026,9]]}},"alternative-id":["2592"],"URL":"https:\/\/doi.org\/10.1007\/s00530-026-02592-4","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"value":"0942-4962","type":"print"},{"value":"1432-1882","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,8,18]]},"assertion":[{"value":"9 May 2026","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"26 July 2026","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"18 August 2026","order":3,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"The authors declare no conflict of interest.","order":1,"name":"Ethics","label":"Conflict of interest","group":{"name":"EthicsHeading","label":"Declarations"}}],"article-number":"523"}}