{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,9,26]],"date-time":"2026-09-26T04:01:30Z","timestamp":1790395290561,"version":"4.1.0"},"reference-count":54,"publisher":"Springer Science and Business Media LLC","issue":"10","license":[{"start":{"date-parts":[[2018,5,4]],"date-time":"2018-05-04T00:00:00Z","timestamp":1525392000000},"content-version":"tdm","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"funder":[{"DOI":"10.13039\/501100013286","name":"Specialized Research Fund for the Doctoral Program of Higher Education","doi-asserted-by":"crossref","award":["20121102130001"],"award-info":[{"award-number":["20121102130001"]}],"id":[{"id":"10.13039\/501100013286","id-type":"DOI","asserted-by":"crossref"}]}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Vis Comput"],"published-print":{"date-parts":[[2018,10]]},"DOI":"10.1007\/s00371-018-1477-y","type":"journal-article","created":{"date-parts":[[2018,5,4]],"date-time":"2018-05-04T09:07:46Z","timestamp":1525424866000},"page":"1461-1475","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":63,"title":["Learning deep facial expression features from image and optical flow sequences using 3D CNN"],"prefix":"10.1007","volume":"34","author":[{"given":"Jianfeng","family":"Zhao","sequence":"first","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Xia","family":"Mao","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Jian","family":"Zhang","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"297","published-online":{"date-parts":[[2018,5,4]]},"reference":[{"key":"1477_CR1","doi-asserted-by":"publisher","first-page":"3","DOI":"10.1002\/ajpa.20001","volume":"116","author":"Karen L Schmidt","year":"2001","unstructured":"Schmidt, Karen L., Cohn, Jeffrey F.: Human facial expressions as adaptations: evolutionary questions in facial expression research. Am. J. Phys. Anthropol. 116, 3\u201324 (2001)","journal-title":"Am. J. Phys. Anthropol."},{"key":"1477_CR2","doi-asserted-by":"crossref","unstructured":"Pantic, M., Bartlett, M.S.: Machine analysis of facial expressions. In: Delac, K., Grgic, M. (eds.) Face Recognition, pp. 77\u2013416 (2007)","DOI":"10.5772\/4847"},{"key":"1477_CR3","volume-title":"The Psychology of Facial Expression","year":"1997","unstructured":"Russell, J.A., Fern\u00e1ndez-Dols, J.M. (eds.): The Psychology of Facial Expression. Cambridge University Press, Cambridge (1997)"},{"issue":"1","key":"1477_CR4","doi-asserted-by":"publisher","first-page":"259","DOI":"10.1016\/S0031-3203(02)00052-3","volume":"36","author":"B Fasel","year":"2003","unstructured":"Fasel, B., Luettin, J.: Automatic facial expression analysis: a survey. Pattern Recogn. 36(1), 259\u2013275 (2003)","journal-title":"Pattern Recogn."},{"issue":"2","key":"1477_CR5","doi-asserted-by":"publisher","first-page":"97","DOI":"10.1109\/34.908962","volume":"23","author":"YI Tian","year":"2001","unstructured":"Tian, Y.I., Kanade, T., Cohn, J.F.: Recognizing action units for facial expression analysis. IEEE Trans. Pattern Anal. Mach. Intell. 23(2), 97\u2013115 (2001)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1477_CR6","doi-asserted-by":"crossref","unstructured":"Tian, Y.-L., Kanade, T., Cohn, J.F.: Facial expression analysis. In: Handbook of Face Recognition, pp. 247\u2013275. Springer, New York (2005)","DOI":"10.1007\/0-387-27257-7_12"},{"issue":"3","key":"1477_CR7","doi-asserted-by":"publisher","first-page":"243","DOI":"10.1016\/S0923-5965(01)00021-2","volume":"17","author":"T Goto","year":"2002","unstructured":"Goto, T., Lee, W.-S., Magnenat-Thalmann, N.: Facial feature extraction for quick 3D face modeling. Signal Process. Image Commun. 17(3), 243\u2013259 (2002)","journal-title":"Signal Process. Image Commun."},{"issue":"6\u20138","key":"1477_CR8","doi-asserted-by":"publisher","first-page":"649","DOI":"10.1007\/s00371-014-0960-3","volume":"30","author":"J Chi","year":"2014","unstructured":"Chi, J., Changhe, T., Zhang, C.: Dynamic 3D facial expression modeling using Laplacian smooth and multi-scale mesh matching. Vis. Comput. 30(6\u20138), 649\u2013659 (2014)","journal-title":"Vis. Comput."},{"key":"1477_CR9","doi-asserted-by":"publisher","first-page":"177","DOI":"10.1007\/s00371-016-1323-z","volume":"34","author":"S Agarwal","year":"2018","unstructured":"Agarwal, S., Santra, B., Mukherjee, D.P.: Anubhav: recognizing emotions through facial expression. Vis. Comput. 34, 177 (2018). https:\/\/doi.org\/10.1007\/s00371-016-1323-z","journal-title":"Vis. Comput."},{"issue":"6","key":"1477_CR10","doi-asserted-by":"publisher","first-page":"536","DOI":"10.1109\/TMM.2010.2052792","volume":"12","author":"Y Huang","year":"2010","unstructured":"Huang, Y., Li, Y., Fan, N.: Robust symbolic dual-view facial expression recognition with skin wrinkles: local versus global approach. IEEE Trans. Multimed. 12(6), 536\u2013543 (2010)","journal-title":"IEEE Trans. Multimed."},{"key":"1477_CR11","unstructured":"Cohn, J.F.: Automated analysis of the configuration and timing of facial expression. In: What the Face Reveals: Basic and Applied Studies of Spontaneous Expression Using the Facial Action Coding System (FACS). Oxford University Press Series in Affective Science, pp. 388\u2013392 (2005)"},{"key":"1477_CR12","doi-asserted-by":"crossref","unstructured":"Liu, P., et al.: Facial expression recognition via a boosted deep belief network. In: Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (2014)","DOI":"10.1109\/CVPR.2014.233"},{"key":"1477_CR13","doi-asserted-by":"crossref","unstructured":"Levi, G., Hassner, T.: Emotion recognition in the wild via convolutional neural networks and mapped binary patterns. In: Proceedings of the 2015 ACM on International Conference on Multimodal Interaction, pp. 503\u2013510 (2015)","DOI":"10.1145\/2818346.2830587"},{"key":"1477_CR14","doi-asserted-by":"crossref","unstructured":"Barros, P., Weber, C., Wermter, S.: Emotional expression recognition with a cross-channel convolutional neural network for human-robot interaction. In: IEEE-RAS, International Conference on Humanoid Robots, pp. 582\u2013587 (2015)","DOI":"10.1109\/HUMANOIDS.2015.7363421"},{"issue":"2","key":"1477_CR15","doi-asserted-by":"publisher","first-page":"173","DOI":"10.1007\/s12193-015-0209-0","volume":"10","author":"BK Kim","year":"2016","unstructured":"Kim, B.K., et al.: Hierarchical committee of deep convolutional neural networks for robust facial expression recognition. J. Multimodal User Interfaces 10(2), 173\u2013189 (2016)","journal-title":"J. Multimodal User Interfaces"},{"issue":"4","key":"1477_CR16","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1016\/j.cviu.2010.12.001","volume":"115","author":"S Moore","year":"2011","unstructured":"Moore, S., Bowden, R.: Local binary patterns for multi-view facial expression recognition. Comput. Vis. Image Underst. 115(4), 541\u2013558 (2011)","journal-title":"Comput. Vis. Image Underst."},{"key":"1477_CR17","doi-asserted-by":"crossref","unstructured":"Happy, S.L., Routray, A.: Robust facial expression classification using shape and appearance features. In: Eighth International Conference on Advances in Pattern Recognition IEEE, pp. 1\u20135 (2015)","DOI":"10.1109\/ICAPR.2015.7050661"},{"key":"1477_CR18","doi-asserted-by":"crossref","unstructured":"Ding, H., Zhou, S.K., Chellappa, R..: Facenet2expnet: regularizing a deep face recognition net for expression recognition. In: 2017 12th IEEE International Conference on Automatic Face and Gesture Recognition (FG 2017). IEEE (2017)","DOI":"10.1109\/FG.2017.23"},{"issue":"12","key":"1477_CR19","doi-asserted-by":"publisher","first-page":"1333","DOI":"10.1007\/s00371-013-0869-2","volume":"29","author":"S Berretti","year":"2013","unstructured":"Berretti, S., Del Bimbo, A., Pala, P.: Automatic facial expression recognition in real-time from dynamic sequences of 3D face scans. Vis. Comput. 29(12), 1333\u20131350 (2013)","journal-title":"Vis. Comput."},{"key":"1477_CR20","doi-asserted-by":"crossref","unstructured":"Khorrami, P., et al.: How deep neural networks can improve emotion recognition on video data. In: 2016 IEEE International Conference on Image Processing (ICIP). IEEE (2016)","DOI":"10.1109\/ICIP.2016.7532431"},{"key":"1477_CR21","doi-asserted-by":"publisher","unstructured":"Mollahosseini, A., Chan, D., Mahoor, M.H.: Going deeper in facial expression recognition using deep neural networks. In: 2016 IEEE Winter Conference on Applications of Computer Vision (WACV). IEEE, New York (2016). https:\/\/doi.org\/10.1109\/WACV.2016.7477450","DOI":"10.1109\/WACV.2016.7477450"},{"key":"1477_CR22","doi-asserted-by":"publisher","first-page":"453","DOI":"10.1016\/j.procs.2016.07.233","volume":"93","author":"V Mayya","year":"2016","unstructured":"Mayya, V., Pai, R.M., Pai, M.M.M.: Automatic facial expression recognition using DCNN. Procedia Comput. Sci. 93, 453\u2013461 (2016)","journal-title":"Procedia Comput. Sci."},{"issue":"6\u20138","key":"1477_CR23","doi-asserted-by":"publisher","first-page":"1001","DOI":"10.1007\/s00371-016-1243-y","volume":"32","author":"A Danelakis","year":"2016","unstructured":"Danelakis, A., Theoharis, T., Pratikakis, I.: A spatio-temporal wavelet-based descriptor for dynamic 3D facial expression retrieval and recognition. Vis. Comput. 32(6\u20138), 1001\u20131011 (2016)","journal-title":"Vis. Comput."},{"issue":"(C)","key":"1477_CR24","first-page":"52","volume":"54","author":"L Seung Ho","year":"2016","unstructured":"Seung Ho, L., Baddar, W.J., Yong, M.R.: Collaborative expression representation using peak expression and intra class variation face images for practical subject-independent emotion recognition in videos. Pattern Recogn. 54((C)), 52\u201367 (2016)","journal-title":"Pattern Recogn."},{"issue":"5","key":"1477_CR25","doi-asserted-by":"publisher","first-page":"373","DOI":"10.1177\/1059712316664017","volume":"24","author":"P Barros","year":"2016","unstructured":"Barros, P., Wermter, S.: Developing crossmodal expression recognition based on a deep neural model. Adapt. Behav. 24(5), 373\u2013396 (2016)","journal-title":"Adapt. Behav."},{"issue":"2","key":"1477_CR26","doi-asserted-by":"publisher","first-page":"2331","DOI":"10.1007\/s11042-015-3180-6","volume":"76","author":"D Gharavian","year":"2017","unstructured":"Gharavian, D., Bejani, M., Sheikhan, M.: Audio-visual emotion recognition using FCBF feature selection method and particle swarm optimization for fuzzy ARTMAP neural networks. Multimed. Tools Appl. 76(2), 2331\u20132352 (2017)","journal-title":"Multimed. Tools Appl."},{"key":"1477_CR27","unstructured":"Charles, D., Prodger, P.: The expression of the emotions in man and animals. Oxford University Press, USA (1998)"},{"key":"1477_CR28","unstructured":"Gibson, J.J.: The perception of the visual world. Houghton Mifflin Company, Boston (1950)"},{"issue":"13","key":"1477_CR29","first-page":"185","volume":"17","author":"BKP Horn","year":"1980","unstructured":"Horn, B.K.P., Brian, G.S.: Determining optical flow. Artif. Intell. 17(13), 185\u2013203 (1980)","journal-title":"Artif. Intell."},{"key":"1477_CR30","first-page":"69","volume-title":"Facial Expressions: A CrossCultural Study. Emotion Recognition: A Pattern Analysis Approach","author":"S Chrani","year":"2015","unstructured":"Chrani, S., et al.: Facial Expressions: A CrossCultural Study. Emotion Recognition: A Pattern Analysis Approach, pp. 69\u201387. Wiley, New York (2015)"},{"issue":"5","key":"1477_CR31","doi-asserted-by":"publisher","first-page":"699","DOI":"10.1109\/TPAMI.2005.93","volume":"27","author":"Y Zhang","year":"2005","unstructured":"Zhang, Y., Ji, Q.: Active and dynamic information fusion for facial expression understanding from image sequences. IEEE Trans. Pattern Anal. Mach. Intell. 27(5), 699\u2013714 (2005)","journal-title":"IEEE Trans. Pattern Anal. Mach. Intell."},{"key":"1477_CR32","doi-asserted-by":"crossref","unstructured":"Farneback, G.: Two-frame motion estimation based on polynomial expansion. Lecture Notes in Computer Science, pp. 363\u2013370 (2003)","DOI":"10.1007\/3-540-45103-X_50"},{"key":"1477_CR33","doi-asserted-by":"publisher","first-page":"541","DOI":"10.1162\/neco.1989.1.4.541","volume":"1","author":"Y LeCun","year":"1989","unstructured":"LeCun, Y., et al.: Backpropagation applied to handwritten zip code recognition. Neural Comput. 1, 541\u2013551 (1989)","journal-title":"Neural Comput."},{"key":"1477_CR34","doi-asserted-by":"crossref","unstructured":"Behnke, S.: Discovering hierarchical speech features using convolutional non-negative matrix factorization. In: International Joint Conference on Neural Networks IEEE, vol. 4, pp. 2758\u20132763 (2003)","DOI":"10.1109\/IJCNN.2003.1224004"},{"key":"1477_CR35","volume-title":"Deep Learning","author":"I Goodfellow","year":"2016","unstructured":"Goodfellow, I., Bengio, Y., Courville, A.: Deep Learning. MIT Press, Cambridge (2016)"},{"key":"1477_CR36","unstructured":"Krogh, A., Hertz, J.: A simple weight decay can improve generalization. In: Neural Information Processing Systems, pp. 950\u2013957 (1992)"},{"key":"1477_CR37","first-page":"1929","volume":"15.1","author":"N Srivastava","year":"2014","unstructured":"Srivastava, N., et al.: Dropout: a simple way to prevent neural networks from overfitting. J. Mach. Learn. Res. 15.1, 1929\u20131958 (2014)","journal-title":"J. Mach. Learn. Res."},{"key":"1477_CR38","volume-title":"Using Early Stopping to Reduce Overfltting in Wrapper-Based Feature Weighting","author":"J Loughrey","year":"2005","unstructured":"Loughrey, J., Cunningham, P.: Using Early Stopping to Reduce Overfltting in Wrapper-Based Feature Weighting. Trinity College Dublin, Department of Computer Science, Dublin (2005)"},{"key":"1477_CR39","doi-asserted-by":"crossref","unstructured":"Hutter, F., Hoos, H.H., Leytonbrown, K.: Sequential model-based optimization for general algorithm configuration. In: Learning and Intelligent Optimization, pp. 507\u2013523 (2011)","DOI":"10.1007\/978-3-642-25566-3_40"},{"key":"1477_CR40","unstructured":"Bergstra, J., et al.: Algorithms for hyper-parameter optimization. In: Neural Information Processing Systems, pp. 2546\u20132554 (2011)"},{"key":"1477_CR41","unstructured":"Snoek, J., Larochelle, H., Adams, R.P.: Practical Bayesian optimization of machine learning algorithms. In: Neural Information Processing Systems, pp. 2951\u20132959 (2012)"},{"key":"1477_CR42","doi-asserted-by":"crossref","unstructured":"Thornton, C., et al.: Auto-WEKA: combined selection and hyperparameter optimization of classification algorithms. In: Knowledge Discovery and Data Mining, pp. 847\u2013855 (2013)","DOI":"10.1145\/2487575.2487629"},{"key":"1477_CR43","doi-asserted-by":"crossref","unstructured":"Bergstra, J., Yamins, D., Cox, D.D.: Hyperopt: a python library for optimizing the hyperparameters of machine learning algorithms. In: Proceedings of the 12th Python in Science Conference (2013)","DOI":"10.25080\/Majora-8b375195-003"},{"key":"1477_CR44","unstructured":"Kanade, T., Cohn, J.F., Tian, Y.: Comprehensive database for facial expression analysis. In: IEEE International Conference on Automatic Face and Gesture Recognition, pp. 46\u201353 (2000)"},{"key":"1477_CR45","doi-asserted-by":"crossref","unstructured":"Lucey, P., et al.: The extended cohn-kanade dataset (CK+): a complete dataset for action unit and emotion-specified expression. In: Computer Vision and Pattern Recognition, pp. 94\u2013101 (2010)","DOI":"10.1109\/CVPRW.2010.5543262"},{"key":"1477_CR46","unstructured":"Haq, S., Jackson, P.J.B.: Speaker-dependent audio-visual emotion recognition. In: Proceedings of the International Conference on Auditory-Visual Speech Processing (AVSP\u201909), Norwich, pp. 53\u201358 (2009)"},{"key":"1477_CR47","doi-asserted-by":"publisher","first-page":"34","DOI":"10.1109\/MMUL.2012.26","volume":"19","author":"A Dhall","year":"2012","unstructured":"Dhall, A., Goecke, R., Lucey, S., Gedeon, T.: Collecting large, richly annotated facial expression databases from movies. IEEE MultiMed. 19, 34\u201341 (2012)","journal-title":"IEEE MultiMed."},{"key":"1477_CR48","doi-asserted-by":"crossref","unstructured":"Dhall, A., Goecke, R., Joshi, J., Sikka, J., Gedeon, T.: Emotion recognition in the wild challenge 2014: baseline, data and protocol. In: ACM ICMI (2014)","DOI":"10.1145\/2663204.2666275"},{"key":"1477_CR49","doi-asserted-by":"crossref","unstructured":"Dhall, A., et al.: Video and image based emotion recognition challenges in the wild: EmotiW 2015. In: International Conference on Multimodal Interfaces, pp. 423\u2013426 (2015)","DOI":"10.1145\/2818346.2829994"},{"key":"1477_CR50","doi-asserted-by":"crossref","unstructured":"Dhall, A., et al.: EmotiW 2016: video and group-level emotion recognition challenges. In: ACM International Conference on Multimodal Interaction ACM, pp. 427\u2013432 (2016)","DOI":"10.1145\/2993148.2997638"},{"issue":"4","key":"1477_CR51","first-page":"127","volume":"21","author":"PI Wilson","year":"2006","unstructured":"Wilson, P.I., Fernandez, J.D.: Facial feature detection using Haar classifiers. J. Comput. Sci. Coll. 21(4), 127\u2013133 (2006)","journal-title":"J. Comput. Sci. Coll."},{"key":"1477_CR52","unstructured":"Franois Chollet.: Keras. https:\/\/github.com\/fchollet\/keras (2015)"},{"key":"1477_CR53","doi-asserted-by":"publisher","first-page":"399","DOI":"10.1016\/j.patcog.2016.12.002","volume":"64","author":"X Fan","year":"2017","unstructured":"Fan, X., Tjahjadi, T.: A dynamic framework based on local Zernike moment and motion history image for facial expression recognition. Pattern Recogn. 64, 399\u2013406 (2017)","journal-title":"Pattern Recogn."},{"key":"1477_CR54","doi-asserted-by":"publisher","first-page":"66","DOI":"10.1016\/j.imavis.2017.01.012","volume":"65","author":"H Kaya","year":"2017","unstructured":"Kaya, H., G\u00fcrp\u0131nar, F., Salah, A.A.: Video-based emotion recognition in the wild using deep transfer learning and score fusion. Image Vis. Comput. 65, 66\u201375 (2017)","journal-title":"Image Vis. Comput."}],"container-title":["The Visual Computer"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s00371-018-1477-y\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-018-1477-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s00371-018-1477-y.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2025,7,4]],"date-time":"2025-07-04T04:23:45Z","timestamp":1751603025000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s00371-018-1477-y"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2018,5,4]]},"references-count":54,"journal-issue":{"issue":"10","published-print":{"date-parts":[[2018,10]]}},"alternative-id":["1477"],"URL":"https:\/\/doi.org\/10.1007\/s00371-018-1477-y","relation":{},"ISSN":["0178-2789","1432-2315"],"issn-type":[{"value":"0178-2789","type":"print"},{"value":"1432-2315","type":"electronic"}],"subject":[],"published":{"date-parts":[[2018,5,4]]},"assertion":[{"value":"4 May 2018","order":1,"name":"first_online","label":"First Online","group":{"name":"ArticleHistory","label":"Article History"}}]}}