{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2025,8,1]],"date-time":"2025-08-01T03:59:30Z","timestamp":1754020770165,"version":"3.40.3"},"publisher-location":"Cham","reference-count":19,"publisher":"Springer International Publishing","isbn-type":[{"type":"print","value":"9783030604561"},{"type":"electronic","value":"9783030604578"}],"license":[{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2020,1,1]],"date-time":"2020-01-01T00:00:00Z","timestamp":1577836800000},"content-version":"vor","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2020]]},"DOI":"10.1007\/978-3-030-60457-8_4","type":"book-chapter","created":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T20:02:57Z","timestamp":1602014577000},"page":"41-53","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Hierarchical Multimodal Transformer with Localness and Speaker Aware Attention for Emotion Recognition in\u00a0Conversations"],"prefix":"10.1007","author":[{"given":"Xiao","family":"Jin","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Jianfei","family":"Yu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Zixiang","family":"Ding","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rui","family":"Xia","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Xiangsheng","family":"Zhou","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaofeng","family":"Tu","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,2]]},"reference":[{"key":"4_CR1","unstructured":"Bahdanau, D., Cho, K., Bengio, Y.: Neural machine translation by jointly learning to align and translate. arXiv preprint \narXiv:1409.0473\n\n (2014)"},{"key":"4_CR2","unstructured":"Chen, S.Y., Hsu, C.C., Kuo, C.C., Ku, L.W., et al.: Emotionlines: an emotion corpus of multi-party conversations. arXiv preprint \narXiv:1802.08379\n\n (2018)"},{"key":"4_CR3","unstructured":"Devlin, J., Chang, M.W., Lee, K., Toutanova, K.: Bert: pre-training of deep bidirectional transformers for language understanding. arXiv preprint \narXiv:1810.04805\n\n (2018)"},{"issue":"3\u20134","key":"4_CR4","doi-asserted-by":"publisher","first-page":"169","DOI":"10.1080\/02699939208411068","volume":"6","author":"P Ekman","year":"1992","unstructured":"Ekman, P.: An argument for basic emotions. Cogn. Emotion 6(3\u20134), 169\u2013200 (1992)","journal-title":"Cogn. Emotion"},{"key":"4_CR5","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":"4_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. arXiv preprint \narXiv:1908.11540\n\n (2019)","DOI":"10.18653\/v1\/D19-1015"},{"key":"4_CR7","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: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, pp. 2594\u20132604 (2018)","DOI":"10.18653\/v1\/D18-1280"},{"key":"4_CR8","doi-asserted-by":"crossref","unstructured":"Jiao, W., Lyu, M.R., King, I.: Real-time emotion recognition via attention gated hierarchical memory network. arXiv preprint \narXiv:1911.09075\n\n (2019)","DOI":"10.1609\/aaai.v34i05.6309"},{"key":"4_CR9","first-page":"6818","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)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"issue":"3","key":"4_CR10","doi-asserted-by":"publisher","first-page":"257","DOI":"10.17763\/haer.47.3.8840364413869005","volume":"47","author":"D Olson","year":"1977","unstructured":"Olson, D.: From utterance to text: the bias of language in speech and writing. Harvard Educ. Rev. 47(3), 257\u2013281 (1977)","journal-title":"Harvard Educ. Rev."},{"key":"4_CR11","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: Proceedings of the 55th Annual Meeting of the Association for Computational Linguistics (volume 1: Long papers), pp. 873\u2013883 (2017)","DOI":"10.18653\/v1\/P17-1081"},{"key":"4_CR12","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. arXiv preprint \narXiv:1810.02508\n\n (2018)","DOI":"10.18653\/v1\/P19-1050"},{"key":"4_CR13","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. arXiv preprint \narXiv:1906.00295\n\n (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"4_CR14","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"4_CR15","first-page":"387","volume":"33","author":"B Yang","year":"2019","unstructured":"Yang, B., Li, J., Wong, D.F., Chao, L.S., Wang, X., Tu, Z.: Context-aware self-attention networks. Proc. AAAI Conf. Artif. Intell. 33, 387\u2013394 (2019)","journal-title":"Proc. AAAI Conf. Artif. Intell."},{"key":"4_CR16","doi-asserted-by":"crossref","unstructured":"Yang, B., Tu, Z., Wong, D.F., Meng, F., Chao, L.S., Zhang, T.: Modeling localness for self-attention networks. arXiv preprint \narXiv:1810.10182\n\n (2018)","DOI":"10.18653\/v1\/D18-1475"},{"issue":"5","key":"4_CR17","doi-asserted-by":"publisher","first-page":"3878","DOI":"10.1121\/1.2935783","volume":"123","author":"J Yuan","year":"2008","unstructured":"Yuan, J., Liberman, M.: Speaker identification on the scotus corpus. J. Acoustical Soc. Am. 123(5), 3878 (2008)","journal-title":"J. Acoustical Soc. Am."},{"key":"4_CR18","doi-asserted-by":"crossref","unstructured":"Zhang, D., Wu, L., Sun, C., Li, S., Zhu, Q., Zhou, G.: Modeling both context-and speaker-sensitive dependence for emotion detection in multi-speaker conversations. In: See Proceedings of the Twenty-Eighth International Joint Conference on Artificial Intelligence, pp. 10\u201316. IJCAI (2019)","DOI":"10.24963\/ijcai.2019\/752"},{"key":"4_CR19","doi-asserted-by":"crossref","unstructured":"Zhong, P., Wang, D., Miao, C.: Knowledge-enriched transformer for emotion detection in textual conversations. arXiv preprint \narXiv:1909.10681\n\n (2019)","DOI":"10.18653\/v1\/D19-1016"}],"container-title":["Lecture Notes in Computer Science","Natural Language Processing and Chinese Computing"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-60457-8_4","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2020,10,6]],"date-time":"2020-10-06T20:04:53Z","timestamp":1602014693000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/978-3-030-60457-8_4"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030604561","9783030604578"],"references-count":19,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-60457-8_4","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"type":"print","value":"0302-9743"},{"type":"electronic","value":"1611-3349"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"2 October 2020","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":"Zhengzhou","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":"2020","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"14 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"9","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"nlpcc2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/tcci.ccf.org.cn\/conference\/2020\/","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Double-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"Softconf","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"320","order":3,"name":"number_of_submissions_sent_for_review","label":"Number of Submissions Sent for Review","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"100","order":4,"name":"number_of_full_papers_accepted","label":"Number of Full Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"14","order":5,"name":"number_of_short_papers_accepted","label":"Number of Short Papers Accepted","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"31% - The value is computed by the equation \"Number of Full Papers Accepted \/ Number of Submissions Sent for Review * 100\" and then rounded to a whole number.","order":6,"name":"acceptance_rate_of_full_papers","label":"Acceptance Rate of Full Papers","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"3","order":7,"name":"average_number_of_reviews_per_paper","label":"Average Number of Reviews per Paper","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"1.5","order":8,"name":"average_number_of_papers_per_reviewer","label":"Average Number of Papers per Reviewer","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"No","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}