{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,3,3]],"date-time":"2026-03-03T16:03:08Z","timestamp":1772553788793,"version":"3.50.1"},"publisher-location":"Cham","reference-count":38,"publisher":"Springer International Publishing","isbn-type":[{"value":"9783030856120","type":"print"},{"value":"9783030856137","type":"electronic"}],"license":[{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"content-version":"tdm","delay-in-days":0,"URL":"https:\/\/www.springer.com\/tdm"},{"start":{"date-parts":[[2021,1,1]],"date-time":"2021-01-01T00:00:00Z","timestamp":1609459200000},"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":[[2021]]},"DOI":"10.1007\/978-3-030-85613-7_16","type":"book-chapter","created":{"date-parts":[[2021,8,25]],"date-time":"2021-08-25T06:03:15Z","timestamp":1629871395000},"page":"227-237","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":23,"title":["DeepVANet: A Deep End-to-End Network for Multi-modal Emotion Recognition"],"prefix":"10.1007","author":[{"given":"Yuhao","family":"Zhang","sequence":"first","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0003-1892-831X","authenticated-orcid":false,"given":"Md Zakir","family":"Hossain","sequence":"additional","affiliation":[]},{"ORCID":"https:\/\/orcid.org\/0000-0001-7169-0318","authenticated-orcid":false,"given":"Shafin","family":"Rahman","sequence":"additional","affiliation":[]}],"member":"297","published-online":{"date-parts":[[2021,8,26]]},"reference":[{"issue":"10","key":"16_CR1","first-page":"355","volume":"8","author":"S Alhagry","year":"2017","unstructured":"Alhagry, S., Fahmy, A.A., El-Khoribi, R.A.: Emotion recognition based on EEG using LSTM recurrent neural network. Emotion 8(10), 355\u2013358 (2017)","journal-title":"Emotion"},{"key":"16_CR2","doi-asserted-by":"crossref","unstructured":"Anubhav, Nath, D., Singh, M., Sethia, D., Kalra, D., Indu, S.: An efficient approach to EEG-based emotion recognition using LSTM network. In: IEEE International Colloquium on Signal Processing & Its Applications (CSPA), pp. 88\u201392 (2020)","DOI":"10.1109\/CSPA48992.2020.9068691"},{"key":"16_CR3","doi-asserted-by":"crossref","unstructured":"Bulat, A., Tzimiropoulos, G.: How far are we from solving the 2d & 3d face alignment problem? (and a dataset of 230,000 3d facial landmarks). In: International Conference on Computer Vision (2017)","DOI":"10.1109\/ICCV.2017.116"},{"issue":"1","key":"16_CR4","doi-asserted-by":"publisher","first-page":"9","DOI":"10.1016\/j.jneumeth.2003.10.009","volume":"134","author":"A Delorme","year":"2004","unstructured":"Delorme, A., Makeig, S.: EEGLAB: an open source toolbox for analysis of single-trial EEG dynamics including independent component analysis. J. Neurosci. Methods 134(1), 9\u201321 (2004)","journal-title":"J. Neurosci. Methods"},{"issue":"3","key":"16_CR5","doi-asserted-by":"publisher","first-page":"592","DOI":"10.3390\/s20030592","volume":"20","author":"A Dzedzickis","year":"2020","unstructured":"Dzedzickis, A., Kaklauskas, A., Bucinskas, V.: Human emotion recognition: review of sensors and methods. Sensors 20(3), 592 (2020)","journal-title":"Sensors"},{"key":"16_CR6","doi-asserted-by":"publisher","first-page":"550","DOI":"10.1037\/0033-295X.99.3.550","volume":"99","author":"P Ekman","year":"1992","unstructured":"Ekman, P.: Are there basic emotions? Psychol. Rev. 99, 550\u2013553 (1992)","journal-title":"Psychol. Rev."},{"key":"16_CR7","unstructured":"Freund, Y., Schapire, R.E., et al.: Experiments with a new boosting algorithm. In: ICML, vol. 96, pp. 148\u2013156 (1996)"},{"issue":"6","key":"16_CR8","doi-asserted-by":"publisher","first-page":"7714","DOI":"10.3390\/s130607714","volume":"13","author":"D Ghimire","year":"2013","unstructured":"Ghimire, D., Lee, J.: Geometric feature-based facial expression recognition in image sequences using multi-class adaboost and support vector machines. Sensors 13(6), 7714\u20137734 (2013)","journal-title":"Sensors"},{"key":"16_CR9","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"298","DOI":"10.1007\/978-3-030-64559-5_23","volume-title":"Advances in Visual Computing","author":"J Haddad","year":"2020","unstructured":"Haddad, J., Lezoray, O., Hamel, P.: 3D-CNN for facial emotion recognition in videos. In: Bebis, G., et al. (eds.) ISVC 2020. LNCS, vol. 12510, pp. 298\u2013309. Springer, Cham (2020). https:\/\/doi.org\/10.1007\/978-3-030-64559-5_23"},{"key":"16_CR10","doi-asserted-by":"crossref","unstructured":"Happy, S., George, A., Routray, A.: A real time facial expression classification system using local binary patterns. In: 2012 4th International Conference on Intelligent Human Computer Interaction (IHCI), pp. 1\u20135. IEEE (2012)","DOI":"10.1109\/IHCI.2012.6481802"},{"key":"16_CR11","doi-asserted-by":"crossref","unstructured":"Huang, J., Li, Y., Tao, J., Lian, Z., Yi, J.: End-to-end continuous emotion recognition from video using 3D ConvLSTM networks. In: 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), pp. 6837\u20136841 (2018)","DOI":"10.1109\/ICASSP.2018.8461963"},{"issue":"5","key":"16_CR12","doi-asserted-by":"publisher","first-page":"105","DOI":"10.3390\/fi11050105","volume":"11","author":"Y Huang","year":"2019","unstructured":"Huang, Y., Yang, J., Liu, S., Pan, J.: Combining facial expressions and electroencephalography to enhance emotion recognition. Future Internet 11(5), 105 (2019)","journal-title":"Future Internet"},{"key":"16_CR13","unstructured":"Jinliang, G., Fang, F., Wang, W., Ren, F.: EEG emotion recognition based on granger causality and CapsNet neural network. In: International Conference on Cloud Computing and Intelligence Systems (CCIS), pp. 47\u201352 (2018)"},{"key":"16_CR14","unstructured":"Kahou, S.E., Michalski, V., Konda, K., Memisevic, R., Pal, C.: Recurrent neural networks for emotion recognition in video. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 467\u2013474 (2015)"},{"key":"16_CR15","unstructured":"Kingma, D.P., Ba, J.L.: Adam: a method for stochastic optimization. arXiv preprint arXiv:1412.6980 (2014)"},{"issue":"2","key":"16_CR16","doi-asserted-by":"publisher","first-page":"401","DOI":"10.3390\/s18020401","volume":"18","author":"BC Ko","year":"2018","unstructured":"Ko, B.C.: A brief review of facial emotion recognition based on visual information. Sensors 18(2), 401 (2018)","journal-title":"Sensors"},{"issue":"1","key":"16_CR17","doi-asserted-by":"publisher","first-page":"18","DOI":"10.1109\/T-AFFC.2011.15","volume":"3","author":"S Koelstra","year":"2012","unstructured":"Koelstra, S., et al.: DEAP: a database for emotion analysis using physiological signals. IEEE Trans. Affect. Comput. 3(1), 18\u201331 (2012)","journal-title":"IEEE Trans. Affect. Comput."},{"issue":"2","key":"16_CR18","doi-asserted-by":"publisher","first-page":"164","DOI":"10.1016\/j.imavis.2012.10.002","volume":"31","author":"S Koelstra","year":"2013","unstructured":"Koelstra, S., Patras, I.: Fusion of facial expressions and EEG for implicit affective tagging. Image Vis. Comput. 31(2), 164\u2013174 (2013)","journal-title":"Image Vis. Comput."},{"key":"16_CR19","doi-asserted-by":"publisher","first-page":"23","DOI":"10.1016\/j.imavis.2017.02.001","volume":"65","author":"J Kossaifi","year":"2017","unstructured":"Kossaifi, J., Tzimiropoulos, G., Todorovic, S., Pantic, M.: AFEW-VA database for valence and arousal estimation in-the-wild. Image Vis. Comput. 65, 23\u201336 (2017)","journal-title":"Image Vis. Comput."},{"key":"16_CR20","doi-asserted-by":"crossref","unstructured":"Kumar, P., Happy, S., Routray, A.: A real-time robust facial expression recognition system using HOG features. In: 2016 International Conference on Computing, Analytics and Security Trends (CAST), pp. 289\u2013293. IEEE (2016)","DOI":"10.1109\/CAST.2016.7914982"},{"key":"16_CR21","doi-asserted-by":"crossref","unstructured":"Lee, J., Kim, S., Kim, S., Park, J., Sohn, K.: Context-aware emotion recognition networks. In: Proceedings of the IEEE\/CVF International Conference on Computer Vision, pp. 10143\u201310152 (2019)","DOI":"10.1109\/ICCV.2019.01024"},{"key":"16_CR22","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"521","DOI":"10.1007\/978-3-319-46672-9_58","volume-title":"Neural Information Processing","author":"W Liu","year":"2016","unstructured":"Liu, W., Zheng, W.-L., Lu, B.-L.: Emotion recognition using multimodal deep learning. In: Hirose, A., Ozawa, S., Doya, K., Ikeda, K., Lee, M., Liu, D. (eds.) ICONIP 2016. LNCS, vol. 9948, pp. 521\u2013529. Springer, Cham (2016). https:\/\/doi.org\/10.1007\/978-3-319-46672-9_58"},{"key":"16_CR23","doi-asserted-by":"crossref","unstructured":"Nie, W., Ren, M., Nie, J., Zhao, S.: C-GCN: correlation based graph convolutional network for audio-video emotion recognition. IEEE Trans. Multimed. 1 (2020)","DOI":"10.1109\/TMM.2020.3032037"},{"key":"16_CR24","series-title":"Smart Innovation, Systems and Technologies","doi-asserted-by":"publisher","first-page":"299","DOI":"10.1007\/978-3-642-13396-1_14","volume-title":"Multimedia Services in Intelligent Environments","author":"KJ Panoulas","year":"2010","unstructured":"Panoulas, K.J., Hadjileontiadis, L.J., Panas, S.M.: Brain-computer interface (BCI): types, processing perspectives and applications. In: Tsihrintzis, G.A., Jain, L.C. (eds.) Multimedia Services in Intelligent Environments. Smart Innovation, Systems and Technologies, vol. 3, pp. 299\u2013321. Springer, Heidelberg (2010). https:\/\/doi.org\/10.1007\/978-3-642-13396-1_14"},{"key":"16_CR25","doi-asserted-by":"publisher","first-page":"167","DOI":"10.1016\/j.eij.2020.07.005","volume":"22","author":"ES Salama","year":"2020","unstructured":"Salama, E.S., El-Khoribi, R.A., Shoman, M.E., Shalaby, M.A.W.: A 3D-convolutional neural network framework with ensemble learning techniques for multi-modal emotion recognition. Egypt. Inform. J. 22, 167\u2013176 (2020)","journal-title":"Egypt. Inform. J."},{"key":"16_CR26","unstructured":"Shi, X., Chen, Z., Wang, H., Yeung, D.Y., Wong, W.K., Woo, W.C.: Convolutional LSTM network: a machine learning approach for precipitation nowcasting. In: Advances in Neural Information Processing Systems, vol. 28, pp. 802\u2013810 (2015)"},{"issue":"7","key":"16_CR27","doi-asserted-by":"publisher","first-page":"2074","DOI":"10.3390\/s18072074","volume":"18","author":"L Shu","year":"2018","unstructured":"Shu, L., et al.: A review of emotion recognition using physiological signals. Sensors 18(7), 2074 (2018)","journal-title":"Sensors"},{"key":"16_CR28","doi-asserted-by":"crossref","unstructured":"Siddharth, J., T.P., Sejnowski, T.J.: Utilizing deep learning towards multi-modal bio-sensing and vision-based affective computing. IEEE Trans. Affect. Comput. (2019)","DOI":"10.1109\/TAFFC.2019.2916015"},{"issue":"1","key":"16_CR29","doi-asserted-by":"publisher","first-page":"42","DOI":"10.1109\/T-AFFC.2011.25","volume":"3","author":"M Soleymani","year":"2012","unstructured":"Soleymani, M., Lichtenauer, J., Pun, T., Pantic, M.: A multimodal database for affect recognition and implicit tagging. IEEE Trans. Affect. Comput. 3(1), 42\u201355 (2012)","journal-title":"IEEE Trans. Affect. Comput."},{"key":"16_CR30","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"811","DOI":"10.1007\/978-3-319-70093-9_86","volume-title":"Neural Information Processing","author":"H Tang","year":"2017","unstructured":"Tang, H., Liu, W., Zheng, W.L., Lu, B.L.: Multimodal emotion recognition using deep neural networks. In: Liu, D., Xie, S., Li, Y., Zhao, D., El-Alfy, E.S. (eds.) ICONIP 2017. LNCS, vol. 10637, pp. 811\u2013819. Springer, Cham (2017). https:\/\/doi.org\/10.1007\/978-3-319-70093-9_86"},{"issue":"18","key":"16_CR31","doi-asserted-by":"publisher","first-page":"5083","DOI":"10.3390\/s20185083","volume":"20","author":"EP Torres","year":"2020","unstructured":"Torres, E.P., Torres, E.A., Hernandez-Alvarez, M., Yoo, S.G.: EEG-based BCI emotion recognition: a survey. Sensors 20(18), 5083 (2020)","journal-title":"Sensors"},{"key":"16_CR32","doi-asserted-by":"publisher","first-page":"61","DOI":"10.1016\/j.eswa.2018.04.021","volume":"107","author":"I Ullah","year":"2018","unstructured":"Ullah, I., Hussain, M., Aboalsamh, H., et al.: An automated system for epilepsy detection using EEG brain signals based on deep learning approach. Expert Syst. Appl. 107, 61\u201371 (2018)","journal-title":"Expert Syst. Appl."},{"issue":"3","key":"16_CR33","first-page":"1","volume":"8","author":"MBH Wiem","year":"2017","unstructured":"Wiem, M.B.H., Lachiri, Z.: Emotion classification in arousal valence model using MAHNOB-HCI database. Int. J. Adv. Comput. Sci. Appl. 8(3), 1\u20136 (2017)","journal-title":"Int. J. Adv. Comput. Sci. Appl."},{"issue":"7","key":"16_CR34","doi-asserted-by":"publisher","first-page":"1319","DOI":"10.1109\/TMM.2016.2557721","volume":"18","author":"J Yan","year":"2016","unstructured":"Yan, J., Zheng, W., Xu, Q., Lu, G., Li, H., Wang, B.: Sparse kernel reduced-rank regression for bimodal emotion recognition from facial expression and speech. IEEE Trans. Multimed. 18(7), 1319\u20131329 (2016)","journal-title":"IEEE Trans. Multimed."},{"key":"16_CR35","series-title":"Lecture Notes in Computer Science","doi-asserted-by":"publisher","first-page":"21","DOI":"10.1007\/978-3-030-69541-5_2","volume-title":"Computer Vision \u2013 ACCV 2020","author":"Y Yang","year":"2021","unstructured":"Yang, Y., Hossain, M.Z., Gedeon, T., Rahman, S.: RealSmileNet: a deep end-to-end network for spontaneous and posed smile recognition. In: Ishikawa, H., Liu, C.-L., Pajdla, T., Shi, J. (eds.) ACCV 2020. LNCS, vol. 12626, pp. 21\u201337. Springer, Cham (2021). https:\/\/doi.org\/10.1007\/978-3-030-69541-5_2"},{"key":"16_CR36","doi-asserted-by":"crossref","unstructured":"Yang, Y., Wu, Q., Qiu, M., Wang, Y., Chen, X.: Emotion recognition from multi-channel EEG through parallel convolutional recurrent neural network. In: 2018 International Joint Conference on Neural Networks (IJCNN), pp. 1\u20137. IEEE (2018)","DOI":"10.1109\/IJCNN.2018.8489331"},{"issue":"2","key":"16_CR37","doi-asserted-by":"publisher","first-page":"424","DOI":"10.1109\/TMM.2006.886310","volume":"9","author":"Z Zeng","year":"2007","unstructured":"Zeng, Z., et al.: Audio-visual affect recognition. IEEE Trans. Multimed. 9(2), 424\u2013428 (2007)","journal-title":"IEEE Trans. Multimed."},{"key":"16_CR38","doi-asserted-by":"publisher","first-page":"164130","DOI":"10.1109\/ACCESS.2020.3021994","volume":"8","author":"H Zhang","year":"2020","unstructured":"Zhang, H.: Expression-EEG based collaborative multimodal emotion recognition using deep autoencoder. IEEE Access 8, 164130\u2013164143 (2020)","journal-title":"IEEE Access"}],"container-title":["Lecture Notes in Computer Science","Human-Computer Interaction \u2013 INTERACT 2021"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/link.springer.com\/content\/pdf\/10.1007\/978-3-030-85613-7_16","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2021,8,25]],"date-time":"2021-08-25T23:42:59Z","timestamp":1629934979000},"score":1,"resource":{"primary":{"URL":"https:\/\/link.springer.com\/10.1007\/978-3-030-85613-7_16"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2021]]},"ISBN":["9783030856120","9783030856137"],"references-count":38,"URL":"https:\/\/doi.org\/10.1007\/978-3-030-85613-7_16","relation":{},"ISSN":["0302-9743","1611-3349"],"issn-type":[{"value":"0302-9743","type":"print"},{"value":"1611-3349","type":"electronic"}],"subject":[],"published":{"date-parts":[[2021]]},"assertion":[{"value":"26 August 2021","order":1,"name":"first_online","label":"First Online","group":{"name":"ChapterHistory","label":"Chapter History"}},{"value":"INTERACT","order":1,"name":"conference_acronym","label":"Conference Acronym","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"IFIP Conference on Human-Computer Interaction","order":2,"name":"conference_name","label":"Conference Name","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Bari","order":3,"name":"conference_city","label":"Conference City","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"Italy","order":4,"name":"conference_country","label":"Conference Country","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"2021","order":5,"name":"conference_year","label":"Conference Year","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"30 August 2021","order":7,"name":"conference_start_date","label":"Conference Start Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"3 September 2021","order":8,"name":"conference_end_date","label":"Conference End Date","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"18","order":9,"name":"conference_number","label":"Conference Number","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"interact2021","order":10,"name":"conference_id","label":"Conference ID","group":{"name":"ConferenceInfo","label":"Conference Information"}},{"value":"http:\/\/www.interact2021.org\/","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":"PCS","order":2,"name":"conference_management_system","label":"Conference Management System","group":{"name":"ConfEventPeerReviewInformation","label":"Peer Review Information (provided by the conference organizers)"}},{"value":"680","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":"105","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":"72","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":"15% - 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":"2","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":"2","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)"}}]}}