{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,1,30]],"date-time":"2026-01-30T05:27:22Z","timestamp":1769750842686,"version":"3.49.0"},"publisher-location":"Cham","reference-count":35,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030598297","type":"print"},{"value":"9783030598303","type":"electronic"}],"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\/978-3-030-59830-3_3","type":"book-chapter","created":{"date-parts":[[2020,10,8]],"date-time":"2020-10-08T23:04:34Z","timestamp":1602198274000},"page":"28-40","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":6,"title":["Gate-Fusion Transformer for Multimodal Sentiment Analysis"],"prefix":"10.1007","author":[{"ORCID":"https:\/\/orcid.org\/0000-0001-7465-5729","authenticated-orcid":false,"given":"Long-Fei","family":"Xie","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"ORCID":"https:\/\/orcid.org\/0000-0001-9260-188X","authenticated-orcid":false,"given":"Xu-Yao","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2020,10,9]]},"reference":[{"issue":"6","key":"3_CR1","first-page":"424","volume":"8","author":"QT Ain","year":"2017","unstructured":"Ain, Q.T., et al.: Sentiment analysis using deep learning techniques: a review. Int. J. Adv. Comput. Sci. Appl. 8(6), 424 (2017)","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"issue":"2","key":"3_CR2","doi-asserted-by":"publisher","first-page":"423","DOI":"10.1109\/TPAMI.2018.2798607","volume":"41","author":"T Baltru\u0161aitis","year":"2019","unstructured":"Baltru\u0161aitis, T., Ahuja, C., Morency, L.: Multimodal machine learning: a survey and taxonomy. IEEE Trans. Pattern Anal. Mach. Intell. 41(2), 423\u2013443 (2019)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"3_CR3","unstructured":"Berndt, D.J., Clifford, J.: Using dynamic time warping to find patterns in time series. In: KDD Workshop, Seattle, WA, vol. 10, pp. 359\u2013370 (1994)"},{"issue":"2","key":"3_CR4","doi-asserted-by":"publisher","first-page":"102","DOI":"10.1109\/MIS.2016.31","volume":"31","author":"E Cambria","year":"2016","unstructured":"Cambria, E.: Affective computing and sentiment analysis. IEEE Intell. Syst. 31(2), 102\u2013107 (2016)","journal-title":"IEEE Intell. Syst."},{"key":"3_CR5","doi-asserted-by":"crossref","unstructured":"Cho, K.,et al.: Learning phrase representations using RNN encoder-decoder for statistical machine translation. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing (EMNLP), Doha, Qatar, October 2014, pp. 1724\u20131734. Association for Computational Linguistics (2014)","DOI":"10.3115\/v1\/D14-1179"},{"key":"3_CR6","doi-asserted-by":"crossref","unstructured":"Dai, Z., et al.: Transformer-xl: attentive language models beyond a fixed-length context (2019). arXiv preprint arXiv:1901.02860","DOI":"10.18653\/v1\/P19-1285"},{"issue":"Jul","key":"3_CR7","first-page":"2211","volume":"12","author":"M Gonen","year":"2011","unstructured":"Gonen, M., Alpaydin, E.: Multiple kernel learning algorithms. J. Mach. Learn. Res. 12(Jul), 2211\u20132268 (2011)","journal-title":"J. Mach. Learn. Res."},{"key":"3_CR8","doi-asserted-by":"crossref","unstructured":"Graves, A., Fern\u00e1ndez, S., Gomez, F., Schmidhuber, J.: Connectionist temporal classification: labelling unsegmented sequence data with recurrent neural networks. In Proceedings of the 23rd International Conference on Machine Learning, pp. 369\u2013376. ACM (2006)","DOI":"10.1145\/1143844.1143891"},{"key":"3_CR9","doi-asserted-by":"crossref","unstructured":"Gurban, M., Thiran, J.P., Drugman, T., Dutoit, T.: Dynamic modality weighting for multi-stream hmms inaudio-visual speech recognition. In: Proceedings of the 10th International Conference on Multimodal Interfaces, pp. 237\u2013240. ACM (2008)","DOI":"10.1145\/1452392.1452442"},{"issue":"8","key":"3_CR10","doi-asserted-by":"publisher","first-page":"1735","DOI":"10.1162\/neco.1997.9.8.1735","volume":"9","author":"S Hochreiter","year":"1997","unstructured":"Hochreiter, S., Schmidhuber, J.: Long short-term memory. Neural Comput. 9(8), 1735\u20131780 (1997)","journal-title":"Neural Comput."},{"key":"3_CR11","unstructured":"Ittichaichareon, C., Suksri, S., Yingthawornsuk, T.: Speech recognition using MFCC. In: International Conference on Computer Graphics, Simulation and Modeling, pp. 135\u2013138 (2012)"},{"key":"3_CR12","unstructured":"Natasha, J., Taylor, S., Sano, A., Picard, R.: Multi-task, multi-kernel learning for estimating individual wellbeing. In: Proceedings NIPS Workshop on Multimodal Machine Learning, Montreal, Quebec, vol. 898, p. 63 (2015)"},{"key":"3_CR13","doi-asserted-by":"publisher","first-page":"63","DOI":"10.1016\/j.patrec.2014.08.005","volume":"51","author":"XY Jiang","year":"2015","unstructured":"Jiang, X.Y., Wu, F., Zhang, Y., Tang, S.L., Lu, W.M., Zhuang, Y.T.: The classification of multi-modal data with hidden conditional random field. Pattern Recogn. Lett. 51, 63\u201369 (2015)","journal-title":"Pattern Recogn. Lett."},{"key":"3_CR14","doi-asserted-by":"crossref","unstructured":"Kim, Y.: Convolutional neural networks for sentence classification. In: Proceedings of the 2014 Conference on Empirical Methods in Natural Language Processing, Doha, Qatar, pp. 1746\u20131751. Association for Computational Linguistics (2014)","DOI":"10.3115\/v1\/D14-1181"},{"key":"3_CR15","volume-title":"Probabilistic Graphical Models: Principles and Techniques","author":"D Koller","year":"2009","unstructured":"Koller, D., Friedman, N.: Probabilistic Graphical Models: Principles and Techniques. MIT press, Cambridge (2009)"},{"key":"3_CR16","doi-asserted-by":"crossref","unstructured":"Liang, P.P., Liu, Z., Zadeh, A.A.B., Morency, L.P.: Multimodal language analysis with recurrent multistage fusion. In: Proceedings of the 2018 Conference on Empirical Methods in Natural Language Processing, Brussels, Belgium, October-November 2018, pp. 150\u2013161. Association for Computational Linguistics (2018)","DOI":"10.18653\/v1\/D18-1014"},{"key":"3_CR17","doi-asserted-by":"crossref","unstructured":"Gwen, L., Sikka, K., Bartlett, M.S., Dykstra, K., Sathyanarayana, S.: Multiple kernel learning for emotion recognition in the wild. In: Proceedings of the 15th ACM International Conference on Multimodal Interaction, pp. 517\u2013524 (2013)","DOI":"10.1145\/2522848.2531741"},{"key":"3_CR18","first-page":"1","volume":"270","author":"B Logan","year":"2000","unstructured":"Logan, B., et al.: Mel frequency cepstral coefficients for music modeling. ISMIR 270, 1\u201311 (2000)","journal-title":"ISMIR"},{"key":"3_CR19","unstructured":"Tom\u00e1\u0161, M., Karafi\u00e1t, M., Burget, L., \u010cernock\u1ef3, J., Khudanpur, S.: Recurrent neural network based language model. In: Eleventh Annual Conference of the International Speech Communication Association (2010)"},{"key":"3_CR20","unstructured":"Manish, M., Shakya, S., Shrestha, A.: Fine-grained sentiment classification using bert (2019). arXiv preprint arXiv:1910.03474"},{"key":"3_CR21","unstructured":"Ngiam, J., Khosla, A., Kim, M., Nam, J., Lee, H., Ng, A.Y.: Multimodal deep learning. In: Proceedings of the 28th International Conference on Machine Learning, pp. 689\u2013696 (2011)"},{"key":"3_CR22","unstructured":"Peng, G., et al.: Dynamic fusion with intra- and inter- modality attention flow for visual question answering. In: The IEEE Conference on Computer Vision and Pattern Recognition (2019)"},{"issue":"1","key":"3_CR23","doi-asserted-by":"publisher","first-page":"22","DOI":"10.1145\/3284750","volume":"15","author":"Y Peng","year":"2019","unstructured":"Peng, Y., Qi, J.: CM-GANS: cross-modal generative adversarial networks for common representation learning. ACM Trans. Multimedia Comput. Commun. Appl. 15(1), 22 (2019)","journal-title":"ACM Trans. Multimedia Comput. Commun. Appl."},{"key":"3_CR24","doi-asserted-by":"crossref","unstructured":"Shaw, P., Uszkoreit, J., Vaswani, A.: Self-attention with relative position representations (2018). arXiv preprint arXiv:1803.02155","DOI":"10.18653\/v1\/N18-2074"},{"key":"3_CR25","doi-asserted-by":"crossref","unstructured":"Soleymani, M., Garcia, D., Jou, B., Schuller, B., Chang, S.F., Pantic, M.: A survey of multimodal sentiment analysis. Image Vis. Comput. 65, 3\u201314 (2017). Multimodal Sentiment Analysis and Mining in the Wild Image and Vision Computing","DOI":"10.1016\/j.imavis.2017.08.003"},{"key":"3_CR26","doi-asserted-by":"crossref","unstructured":"Tsai, Y.H.H., Bai, S., Liang, P.P., Zico Kolter,J., Morency, L.P., Salakhutdinov, R.: Multimodal transformer for unaligned multimodal language sequences. In: Proceedings of the 57th Annual Meeting of the Association for Computational Linguistics, Florence, Italy, July 2019, pp. 6558\u20136569. Association for Computational Linguistics (2019)","DOI":"10.18653\/v1\/P19-1656"},{"key":"3_CR27","unstructured":"Vaswani, A., et al.: Attention is all you need. In: Advances in Neural Information Processing Systems, pp. 5998\u20136008 (2017)"},{"key":"3_CR28","unstructured":"Wang, J., Fu, J., Xu, Y., Mei, T.: Beyond object recognition: Visual sentiment analysis with deep coupled adjective and noun neural networks. In: IJCAI, pp. 3484\u20133490 (2016)"},{"key":"3_CR29","doi-asserted-by":"publisher","first-page":"50","DOI":"10.1016\/j.neucom.2017.05.013","volume":"275","author":"N Wang","year":"2018","unstructured":"Wang, N., Gao, X., Tao, D., Yang, H., Li, X.: Facial feature point detection: a comprehensive survey. Neurocomputing 275, 50\u201365 (2018)","journal-title":"Neurocomputing"},{"key":"3_CR30","doi-asserted-by":"crossref","unstructured":"Wang, Y., Shen, Y., Liu, Z., Liang, P.P., Zadeh, A., Morency, L.P.: Dynamically adjusting word representations using nonverbal behaviors. Words can shift. In: Proceedings of the AAAI Conference on Artificial Intelligence, vol. 33, pp. 7216\u20137223 (2019)","DOI":"10.1609\/aaai.v33i01.33017216"},{"key":"3_CR31","doi-asserted-by":"crossref","unstructured":"Zadeh, A., Chen, M., Poria, S., Cambria, E., Morency, L.P.: Tensor fusion network for multimodal sentiment analysis. In Proceedings of the 2017 Conference on Empirical Methods in Natural Language Processing, Copenhagen, Denmark, September 2017, pp. 1103\u20131114. Association for Computational Linguistics (2017)","DOI":"10.18653\/v1\/D17-1115"},{"key":"3_CR32","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: Thirty-Second AAAI Conference on Artificial Intelligence (2018)","DOI":"10.1609\/aaai.v32i1.12021"},{"key":"3_CR33","unstructured":"Zadeh, A., Zellers, R., Pincus, E., Morency, L.P.: Mosi: multimodal corpus of sentiment intensity and subjectivity analysis in online opinion videos (2016). arXiv preprint arXiv:1606.06259"},{"key":"3_CR34","unstructured":"Zadeh, A.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 (Volume 1: Long Papers), pp. 2236\u20132246 (2018)"},{"key":"3_CR35","unstructured":"Zhou, C., Sun, C., Liu, Z., Lau, F.: A c-lstm neural network for text classification (2015). arXiv preprint arXiv:1511.08630"}],"container-title":["Lecture Notes in Computer Science","Pattern Recognition and Artificial Intelligence"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-59830-3_3","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2024,3,12]],"date-time":"2024-03-12T13:28:14Z","timestamp":1710250094000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-59830-3_3"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2020]]},"ISBN":["9783030598297","9783030598303"],"references-count":35,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-59830-3_3","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2020]]},"assertion":[{"value":"9 October 2020","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"ICPRAI","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"International Conference on Pattern Recognition and Artificial Intelligence","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Zhongshan","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":"19 October 2020","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"23 October 2020","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"icprai2020","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.icprai2020.com","order":11,"name":"conference_url","label":"Conference URL","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Single-blind","order":1,"name":"type","label":"Type","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"EasyChair","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"77","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":"49","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":"64% - 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":"1,99","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":"4,11","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)"}}]}}