{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,23]],"date-time":"2026-01-23T11:46:43Z","timestamp":1769168803122,"version":"3.49.0"},"publisher-location":"Cham","reference-count":29,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030983574","type":"print"},{"value":"9783030983581","type":"electronic"}],"license":[{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2022,1,1]],"date-time":"2022-01-01T00:00:00Z","timestamp":1640995200000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":[],"published-print":{"date-parts":[[2022]]},"DOI":"10.1007\/978-3-030-98358-1_48","type":"book-chapter","created":{"date-parts":[[2022,3,14]],"date-time":"2022-03-14T12:06:56Z","timestamp":1647259616000},"page":"612-623","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":11,"title":["Non-Uniform Attention Network for\u00a0Multi-modal Sentiment Analysis"],"prefix":"10.1007","author":[{"given":"Binqiang","family":"Wang","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Gang","family":"Dong","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yaqian","family":"Zhao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Rengang","family":"Li","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Qichun","family":"Cao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Yinyin","family":"Chao","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2022,3,15]]},"reference":[{"key":"48_CR1","doi-asserted-by":"publisher","first-page":"698","DOI":"10.1109\/LSP.2021.3063609","volume":"28","author":"M Hu","year":"2021","unstructured":"Hu, M., Chu, Q., Wang, X., He, L., Ren, F.: A two-stage spatiotemporal attention convolution network for continuous dimensional emotion recognition from facial video. IEEE Signal Process. Lett. 28, 698\u2013702 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"48_CR2","doi-asserted-by":"publisher","first-page":"992","DOI":"10.1109\/LSP.2021.3078074","volume":"28","author":"J He","year":"2021","unstructured":"He, J., Mai, S., Hu, H.: A unimodal reinforced transformer with time squeeze fusion for multimodal sentiment analysis. IEEE Signal Process. Lett. 28, 992\u2013996 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"48_CR3","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. arXiv preprint arXiv:1707.07250 (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"48_CR4","doi-asserted-by":"crossref","unstructured":"Liu, Z., Shen, Y., Lakshminarasimhan, V.B., Liang, P.P., Zadeh, A., Morency, L.P.: Efficient low-rank multimodal fusion with modality-specific factors. arXiv preprint arXiv:1806.00064 (2018)","DOI":"10.18653\/v1\/P18-1209"},{"issue":"02","key":"48_CR5","doi-asserted-by":"publisher","first-page":"52","DOI":"10.38094\/jastt20291","volume":"2","author":"SMSA Abdullah","year":"2021","unstructured":"Abdullah, S.M.S.A., Ameen, S.Y.A., Sadeeq, M.A., Zeebaree, S.: Multimodal emotion recognition using deep learning. J. Appl. Sci. Technol. Trends 2(02), 52\u201358 (2021)","journal-title":"J. Appl. Sci. Technol. Trends"},{"key":"48_CR6","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":"48_CR7","doi-asserted-by":"crossref","unstructured":"Nguyen, D., Nguyen, K., Sridharan, S., Ghasemi, A., Dean, D., Fookes, C.: Deep spatio-temporal features for multimodal emotion recognition. In: 2017 IEEE Winter Conference on Applications of Computer Vision (WACV), pp. 1215\u20131223. IEEE (2017)","DOI":"10.1109\/WACV.2017.140"},{"issue":"8","key":"48_CR8","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., Schuller, B.W., Zafeiriou, S.: End-to-end multimodal emotion recognition using deep neural networks. IEEE J. Sel. Topics Signal Process. 11(8), 1301\u20131309 (2017)","journal-title":"IEEE J. Sel. Topics Signal Process."},{"key":"48_CR9","doi-asserted-by":"crossref","unstructured":"Xu, H., Zhang, H., Han, K., Wang, Y., Peng, Y., Li, X.: Learning alignment for multimodal emotion recognition from speech. arXiv preprint arXiv:1909.05645 (2019)","DOI":"10.21437\/Interspeech.2019-3247"},{"key":"48_CR10","doi-asserted-by":"crossref","unstructured":"Mittal, T., Bhattacharya, U., Chandra, R., Bera, A., Manocha, D.: M3er: multiplicative multimodal emotion recognition using facial, textual, and speech cues. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 34, pp. 1359\u20131367 (2020)","DOI":"10.1609\/aaai.v34i02.5492"},{"key":"48_CR11","doi-asserted-by":"crossref","unstructured":"Mittal, T., Guhan, P., Bhattacharya, U., Chandra, R., Bera, A., Manocha, D.: Emoticon: Context-aware multimodal emotion recognition using frege\u2019s principle. In: Proceedings of the IEEE\/CVF Conference on Computer Vision and Pattern Recognition, pp. 14234\u201314243 (2020)","DOI":"10.1109\/CVPR42600.2020.01424"},{"key":"48_CR12","doi-asserted-by":"publisher","first-page":"184","DOI":"10.1016\/j.inffus.2020.09.005","volume":"66","author":"D Gkoumas","year":"2021","unstructured":"Gkoumas, D., Li, Q., Lioma, C., Yu, Y., Song, D.: What makes the difference? an empirical comparison of fusion strategies for multimodal language analysis. Inf. Fusion 66, 184\u2013197 (2021)","journal-title":"Inf. Fusion"},{"key":"48_CR13","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Poria, S., Vij, P., Cambria, E., Morency, L.P.: Multi-attention recurrent network for human communication comprehension. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12024"},{"key":"48_CR14","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shen, Y., Liu, Z., Liang, P.P., Zadeh, A., Morency, L.P.: Words can shift: dynamically adjusting word representations using nonverbal behaviors. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 7216\u20137223 (2019)","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"48_CR15","doi-asserted-by":"publisher","first-page":"533","DOI":"10.1109\/LSP.2021.3055755","volume":"28","author":"C Guanghui","year":"2021","unstructured":"Guanghui, C., Xiaoping, Z.: Multi-modal emotion recognition by fusing correlation features of speech-visual. IEEE Signal Process. Lett. 28, 533\u2013537 (2021)","journal-title":"IEEE Signal Process. Lett."},{"key":"48_CR16","unstructured":"Zadeh, A., Zellers, R., Pincus, E., Morency, L.P.: Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos. arXiv preprint arXiv:1606.06259 (2016)"},{"issue":"3","key":"48_CR17","doi-asserted-by":"publisher","first-page":"38","DOI":"10.1109\/MIS.2013.9","volume":"28","author":"VP Rosas","year":"2013","unstructured":"Rosas, V.P., Mihalcea, R., Morency, L.P.: Multimodal sentiment analysis of Spanish online videos. IEEE Intell. Syst. 28(3), 38\u201345 (2013)","journal-title":"IEEE Intell. Syst."},{"key":"48_CR18","doi-asserted-by":"crossref","unstructured":"Poria, S., Cambria, E., Gelbukh, A.: Deep convolutional neural network textual features and multiple kernel learning for utterance-level multimodal sentiment analysis. In: Proceedings of the 2015 Conference on Empirical Methods in Natural Language Processing, pp. 2539\u20132544 (2015)","DOI":"10.18653\/v1\/D15-1303"},{"key":"48_CR19","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"278","DOI":"10.1007\/978-3-030-67832-6_23","volume-title":"MultiMedia Modeling","author":"Y Fu","year":"2021","unstructured":"Fu, Y., Guo, L., Wang, L., Liu, Z., Liu, J., Dang, J.: A sentiment similarity-oriented attention model with multi-task learning for text-based emotion recognition. In: Loko\u010d, J., Skopal, T., Schoeffmann, K., Mezaris, V., Li, X., Vrochidis, S., Patras, I. (eds.) MMM 2021. LNCS, vol. 12572, pp. 278\u2013289. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-67832-6_23"},{"key":"48_CR20","doi-asserted-by":"crossref","unstructured":"You, Q., Jin, H., Luo, J.: Visual sentiment analysis by attending on local image regions. In: Thirty-First AAAI Conference on Artificial Intelligence (2017)","DOI":"10.1609\/aaai.v31i1.10501"},{"key":"48_CR21","doi-asserted-by":"crossref","unstructured":"Tsai, Y., Bai, S., Liang, P.P., Kolter, J.Z., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1656"},{"issue":"8","key":"48_CR22","doi-asserted-by":"publisher","first-page":"5535","DOI":"10.1109\/TGRS.2019.2900302","volume":"57","author":"Y Zhang","year":"2019","unstructured":"Zhang, Y., Yuan, Y., Feng, Y., Lu, X.: Hierarchical and robust convolutional neural network for very high-resolution remote sensing object detection. IEEE Trans. Geosci. Remote Sens. 57(8), 5535\u20135548 (2019)","journal-title":"IEEE Trans. Geosci. Remote Sens."},{"issue":"10","key":"48_CR23","doi-asserted-by":"publisher","first-page":"1440","DOI":"10.1109\/LSP.2018.2860246","volume":"25","author":"M Chen","year":"2018","unstructured":"Chen, M., He, X., Yang, J., Zhang, H.: 3-d convolutional recurrent neural networks with attention model for speech emotion recognition. IEEE Signal Process. Lett. 25(10), 1440\u20131444 (2018)","journal-title":"IEEE Signal Process. Lett."},{"key":"48_CR24","doi-asserted-by":"crossref","unstructured":"Ghosal, D., Akhtar, M.S., Chauhan, D., Poria, S., Bhattacharyya, P.: Contextual inter-modal attention for multi-modal sentiment analysis. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing (2018)","DOI":"10.18653\/v1\/D18-1382"},{"issue":"Aug","key":"48_CR25","first-page":"115","volume":"3","author":"FA Gers","year":"2002","unstructured":"Gers, F.A., Schraudolph, N.N., Schmidhuber, J.: Learning precise timing with LSTM recurrent networks. J. Mach. Learn. Res. 3(Aug), 115\u2013143 (2002)","journal-title":"J. Mach. Learn. Res."},{"key":"48_CR26","doi-asserted-by":"crossref","unstructured":"Rahman, W., et al.: Integrating multimodal information in large pretrained transformers. In: Proceedings of the Conference. Association for Computational Linguistics. Meeting, vol. 2020, p. 2359. NIH Public Access (2020)","DOI":"10.18653\/v1\/2020.acl-main.214"},{"key":"48_CR27","unstructured":"Zadeh, A.B., Liang, P.P., Poria, S., Cambria, E., Morency, L.P.: Multimodal language analysis in the wild: cmu-mosei dataset and interpretable dynamic fusion graph. In: Proceedings of the 56th Annual Meeting of the Association for Computational Linguistics, vol. 1: Long Papers, pp. 2236\u20132246 (2018)"},{"key":"48_CR28","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Liang, P.P., Mazumder, N., Poria, S., Cambria, E., Morency, L.P.: Memory fusion network for multi-view sequential learning. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 32 (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"48_CR29","doi-asserted-by":"crossref","unstructured":"Pennington, J., Socher, R., Manning, C.: Glove: global vectors for word representation. In: Proceedings of Empirical Methods Natural Language Processing, pp. 1532\u20131543 (2014)","DOI":"10.3115\/v1\/D14-1162"}],"container-title":["Lecture Notes in Computer Science","MultiMedia Modeling"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-98358-1_48","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,2,19]],"date-time":"2024-02-19T10:16:43Z","timestamp":1708337803000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-98358-1_48"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2022]]},"ISBN":["9783030983574","9783030983581"],"references-count":29,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-98358-1_48","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2022]]},"assertion":[{"value":"15 March 2022","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"MMM","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Multimedia Modeling","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Phu Quoc","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Vietnam","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2022","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"6 June 2022","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"10 June 2022","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"28","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"mmm2022","order":10,"name":"conference_id","label":"Conference ID","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":"Conftool Pro","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"212","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":"84","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":"0","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":"40% - 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":"4","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":"Yes","order":9,"name":"external_reviewers_involved","label":"External Reviewers Involved","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}}]}}