{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,3,25]],"date-time":"2025-03-25T14:34:12Z","timestamp":1742913252476,"version":"3.40.3"},"publisher-location":"Singapore","reference-count":30,"publisher":"Springer Nature Singapore","isbn-type":[{"type":"print","value":"9789819794423"},{"type":"electronic","value":"9789819794430"}],"license":[{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springernature.com\/gp\/researchers\/text-and-data-mining"},{"start":{"date-parts":[[2024,11,1]],"date-time":"2024-11-01T00:00:00Z","timestamp":1730419200000},"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\/978-981-97-9443-0_5","type":"book-chapter","created":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:29:05Z","timestamp":1730392145000},"page":"55-68","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Cross-Modal Correlation Fusion Network for\u00a0Emotion Recognition in\u00a0Conversations"],"prefix":"10.1007","author":[{"given":"Xiaolyu","family":"Tang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Guoyong","family":"Cai","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Ming","family":"Chen","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Peicong","family":"Yuan","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2024,11,1]]},"reference":[{"issue":"4","key":"5_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(4), 335\u2013359 (2008)","journal-title":"Lang. Resour. Eval."},{"key":"5_CR2","doi-asserted-by":"crossref","unstructured":"Chen, F., Shao, J., Zhu, S., Shen, H.T.: Multivariate, multi-frequency and multimodal: rethinking graph neural networks for emotion recognition in conversation. In: CVPR, pp. 10761\u201310770 (2023)","DOI":"10.1109\/CVPR52729.2023.01036"},{"key":"5_CR3","doi-asserted-by":"crossref","unstructured":"Chudasama, V., Kar, P., Gudmalwar, A., Shah, N., Wasnik, P., Onoe, N.: M2Fnet: multi-modal fusion network for emotion recognition in conversation. In: 2022 IEEE\/CVF Conference on Computer Vision and Pattern Recognition Workshops (CVPRW), pp. 4652\u20134661 (2022)","DOI":"10.1109\/CVPRW56347.2022.00511"},{"key":"5_CR4","doi-asserted-by":"crossref","unstructured":"Eyben, F., W\u00f6llmer, M., Schuller, B.: Opensmile: the Munich versatile and fast open-source audio feature extractor. In: Proceedings of the 18th ACM International Conference on Multimedia, pp. 1459\u20131462 (2010)","DOI":"10.1145\/1873951.1874246"},{"key":"5_CR5","doi-asserted-by":"crossref","unstructured":"Hazarika, D., Poria, S., Mihalcea, R., Cambria, E., Zimmermann, R.: ICON: interactive conversational memory network for multimodal emotion detection. In: EMNLP, pp. 2594\u20132604 (2018)","DOI":"10.18653\/v1\/D18-1280"},{"key":"5_CR6","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: NAACL-HLT, pp. 2122\u20132132 (2018)","DOI":"10.18653\/v1\/N18-1193"},{"key":"5_CR7","doi-asserted-by":"crossref","unstructured":"Hu, D., Hou, X., Wei, L., Jiang, L., Mo, Y.: MM-DFN: multimodal dynamic fusion network for emotion recognition in conversations. In: ICASSP, pp. 7037\u20137041 (2022)","DOI":"10.1109\/ICASSP43922.2022.9747397"},{"key":"5_CR8","doi-asserted-by":"crossref","unstructured":"Hu, G., Lin, T.E., Zhao, Y., Lu, G., Wu, Y., Li, Y.: UniMSE: towards unified multimodal sentiment analysis and emotion recognition. In: EMNLP, pp. 7837\u20137851 (2022)","DOI":"10.18653\/v1\/2022.emnlp-main.534"},{"key":"5_CR9","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: ACL-IJCNLP, pp. 5666\u20135675 (2021)","DOI":"10.18653\/v1\/2021.acl-long.440"},{"key":"5_CR10","doi-asserted-by":"crossref","unstructured":"Huang, G., Liu, Z., Van Der\u00a0Maaten, L., Weinberger, K.Q.: Densely connected convolutional networks. In: CVPR, pp. 2261\u20132269 (2017)","DOI":"10.1109\/CVPR.2017.243"},{"key":"5_CR11","unstructured":"Khosla, P., et al.: Supervised contrastive learning. In: NeurIPS, vol. 33, pp. 18661\u201318673 (2020)"},{"key":"5_CR12","unstructured":"Kim, T., Vossen, P.: EmoBERTa: speaker-aware emotion recognition in conversation with roberta. arXiv preprint arXiv:2108.12009 (2021)"},{"key":"5_CR13","unstructured":"Kingma, D.P., Ba, J.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"1","key":"5_CR14","doi-asserted-by":"publisher","first-page":"130","DOI":"10.1109\/TAFFC.2023.3261279","volume":"15","author":"J Li","year":"2024","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. Affect. Comput. 15(1), 130\u2013143 (2024)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"5_CR15","doi-asserted-by":"crossref","unstructured":"Liu, L., Zhang, Z., Zhao, H., Zhou, X., Zhou, X.: Filling the gap of utterance-aware and speaker-aware representation for multi-turn dialogue. In: AAAI, vol.\u00a035, pp. 13406\u201313414 (2021)","DOI":"10.1609\/aaai.v35i15.17582"},{"key":"5_CR16","unstructured":"Liu, Y., et al.: RoBERTa: a robustly optimized BERT pretraining approach. arXiv preprint arXiv:1907.11692 (2019)"},{"key":"5_CR17","doi-asserted-by":"crossref","unstructured":"Luo, J., Phan, H., Reiss, J.: Cross-modal fusion techniques for utterance-level emotion recognition from text and speech. In: ICASSP, pp.\u00a01\u20135 (2023)","DOI":"10.1109\/ICASSP49357.2023.10096885"},{"key":"5_CR18","doi-asserted-by":"crossref","unstructured":"Ma, F., Huang, S.L., Zhang, L.: An efficient approach for audio-visual emotion recognition with missing labels and missing modalities. In: ICME, pp.\u00a01\u20136 (2021)","DOI":"10.1109\/ICME51207.2021.9428219"},{"key":"5_CR19","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: AAAI, vol.\u00a033, pp. 6818\u20136825 (2019)","DOI":"10.1609\/aaai.v33i01.33016818"},{"key":"5_CR20","doi-asserted-by":"crossref","unstructured":"Poria, S., Cambria, E., Hazarika, D., Majumder, N., Zadeh, A., Morency, L.P.: Context-dependent sentiment analysis in user-generated videos. In: ACL, pp. 873\u2013883 (2017)","DOI":"10.18653\/v1\/P17-1081"},{"key":"5_CR21","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: ACL, pp. 527\u2013536 (2019)","DOI":"10.18653\/v1\/P19-1050"},{"issue":"140","key":"5_CR22","first-page":"1","volume":"21","author":"C Raffel","year":"2020","unstructured":"Raffel, C., et al.: Exploring the limits of transfer learning with a unified text-to-text transformer. J. Mach. Learn. Res. 21(140), 1\u201367 (2020)","journal-title":"J. Mach. Learn. Res."},{"key":"5_CR23","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 Sig. Process. Lett. 28, 1046\u20131050 (2021)","journal-title":"IEEE Sig. Process. Lett."},{"key":"5_CR24","doi-asserted-by":"crossref","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: ACL, pp. 6558\u20136569 (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"5_CR25","unstructured":"Vaswani, A., et al.: Attention is all you need. In: NIPS, vol.\u00a030, pp. 5998\u20136008 (2017)"},{"key":"5_CR26","unstructured":"Veli\u010dkovi\u0107, P., Cucurull, G., Casanova, A., Romero, A., Li\u00f2, P., Bengio, Y.: Graph attention networks. In: ICLR (2018)"},{"key":"5_CR27","doi-asserted-by":"crossref","unstructured":"Wang, L., et al.: An efficient approach to informative feature extraction from multimodal data. In: AAAI, vol.\u00a033, pp. 5281\u20135288 (2019)","DOI":"10.1609\/aaai.v33i01.33015281"},{"key":"5_CR28","doi-asserted-by":"crossref","unstructured":"Yang, B., Li, J., Wong, D.F., Chao, L.S., Wang, X., Tu, Z.: Context-aware self-attention networks. In: AAAI, vol. 33, pp. 387\u2013394 (2019)","DOI":"10.1609\/aaai.v33i01.3301387"},{"issue":"24","key":"5_CR29","doi-asserted-by":"publisher","first-page":"17619","DOI":"10.1007\/s00521-023-08638-2","volume":"35","author":"T Zhang","year":"2023","unstructured":"Zhang, T., Tan, Z., Wu, X.: HAAN-ERC: hierarchical adaptive attention network for multimodal emotion recognition in conversation. Neural Comput. Appl. 35(24), 17619\u201317632 (2023)","journal-title":"Neural Comput. Appl."},{"key":"5_CR30","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)","journal-title":"Knowl.-Based Syst."}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-981-97-9443-0_5","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,10,31]],"date-time":"2024-10-31T16:34:11Z","timestamp":1730392451000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-981-97-9443-0_5"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2024,11,1]]},"ISBN":["9789819794423","9789819794430"],"references-count":30,"URL":"https:\/\/doi.org\/10.1007\/978-981-97-9443-0_5","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2024,11,1]]},"assertion":[{"value":"1 November 2024","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"NLPCC","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"CCF International Conference on Natural Language Processing and Chinese Computing","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Hangzhou","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":"2024","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2 November 2024","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"4 November 2024","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"13","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2024","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2024\/index.php","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}}]}}