{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T06:46:48Z","timestamp":1771915608149,"version":"3.50.1"},"publisher-location":"Singapore","reference-count":24,"publisher":"Springer Nature Singapore","isbn-type":[{"value":"9789819500055","type":"print"},{"value":"9789819500062","type":"electronic"}],"license":[{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2025,1,1]],"date-time":"2025-01-01T00:00:00Z","timestamp":1735689600000},"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":[[2025]]},"DOI":"10.1007\/978-981-95-0006-2_35","type":"book-chapter","created":{"date-parts":[[2025,7,24]],"date-time":"2025-07-24T07:34:10Z","timestamp":1753342450000},"page":"413-424","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["Multi-Dimensional Spatiotemporal Modeling for Multimodal Emotion Recognition in Conversations"],"prefix":"10.1007","author":[{"given":"Xiaoyang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8199-2720","authenticated-orcid":false,"given":"Zhenyu","family":"Yang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xueli","family":"Chang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ziyu","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Haozhi","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2025,7,25]]},"reference":[{"key":"35_CR1","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."},{"key":"35_CR2","doi-asserted-by":"crossref","unstructured":"Chen, F., Shao, J., Zhu, S., Shen, H.T.: Multivariate, multi-frequency and multi-modal: Rethinking graph neural networks for emotion recognition in conversation. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 10761\u201310770 (2023)","DOI":"10.1109\/CVPR52729.2023.01036"},{"key":"35_CR3","doi-asserted-by":"crossref","unstructured":"Eyben, F., Weninger, F., Gross, F., Schuller, B.: Recent developments in opensmile, the munich open-source multimedia feature extractor. In: Proceedings of the 21st ACM International Conference on Multimedia, pp. 835\u2013838 (2013)","DOI":"10.1145\/2502081.2502224"},{"key":"35_CR4","doi-asserted-by":"crossref","unstructured":"Fitzpatrick, K., Darcy, A., Therapy, M.V.D.C.B.: To young adults with symptoms of depression and anxiety using a fully automated conversational agent (woebot): a randomized control trial. J. Med. Interest Res. Ment. Health 4(2), e19","DOI":"10.2196\/mental.7785"},{"key":"35_CR5","doi-asserted-by":"publisher","DOI":"10.1016\/j.neunet.2024.106764","volume":"181","author":"C Fu","year":"2025","unstructured":"Fu, C., et al.: Himul-lgg: a hierarchical decision fusion-based local\u2013global graph neural network for multimodal emotion recognition in conversation. Neural Netw. 181, 106764 (2025)","journal-title":"Neural Netw."},{"key":"35_CR6","doi-asserted-by":"crossref","unstructured":"Ghosal, D., Majumder, N., Poria, S., Chhaya, N., Gelbukh, A.: 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 (2019)","DOI":"10.18653\/v1\/D19-1015"},{"key":"35_CR7","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Poria, S., Zadeh, A., Cambria, E., Morency, L.P., Zimmermann, R.: Conversational memory network for emotion recognition in dyadic dialogue videos. In: Proceedings of the Conference. Association for Computational Linguistics. North American Chapter. Meeting, vol. 2018, p. 2122 (2018)","DOI":"10.18653\/v1\/N18-1193"},{"key":"35_CR8","doi-asserted-by":"crossref","unstructured":"Hu, D., Bao, Y., Wei, L., Zhou, W., Hu, S.: Supervised adversarial contrastive learning for emotion recognition in conversations. In: Proceedings of the 61st Annual Meeting of the Association for Computational Linguistics (volume 1: Long Papers), pp. 10835\u201310852 (2023)","DOI":"10.18653\/v1\/2023.acl-long.606"},{"key":"35_CR9","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, pp. 4700\u20134708 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"35_CR10","doi-asserted-by":"crossref","unstructured":"Huang, Y., Zeng, Y., Wu, Q., L\u00fc, L.: Higher-order graph convolutional network with flower-petals laplacians on simplicial complexes. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 38, pp. 12653\u201312661 (2024)","DOI":"10.1609\/aaai.v38i11.29160"},{"key":"35_CR11","doi-asserted-by":"crossref","unstructured":"Joshi, A., Bhat, A., Jain, A., Singh, A., Modi, A.: Cogmen: contextualized GNN based multimodal emotion recognition. In: Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies, pp. 4148\u20134164 (2022)","DOI":"10.18653\/v1\/2022.naacl-main.306"},{"key":"35_CR12","doi-asserted-by":"publisher","first-page":"77","DOI":"10.1109\/TMM.2023.3260635","volume":"26","author":"J Li","year":"2023","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. Multimedia 26, 77\u201389 (2023)","journal-title":"IEEE Trans. Multimedia"},{"key":"35_CR13","doi-asserted-by":"crossref","unstructured":"Li, S., Yan, H., Qiu, X.: Contrast and generation make bart a good dialogue emotion recognizer. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 36, pp. 11002\u201311010 (2022)","DOI":"10.1609\/aaai.v36i10.21348"},{"key":"35_CR14","doi-asserted-by":"publisher","first-page":"985","DOI":"10.1109\/TASLP.2021.3049898","volume":"29","author":"Z Lian","year":"2021","unstructured":"Lian, Z., Liu, B., Tao, J.: Ctnet: conversational transformer network for emotion recognition. IEEE\/ACM Trans. Audio, Speech, Lang. Process. 29, 985\u20131000 (2021)","journal-title":"IEEE\/ACM Trans. Audio, Speech, Lang. Process."},{"key":"35_CR15","unstructured":"Liu, Y., et al.: Roberta: a robustly optimized bert pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"35_CR16","doi-asserted-by":"crossref","unstructured":"Ma, H., Wang, J., Lin, H., Zhang, B., Zhang, Y., Xu, B.: A transformer-based model with self-distillation for multimodal emotion recognition in conversations. IEEE Trans. Multimedia (2023)","DOI":"10.1109\/TMM.2023.3271019"},{"key":"35_CR17","doi-asserted-by":"crossref","unstructured":"Majumder, N., Poria, S., Hazarika, D., Mihalcea, R., Gelbukh, A., Cambria, E.: Dialoguernn: an attentive RNN for emotion detection in conversations. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 6818\u20136825 (2019)","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"35_CR18","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. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1050"},{"key":"35_CR19","doi-asserted-by":"publisher","first-page":"100943","DOI":"10.1109\/ACCESS.2019.2929050","volume":"7","author":"S Poria","year":"2019","unstructured":"Poria, S., Majumder, N., Mihalcea, R., Hovy, E.: Emotion recognition in conversation: research challenges, datasets, and recent advances. IEEE access 7, 100943\u2013100953 (2019)","journal-title":"IEEE access"},{"key":"35_CR20","doi-asserted-by":"crossref","unstructured":"Shi, W., Chen, X., Yao, B., Wen, Y., Sheng, B.: Identity and modality attributes driven multimodal fusion networks for emotion recognition in conversations. IEEE Trans. Multimedia (2025)","DOI":"10.1109\/TMM.2025.3535347"},{"key":"35_CR21","doi-asserted-by":"crossref","unstructured":"Yang, H., Gao, X., Wu, J., Gan, T., Ding, N., Jiang, F., Nie, L.: Self-adaptive context and modal-interaction modeling for multimodal emotion recognition. In: Findings of the Association for Computational Linguistics: ACL 2023, pp. 6267\u20136281 (2023)","DOI":"10.18653\/v1\/2023.findings-acl.390"},{"issue":"4","key":"35_CR22","doi-asserted-by":"publisher","first-page":"3269","DOI":"10.1109\/TAFFC.2023.3243463","volume":"14","author":"K Yang","year":"2023","unstructured":"Yang, K., Zhang, T., Alhuzali, H., Ananiadou, S.: Cluster-level contrastive learning for emotion recognition in conversations. IEEE Trans. Affect. Comput. 14(4), 3269\u20133280 (2023)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"35_CR23","doi-asserted-by":"publisher","first-page":"3987","DOI":"10.1109\/TMM.2023.3238314","volume":"26","author":"D Zhang","year":"2023","unstructured":"Zhang, D., Chen, F., Chang, J., Chen, X., Tian, Q.: Structure aware multi-graph network for multi-modal emotion recognition in conversations. IEEE Trans. Multimedia 26, 3987\u20133997 (2023)","journal-title":"IEEE Trans. Multimedia"},{"issue":"3","key":"35_CR24","doi-asserted-by":"publisher","first-page":"1553","DOI":"10.1109\/TAFFC.2024.3354382","volume":"15","author":"X Zhang","year":"2024","unstructured":"Zhang, X., Cui, W., Hu, B., Li, Y.: A multi-level alignment and cross-modal unified semantic graph refinement network for conversational emotion recognition. IEEE Trans. Affect. Comput. 15(3), 1553\u20131566 (2024)","journal-title":"IEEE Trans. Affect. Comput."}],"container-title":["Lecture Notes in Computer Science","Advanced Intelligent Computing Technology and Applications"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-95-0006-2_35","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,2,24]],"date-time":"2026-02-24T02:58:59Z","timestamp":1771901939000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-95-0006-2_35"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2025]]},"ISBN":["9789819500055","9789819500062"],"references-count":24,"URL":"https:\/\/doi.org\/10.1007\/978-981-95-0006-2_35","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2025]]},"assertion":[{"value":"25 July 2025","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICIC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Intelligent Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Ningbo","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"China","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":"26 July 2025","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"29 July 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":"icic2025","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.ic-icc.cn\/icg\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}