{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T10:28:40Z","timestamp":1761388120666,"version":"build-2065373602"},"reference-count":49,"publisher":"Springer Science and Business Media LLC","issue":"5","license":[{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T00:00:00Z","timestamp":1755734400000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"}],"funder":[{"name":"National Science and Technology Major Project,China","award":["2022ZD0118002","2022ZD0118002","2022ZD0118002","2022ZD0118002","2022ZD0118002","2022ZD0118002","2022ZD0118002"],"award-info":[{"award-number":["2022ZD0118002","2022ZD0118002","2022ZD0118002","2022ZD0118002","2022ZD0118002","2022ZD0118002","2022ZD0118002"]}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Multimedia Systems"],"published-print":{"date-parts":[[2025,10]]},"DOI":"10.1007\/s00530-025-01925-z","type":"journal-article","created":{"date-parts":[[2025,8,21]],"date-time":"2025-08-21T10:48:28Z","timestamp":1755773308000},"update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A cross-modal fusion network based on dual attention mechanism for emotion recognition in conversation"],"prefix":"10.1007","volume":"31","author":[{"given":"Xinheng","family":"Wang","sequence":"first","affiliation":[]},{"given":"Lun","family":"Xie","sequence":"additional","affiliation":[]},{"given":"Chiqin","family":"Li","sequence":"additional","affiliation":[]},{"given":"Mengsheng","family":"Wang","sequence":"additional","affiliation":[]},{"given":"Ziyang","family":"Liu","sequence":"additional","affiliation":[]},{"given":"Xiaolan","family":"Peng","sequence":"additional","affiliation":[]},{"given":"Zhiliang","family":"Wang","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2025,8,21]]},"reference":[{"key":"1925_CR1","doi-asserted-by":"publisher","unstructured":"Peng, X., Xie, X., Huang, J., et al.: ChallengeDetect: investigating the potential of detecting In-game challenge experience from physiological measures. In: Proceedings of the 2023 CHI Conference on Human Factors in Computing Systems. Association for Computing Machinery, New York, NY, USA, pp 1\u201329 (2023). https:\/\/doi.org\/10.1145\/3544548.3581232","DOI":"10.1145\/3544548.3581232"},{"key":"1925_CR2","doi-asserted-by":"publisher","first-page":"2112","DOI":"10.1109\/TAFFC.2024.3399328","volume":"15","author":"Y Gu","year":"2024","unstructured":"Gu, Y., Weng, Y., Wang, Y., et al.: EmoTake: exploring drivers\u2019 emotion for takeover behavior prediction. IEEE Trans. Affect. Comput. 15, 2112\u20132127 (2024). https:\/\/doi.org\/10.1109\/TAFFC.2024.3399328","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1925_CR3","doi-asserted-by":"publisher","first-page":"17","DOI":"10.1109\/TAFFC.2022.3205919","volume":"14","author":"J Hu","year":"2023","unstructured":"Hu, J., Huang, Y., Hu, X., Xu, Y.: The acoustically emotion-aware conversational agent with speech emotion recognition and empathetic responses. IEEE Trans. Affect. Comput. 14, 17\u201330 (2023). https:\/\/doi.org\/10.1109\/TAFFC.2022.3205919","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1925_CR4","doi-asserted-by":"publisher","first-page":"32","DOI":"10.1109\/79.911197","volume":"18","author":"R Cowie","year":"2001","unstructured":"Cowie, R., Douglas-Cowie, E., Tsapatsoulis, N., et al.: Emotion recognition in human-computer interaction. IEEE Signal Process. Mag. 18, 32\u201380 (2001). https:\/\/doi.org\/10.1109\/79.911197","journal-title":"IEEE Signal Process. Mag."},{"key":"1925_CR5","doi-asserted-by":"publisher","unstructured":"Majumder, N., Poria, S., Hazarika, D., et al.: DialogueRNN: an attentive RNN for emotion detection in conversations. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence. AAAI Press, Honolulu, Hawaii, USA, pp 6818\u20136825 (2019). https:\/\/doi.org\/10.1609\/aaai.v33i01.33016818","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"1925_CR6","doi-asserted-by":"publisher","unstructured":"Ghosal, D., Majumder, N., Poria, S., et al.: DialogueGCN: a graph convolutional neural network for emotion recognition in conversation. In: Proceedings of the 2019 Conference on Empirical Methods in Natural Language Processing and the 9th International Joint Conference on Natural Language Processing (EMNLP-IJCNLP). Association for Computational Linguistics, Hong Kong, China, pp 154\u2013164 (2019). https:\/\/doi.org\/10.18653\/v1\/D19-1015","DOI":"10.18653\/v1\/D19-1015"},{"key":"1925_CR7","doi-asserted-by":"publisher","first-page":"1301","DOI":"10.1109\/JSTSP.2017.2764438","volume":"11","author":"P Tzirakis","year":"2017","unstructured":"Tzirakis, P., Trigeorgis, G., Nicolaou, M.A., et al.: End-to-end multimodal emotion recognition using deep neural networks. IEEE J Sel Topics Signal Process 11, 1301\u20131309 (2017). https:\/\/doi.org\/10.1109\/JSTSP.2017.2764438","journal-title":"IEEE J Sel Topics Signal Process"},{"key":"1925_CR8","doi-asserted-by":"publisher","DOI":"10.1016\/j.engappai.2024.108413","author":"C Li","year":"2024","unstructured":"Li, C., Xie, L., Shao, X., et al.: A multimodal shared network with a cross-modal distribution constraint for continuous emotion recognition. Eng. Appl. Artif. Intell. (2024). https:\/\/doi.org\/10.1016\/j.engappai.2024.108413","journal-title":"Eng. Appl. Artif. Intell."},{"key":"1925_CR9","doi-asserted-by":"publisher","unstructured":"Hazarika, D., Poria, S., Zadeh, A., et al.: Conversational memory network for emotion recognition in dyadic dialogue videos. In: Walker M, Ji H, Stent A (eds) Proceedings of the 2018 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long Papers). Association for Computational Linguistics, New Orleans, Louisiana, pp 2122\u20132132 (2018). https:\/\/doi.org\/10.18653\/v1\/N18-1193","DOI":"10.18653\/v1\/N18-1193"},{"key":"1925_CR10","doi-asserted-by":"publisher","unstructured":"Hazarika, D., Poria, S., Mihalcea, R., et al.: ICON: interactive conversational memory network for multimodal emotion detection. In: Riloff E, Chiang D, Hockenmaier J, Tsujii J (eds) Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing. Association for Computational Linguistics, Brussels, Belgium, pp 2594\u20132604 (2018).https:\/\/doi.org\/10.18653\/v1\/D18-1280","DOI":"10.18653\/v1\/D18-1280"},{"key":"1925_CR11","doi-asserted-by":"publisher","unstructured":"Zheng, C., Xu, H., Sun, X.: MHG-ERC: multi-hypergraph feature aggregation network for emotion recognition in conversations. ACM Trans, Asian Low-Resour, Lang, Inf, Process, 22:238:1\u2013238:22 (2023). https:\/\/doi.org\/10.1145\/3622935","DOI":"10.1145\/3622935"},{"key":"1925_CR12","doi-asserted-by":"publisher","first-page":"4298","DOI":"10.1109\/TASLP.2024.3434495","volume":"32","author":"T Meng","year":"2024","unstructured":"Meng, T., Zhang, F., Shou, Y., et al.: Masked graph learning with recurrent alignment for multimodal emotion recognition in conversation. IEEE\/ACM Trans. Audio Speech Lang. Process 32, 4298\u20134312 (2024). https:\/\/doi.org\/10.1109\/TASLP.2024.3434495","journal-title":"IEEE\/ACM Trans. Audio Speech Lang. Process"},{"key":"1925_CR13","doi-asserted-by":"publisher","first-page":"776","DOI":"10.1109\/TMM.2023.3271019","volume":"26","author":"H Ma","year":"2024","unstructured":"Ma, H., Wang, J., Lin, H., et al.: A transformer-based model with self-distillation for multimodal emotion recognition in conversations. IEEE Trans. Multimedia 26, 776\u2013788 (2024). https:\/\/doi.org\/10.1109\/TMM.2023.3271019","journal-title":"IEEE Trans. Multimedia"},{"key":"1925_CR14","unstructured":"Sutskever, I., Vinyals, O., Le, Q.V.: Sequence to sequence learning with neural networks. In: Proceedings of the 27th International Conference on Neural Information Processing Systems - Volume 2. MIT Press, Cambridge, MA, USA, pp 3104\u20133112 (2014)"},{"key":"1925_CR15","unstructured":"Vaswani, A., Shazeer, N., Parmar, N., et al.: Attention is all you need. In: Proceedings of the 31st International Conference on Neural Information Processing Systems. Curran Associates Inc., Red Hook, NY, USA, pp 6000\u20136010 (2017)"},{"key":"1925_CR16","doi-asserted-by":"publisher","first-page":"10591","DOI":"10.1109\/TNNLS.2023.3243000","volume":"35","author":"R Liu","year":"2024","unstructured":"Liu, R., Huang, Z.-A., Hu, Y., et al.: Spatial\u2013temporal Co-attention learning for diagnosis of mental disorders from resting-state fMRI data. IEEE Trans. Neural Netw. Learn. Syst. 35, 10591\u201310605 (2024). https:\/\/doi.org\/10.1109\/TNNLS.2023.3243000","journal-title":"IEEE Trans. Neural Netw. Learn. Syst."},{"key":"1925_CR17","doi-asserted-by":"publisher","unstructured":"Jiao, W., Yang, H., King, I., Lyu, M.R.: HiGRU: hierarchical gated recurrent units for utterance-level emotion recognition. In: Proceedings of the 2019 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, Volume 1 (Long and Short Papers). Association for Computational Linguistics, Minneapolis, Minnesota, pp 397\u2013406 (2019). https:\/\/doi.org\/10.18653\/v1\/N19-1037","DOI":"10.18653\/v1\/N19-1037"},{"key":"1925_CR18","doi-asserted-by":"publisher","first-page":"8002","DOI":"10.1609\/aaai.v34i05.6309","volume":"34","author":"W Jiao","year":"2020","unstructured":"Jiao, W., Lyu, M., King, I.: Real-time emotion recognition via attention gated hierarchical memory network. Proc. AAAI Conf. Artif. Intell. 34, 8002\u20138009 (2020). https:\/\/doi.org\/10.1609\/aaai.v34i05.6309","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"1925_CR19","doi-asserted-by":"publisher","unstructured":"Poria, S., Cambria, E., Hazarika, D., et al.: 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). Association for Computational Linguistics, Vancouver, Canada, pp 873\u2013883 (2017). https:\/\/doi.org\/10.18653\/v1\/P17-1081","DOI":"10.18653\/v1\/P17-1081"},{"key":"1925_CR20","doi-asserted-by":"publisher","DOI":"10.1016\/j.neucom.2023.126427","author":"J Li","year":"2023","unstructured":"Li, J., Wang, X., Lv, G., Zeng, Z.: GraphMFT: a graph network based multimodal fusion technique for emotion recognition in conversation. Neurocomput (2023). https:\/\/doi.org\/10.1016\/j.neucom.2023.126427","journal-title":"Neurocomput"},{"key":"1925_CR21","doi-asserted-by":"publisher","unstructured":"Hu, J., Liu, Y., Zhao, J., Jin, Q.: MMGCN: multimodal fusion via deep graph convolution network for emotion recognition in conversation. In: 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). Association for Computational Linguistics, Online, pp 5666\u20135675 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.acl-long.440","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"1925_CR22","doi-asserted-by":"publisher","unstructured":"Mao, Y., Liu, G., Wang, X., et al.: DialogueTRM: exploring multi-modal emotional dynamics in a conversation. In: Findings of the Association for Computational Linguistics: EMNLP 2021. Association for Computational Linguistics, Punta Cana, Dominican Republic, pp 2694\u20132704 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.findings-emnlp.229","DOI":"10.18653\/v1\/2021.findings-emnlp.229"},{"key":"1925_CR23","doi-asserted-by":"publisher","unstructured":"Li, Z., Tang, F., Zhao, M., Zhu, Y.: EmoCaps: emotion capsule based model for conversational emotion recognition. In: Findings of the Association for Computational Linguistics: ACL 2022. Association for Computational Linguistics, Dublin, Ireland, pp 1610\u20131618 (2022). https:\/\/doi.org\/10.18653\/v1\/2022.findings-acl.126","DOI":"10.18653\/v1\/2022.findings-acl.126"},{"key":"1925_CR24","doi-asserted-by":"publisher","DOI":"10.1016\/j.knosys.2022.109978","volume":"258","author":"S Zou","year":"2022","unstructured":"Zou, S., Huang, X., Shen, X., Liu, H.: Improving multimodal fusion with main modal transformer for emotion recognition in conversation. Knowl.-Based Syst. 258, 109978 (2022). https:\/\/doi.org\/10.1016\/j.knosys.2022.109978","journal-title":"Knowl.-Based Syst."},{"key":"1925_CR25","doi-asserted-by":"publisher","unstructured":"Rahman, W., Hasan, M.K., Lee, S., et al.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics, Online, pp 2359\u20132369. (2020) https:\/\/doi.org\/10.18653\/v1\/2020.acl-main.214","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"1925_CR26","doi-asserted-by":"publisher","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. Association for Computing Machinery, New York, NY, USA, pp 521\u2013528. (2020) https:\/\/doi.org\/10.1145\/3394171.3413690","DOI":"10.1145\/3394171.3413690"},{"key":"1925_CR27","doi-asserted-by":"publisher","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. Association for Computational Linguistics, Online and Punta Cana, Dominican Republic, pp 9180\u20139192 (2021). https:\/\/doi.org\/10.18653\/v1\/2021.emnlp-main.723","DOI":"10.18653\/v1\/2021.emnlp-main.723"},{"key":"1925_CR28","doi-asserted-by":"publisher","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. Association for Computing Machinery, New York, NY, USA, pp 1122\u20131131. https:\/\/doi.org\/10.1145\/3394171.3413678 (2020)","DOI":"10.1145\/3394171.3413678"},{"key":"1925_CR29","doi-asserted-by":"publisher","DOI":"10.1109\/TCSVT.2023.3332814","author":"M Yang","year":"2023","unstructured":"Yang, M., Gao, Y., Tang, L., et al.: Wearable eye-tracking system for synchronized multimodal data acquisition. IEEE Trans. Circ. Syst. Video Technol. (2023). https:\/\/doi.org\/10.1109\/TCSVT.2023.3332814","journal-title":"IEEE Trans. Circ. Syst. Video Technol."},{"key":"1925_CR30","doi-asserted-by":"publisher","first-page":"13292","DOI":"10.1109\/TMC.2024.3425928","volume":"23","author":"Y Li","year":"2024","unstructured":"Li, Y., Bai, X., Xie, L., et al.: Real-time gaze tracking via head-eye cues on head mounted devices. IEEE Trans. Mobile Comput. 23, 13292\u201313309 (2024). https:\/\/doi.org\/10.1109\/TMC.2024.3425928","journal-title":"IEEE Trans. Mobile Comput."},{"key":"1925_CR31","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2023.122666","volume":"241","author":"S Islam","year":"2024","unstructured":"Islam, S., Elmekki, H., Elsebai, A., et al.: A comprehensive survey on applications of transformers for deep learning tasks. Expert Syst. Appl. 241, 122666 (2024). https:\/\/doi.org\/10.1016\/j.eswa.2023.122666","journal-title":"Expert Syst. Appl."},{"key":"1925_CR32","unstructured":"Katharopoulos, A., Vyas, A., Pappas, N., Fleuret, F.: Transformers are RNNs: fast autoregressive transformers with linear attention. In: Proceedings of the 37th International Conference on Machine Learning. JMLR.org, pp 5156\u20135165 (2020)"},{"key":"1925_CR33","unstructured":"Child, R., Gray, S., Radford, A., et al.: (2019) Generating long sequences with sparse transformers. arXiv preprint arXiv:1904.10509."},{"key":"1925_CR34","doi-asserted-by":"publisher","first-page":"5436","DOI":"10.1109\/TPAMI.2022.3211006","volume":"45","author":"M-H Guo","year":"2023","unstructured":"Guo, M.-H., Liu, Z.-N., Mu, T.-J., Hu, S.-M.: Beyond self-attention: external attention using two linear layers for visual tasks. IEEE Trans. Pattern Anal. Mach. Intell. 45, 5436\u20135447 (2023). https:\/\/doi.org\/10.1109\/TPAMI.2022.3211006","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1925_CR35","doi-asserted-by":"publisher","DOI":"10.1109\/TAFFC.2024.3498443","author":"Y Shou","year":"2024","unstructured":"Shou, Y., Liu, H., Cao, X., et al.: A low-rank matching attention based cross-modal feature fusion method for conversational emotion recognition. IEEE Trans. Affect. Comput. (2024). https:\/\/doi.org\/10.1109\/TAFFC.2024.3498443","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1925_CR36","doi-asserted-by":"publisher","DOI":"10.1016\/j.ins.2023.120007","volume":"657","author":"W Ding","year":"2024","unstructured":"Ding, W., Sun, Y., Huang, J., et al.: RCAR-UNet: retinal vessel segmentation network algorithm via novel rough attention mechanism. Inf. Sci. 657, 120007 (2024). https:\/\/doi.org\/10.1016\/j.ins.2023.120007","journal-title":"Inf. Sci."},{"key":"1925_CR37","unstructured":"Zhao, G., Sun, X., Xu, J., et al.: Muse: Parallel multi-scale attention for sequence to sequence learning. arXiv preprint arXiv:1911.09483. (2019)"},{"key":"1925_CR38","unstructured":"Huang, C.-Z.A., Vaswani, A., Uszkoreit, J., et al.: Music transformer. arXiv preprint arXiv:1809.04281. (2018)"},{"key":"1925_CR39","unstructured":"Beck, M., P\u00f6ppel, K., Spanring, M., et al.: xLSTM: extended long short-term memory. arXiv preprint arXiv:2405.04517 (2024)"},{"key":"1925_CR40","doi-asserted-by":"publisher","first-page":"1","DOI":"10.1109\/LGRS.2025.3562480","volume":"22","author":"Z Wu","year":"2025","unstructured":"Wu, Z., Ma, X., Lian, R., Zheng, K., Zhang, W.: CDxLSTM: boosting remote sensing change detection with extended long short-term memory. IEEE Geosci. Remote Sens. Lett. 22, 1\u20135 (2025). https:\/\/doi.org\/10.1109\/LGRS.2025.3562480","journal-title":"IEEE Geosci. Remote Sens. Lett."},{"key":"1925_CR41","unstructured":"Schmidinger, N., Schneckenreiter, L., Seidl, P., Schimunek, J., Hoedt, P.-J., Brandstetter, J., Mayr, A., Luukkonen, S., Hochreiter, S., Klambauer, G.: Bio-xLSTM: generative modeling, representation and in-context learning of biological and chemical sequences, (2024) http:\/\/arxiv.org\/abs\/2411.04165"},{"key":"1925_CR42","doi-asserted-by":"publisher","first-page":"1919","DOI":"10.1109\/TAFFC.2024.3389453","volume":"15","author":"J Li","year":"2024","unstructured":"Li, J., Wang, X., Liu, Y., Zeng, Z.: CFN-ESA: a cross-modal fusion network with emotion-shift awareness for dialogue emotion recognition. IEEE Trans. Affect. Comput. 15, 1919\u20131933 (2024). https:\/\/doi.org\/10.1109\/TAFFC.2024.3389453","journal-title":"IEEE Trans. Affect. Comput."},{"key":"1925_CR43","unstructured":"Zhang, Q., Yang, Y.-B.: ResT: an efficient transformer for visual recognition. In: Advances in Neural Information Processing Systems. Curran Associates, Inc., pp 15475\u201315485 (2021)"},{"key":"1925_CR44","doi-asserted-by":"publisher","first-page":"187","DOI":"10.1007\/s41095-021-0229-5","volume":"7","author":"M-H Guo","year":"2021","unstructured":"Guo, M.-H., Cai, J.-X., Liu, Z.-N., et al.: PCT: point cloud transformer. Comput Visual Media 7, 187\u2013199 (2021). https:\/\/doi.org\/10.1007\/s41095-021-0229-5","journal-title":"Comput Visual Media"},{"key":"1925_CR45","doi-asserted-by":"publisher","unstructured":"Wang, L., Wu, J., Huang, S.-L., et al.: An efficient approach to informative feature extraction from multimodal data. In: Proceedings of the Thirty-Third AAAI Conference on Artificial Intelligence and Thirty-First Innovative Applications of Artificial Intelligence Conference and Ninth AAAI Symposium on Educational Advances in Artificial Intelligence. AAAI Press, Honolulu, Hawaii, USA, pp 5281\u20135288. (2019) https:\/\/doi.org\/10.1609\/aaai.v33i01.33015281","DOI":"10.1609\/aaai.v33i01.33015281"},{"key":"1925_CR46","unstructured":"Leng, Z., Tan, M., Liu, C., et al.: Polyloss: A polynomial expansion perspective of classification loss functions. arXiv preprint arXiv:2204.12511. (2022)"},{"key":"1925_CR47","doi-asserted-by":"publisher","unstructured":"Cipolla, R., Gal, Y., Kendall, A.: Multi-task learning using uncertainty to weigh losses for scene geometry and semantics. In: 2018 IEEE\/CVF Conference on Computer Vision and Pattern Recognition. pp 7482\u20137491. (2018) https:\/\/doi.org\/10.1109\/CVPR.2018.00781","DOI":"10.1109\/CVPR.2018.00781"},{"key":"1925_CR48","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.: IEMOCAP: interactive emotional dyadic motion capture database. Lang. Resour. Eval. 42, 335\u2013359 (2008). https:\/\/doi.org\/10.1007\/s10579-008-9076-6","journal-title":"Lang. Resour. Eval."},{"key":"1925_CR49","doi-asserted-by":"publisher","unstructured":"Poria, S., Hazarika, D., Majumder, N., et al.: 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. Association for Computational Linguistics, Florence, Italy, pp 527\u2013536. (2019) https:\/\/doi.org\/10.18653\/v1\/P19-1050","DOI":"10.18653\/v1\/P19-1050"}],"container-title":["Multimedia Systems"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01925-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/article\/10.1007\/s00530-025-01925-z\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/s00530-025-01925-z.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,10,25]],"date-time":"2025-10-25T10:24:10Z","timestamp":1761387850000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/s00530-025-01925-z"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025,8,21]]},"references-count":49,"journal-issue":{"issue":"5","published-print":{"date-parts":[[2025,10]]}},"alternative-id":["1925"],"URL":"https:\/\/doi.org\/10.1007\/s00530-025-01925-z","relation":{},"ISSN":["0942-4962","1432-1882"],"issn-type":[{"type":"print","value":"0942-4962"},{"type":"electronic","value":"1432-1882"}],"subject":[],"published":{"date-parts":[[2025,8,21]]},"assertion":[{"value":"5 December 2024","order":1,"name":"received","label":"Received","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"30 June 2025","order":2,"name":"accepted","label":"Accepted","group":{"name":"ArticleHistory","label":"Article History"}},{"value":"21 August 2025","order":3,"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"}}],"article-number":"325"}}