{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,5,15]],"date-time":"2026-05-15T01:55:24Z","timestamp":1778810124944,"version":"3.51.4"},"reference-count":51,"publisher":"Springer Science and Business Media LLC","issue":"2-4","license":[{"start":{"date-parts":[[2017,4,8]],"date-time":"2017-04-08T00:00:00Z","timestamp":1491609600000},"content-version":"unspecified","delay-in-days":0,"URL":"http:\/\/www.springer.com\/tdm"}],"content-domain":{"domain":["link.springer.com"],"crossmark-restriction":false},"short-container-title":["Int J Comput Vis"],"published-print":{"date-parts":[[2018,4]]},"DOI":"10.1007\/s11263-017-1010-1","type":"journal-article","created":{"date-parts":[[2017,4,8]],"date-time":"2017-04-08T01:19:49Z","timestamp":1491614389000},"page":"255-271","update-policy":"https:\/\/doi.org\/10.1007\/springer_crossmark_policy","source":"Crossref","is-referenced-by-count":58,"title":["Confidence-Weighted Local Expression Predictions for Occlusion Handling in Expression Recognition and Action Unit Detection"],"prefix":"10.1007","volume":"126","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0074-8719","authenticated-orcid":false,"given":"Arnaud","family":"Dapogny","sequence":"first","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"Kevin","family":"Bailly","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]},{"given":"S\u00e9verine","family":"Dubuisson","sequence":"additional","affiliation":[],"role":[{"role":"author","vocabulary":"crossref"}]}],"member":"297","published-online":{"date-parts":[[2017,4,8]]},"reference":[{"issue":"1","key":"1010_CR1","doi-asserted-by":"crossref","first-page":"5","DOI":"10.1023\/A:1010933404324","volume":"45","author":"L Breiman","year":"2001","unstructured":"Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5\u201332.","journal-title":"Machine Learning"},{"issue":"1\u20133","key":"1010_CR2","doi-asserted-by":"crossref","first-page":"287","DOI":"10.1023\/A:1013964023376","volume":"48","author":"T Bylander","year":"2002","unstructured":"Bylander, T. (2002). Estimating generalization error on two-class datasets using out-of-bag estimates. Machine Learning, 48(1\u20133), 287\u2013297.","journal-title":"Machine Learning"},{"key":"1010_CR3","unstructured":"Chen, C., Liaw, A., & Breiman, L. (2004). Using random forest to learn imbalanced data (Vol. 110). Technical report. Berkeley: University of California."},{"key":"1010_CR4","doi-asserted-by":"crossref","unstructured":"Chu, W.-S., De\u00a0la Torre, F., & Cohn, J. F. (2013). Selective transfer machine for personalized facial action unit detection. In CVPR (pp. 3515\u20133522).","DOI":"10.1109\/CVPR.2013.451"},{"key":"1010_CR5","doi-asserted-by":"crossref","unstructured":"Cotter, S. F. (2010). Sparse representation for accurate classification of corrupted and occluded facial expressions. In ICASSP (pp. 838\u2013841).","DOI":"10.1109\/ICASSP.2010.5494903"},{"key":"1010_CR6","doi-asserted-by":"crossref","unstructured":"Dapogny, A., Bailly, K., & Dubuisson, S. (2015) Pairwise conditional random forests for facial expression recognition. In ICCV.","DOI":"10.1109\/ICCV.2015.431"},{"key":"1010_CR7","doi-asserted-by":"crossref","unstructured":"Dhall, A., Goecke, R., Lucey, S., & Gedeon, T. (2011). Static facial expression analysis in tough conditions: Data, evaluation protocol and benchmark. In ICCV Workshops (pp. 2106\u20132112).","DOI":"10.1109\/ICCVW.2011.6130508"},{"key":"1010_CR8","doi-asserted-by":"crossref","unstructured":"Doll\u00e1r, P., Tu, Z., Perona, P., & Belongie, S. (2009). Integral channel features. In BMVC.","DOI":"10.5244\/C.23.91"},{"key":"1010_CR9","doi-asserted-by":"crossref","unstructured":"Du, S., Tao, Y., & Martinez, A. M. (2014). Compound facial expressions of emotion. In Proceedings of the National Academy of Sciences (pp. 111).","DOI":"10.1073\/pnas.1322355111"},{"key":"1010_CR10","unstructured":"Ekman, P., & Friesen, W. V. (1977). Facial action coding system. Palo Alto: Consulting Psychologists Press."},{"issue":"2","key":"1010_CR11","doi-asserted-by":"crossref","first-page":"124","DOI":"10.1037\/h0030377","volume":"17","author":"Paul Ekman","year":"1971","unstructured":"Ekman, Paul, & Friesen, W. V. (1971). Constants across cultures in the face and emotion. Journal of Personality and Social Psychology, 17(2), 124.","journal-title":"Journal of Personality and Social Psychology"},{"key":"1010_CR12","doi-asserted-by":"crossref","unstructured":"Eleftheriadis, S., Rudovic, O., & Pantic, M. (2015). Multi-conditional latent variable model for joint facial action unit detection. In ICCV.","DOI":"10.1109\/ICCV.2015.432"},{"issue":"1","key":"1010_CR13","doi-asserted-by":"crossref","first-page":"189","DOI":"10.1109\/TIP.2014.2375634","volume":"24","author":"S Eleftheriadis","year":"2015","unstructured":"Eleftheriadis, S., Rudovic, O., & Pantic, M. (2015). Discriminative shared gaussian processes for multiview and view-invariant facial expression recognition. IEEE Transactions on Image Processing, 24(1), 189\u2013204.","journal-title":"IEEE Transactions on Image Processing"},{"key":"1010_CR14","doi-asserted-by":"crossref","unstructured":"Ghiasi, G., & Fowlkes, C. C. (2014). Occlusion coherence: Localizing occluded faces with a hierarchical deformable part model. In CVPR (pp. 1899\u20131906).","DOI":"10.1109\/CVPR.2014.306"},{"key":"1010_CR15","doi-asserted-by":"crossref","unstructured":"Ghosh, S., Laksana, E., Scherer, S., & Morency, L.-P. (2015) A multi-label convolutional neural network approach to cross-domain action unit detection. In ACII.","DOI":"10.1109\/ACII.2015.7344632"},{"issue":"1","key":"1010_CR16","first-page":"51","volume":"3","author":"MK Greenwald","year":"1989","unstructured":"Greenwald, M. K., Cook, E. W., & Lang, P. J. (1989). Affective judgment and psychophysiological response: Dimensional covariation in the evaluation of pictorial stimuli. Journal of Psychophysiology, 3(1), 51\u201364.","journal-title":"Journal of Psychophysiology"},{"key":"1010_CR17","doi-asserted-by":"crossref","unstructured":"Hayat, M., Bennamoun, M., & El-Sallam, A. A. (2012). Evaluation of spatiotemporal detectors and descriptors for facial expression recognition. In International Conference on Human-System Interaction (pp. 43\u201347).","DOI":"10.1109\/HSI.2012.16"},{"issue":"16","key":"1010_CR18","doi-asserted-by":"crossref","first-page":"2181","DOI":"10.1016\/j.patrec.2012.07.015","volume":"33","author":"X Huang","year":"2012","unstructured":"Huang, X., Zhao, G., Zheng, W., & Pietik\u00e4inen, M. (2012). Towards a dynamic expression recognition system under facial occlusion. Pattern Recognition Letters, 33(16), 2181\u20132191.","journal-title":"Pattern Recognition Letters"},{"key":"1010_CR19","doi-asserted-by":"crossref","unstructured":"Jeni, L., Cohn, J. F, & Kanade, J. F. (2015). Dense 3d face alignment from 2d videos in real-time. In FG.","DOI":"10.1109\/FG.2015.7163142"},{"key":"1010_CR20","doi-asserted-by":"crossref","unstructured":"Jiang, B., Valstar, M. F, & Pantic, M. (2011). Action unit detection using sparse appearance descriptors in space-time video volumes. In FG (pp. 314\u2013321).","DOI":"10.1109\/FG.2011.5771416"},{"key":"1010_CR21","volume-title":"Principal component analysis","author":"I Jolliffe","year":"2002","unstructured":"Jolliffe, I. (2002). Principal component analysis. NewYork: Wiley."},{"issue":"7","key":"1010_CR22","doi-asserted-by":"crossref","first-page":"1052","DOI":"10.1016\/j.imavis.2007.11.004","volume":"26","author":"I Kotsia","year":"2008","unstructured":"Kotsia, I., Buciu, I., & Pitas, I. (2008). An analysis of facial expression recognition under partial facial image occlusion. Image and Vision Computing, 26(7), 1052\u20131067.","journal-title":"Image and Vision Computing"},{"key":"1010_CR23","unstructured":"Linusson, H. (2013). Multi-output random forests. University of Bor\u00e5s\/School of Business and IT."},{"key":"1010_CR24","doi-asserted-by":"crossref","unstructured":"Liu, M., Li, S., Shan, Shiguang, S., & Chen, X. (2013). Enhancing expression recognition in the wild with unlabeled reference data. In ACCV (pp. 577\u2013588).","DOI":"10.1007\/978-3-642-37444-9_45"},{"key":"1010_CR25","doi-asserted-by":"crossref","first-page":"126","DOI":"10.1016\/j.neucom.2015.02.011","volume":"159","author":"M Liu","year":"2015","unstructured":"Liu, M., Li, S., Shan, S., & Chen, X. (2015). Au-inspired deep networks for facial expression feature learning. Neurocomputing, 159, 126\u2013136.","journal-title":"Neurocomputing"},{"key":"1010_CR26","doi-asserted-by":"crossref","unstructured":"Lucey, P., Cohn J. F., Kanade, T., Saragih, J., Ambadar, Z., & Matthews, I. (2010). The extended cohn-kanade dataset (CK+): A complete dataset for action unit and emotion-specified expression. In CVPR Workshops (pp. 94\u2013101).","DOI":"10.1109\/CVPRW.2010.5543262"},{"issue":"2","key":"1010_CR27","doi-asserted-by":"crossref","first-page":"151","DOI":"10.1109\/T-AFFC.2013.4","volume":"4","author":"SM Mavadati","year":"2013","unstructured":"Mavadati, S. M., Mahoor, M. H., Bartlett, K., Trinh, P., & Cohn, J. F. (2013). DISFA: A spontaneous facial action intensity database. Transactions on Affective Computing, 4(2), 151\u2013160.","journal-title":"Transactions on Affective Computing"},{"key":"1010_CR28","doi-asserted-by":"crossref","unstructured":"Nicolle, J., Bailly, K., & Chetouani, M. (2015). Facial action unit intensity prediction via hard multi-task metric learning for kernel regression. In FG.","DOI":"10.1109\/FG.2015.7284868"},{"key":"1010_CR29","doi-asserted-by":"crossref","unstructured":"Pei, Y., Kim, T.-K., & Zha, H. (2013). Unsupervised random forest manifold alignment for lipreading. In ICCV (pp. 129\u2013136).","DOI":"10.1109\/ICCV.2013.23"},{"key":"1010_CR30","doi-asserted-by":"crossref","unstructured":"Ranzato, M. A., Susskind, J., Mnih, V., & Hinton, G. (2011). On deep generative models with applications to recognition. In CVPR (pp. 2857\u20132864).","DOI":"10.1109\/CVPR.2011.5995710"},{"key":"1010_CR31","doi-asserted-by":"crossref","unstructured":"Ren, S., Cao, X., Wei, Y., & Sun, J. (2014). Face alignment at 3000 fps via regressing local binary features. In CVPR (pp. 1685\u20131692).","DOI":"10.1109\/CVPR.2014.218"},{"key":"1010_CR32","doi-asserted-by":"crossref","unstructured":"Rifai, S., Bengio, Y., Courville, A., Vincent, P., & Mirza, M. (2012). Disentangling factors of variation for facial expression recognition. In ECCV.","DOI":"10.1007\/978-3-642-33783-3_58"},{"key":"1010_CR33","unstructured":"Rifai, S., Vincent, P., Muller, X., Glorot, X., & Bengio, Y. (2011). Contractive auto-encoders: Explicit invariance during feature extraction. In ICML (pp. 833\u2013840)."},{"key":"1010_CR34","doi-asserted-by":"crossref","unstructured":"Sandbach, G., Zafeiriou, S., Pantic, M., & Rueck, D. (2011). A dynamic approach to the recognition of 3D facial expressions and their temporal models. In FG (pp. 406\u2013413).","DOI":"10.1109\/FG.2011.5771434"},{"key":"1010_CR35","doi-asserted-by":"crossref","unstructured":"Savran, A., Aly\u00fcz, N., Dibeklio\u011flu, H., \u00c7eliktutan, O., G\u00f6kberk, B., Sankur, B., & Akarun, L. (2008). Bosphorus database for 3d face analysis. In Biometrics and Identity Management (pp. 47\u201356).","DOI":"10.1007\/978-3-540-89991-4_6"},{"key":"1010_CR36","unstructured":"S\u00e9n\u00e9chal, T., Rapp, V., Salam, H., Seguier, R., Bailly, K., & Prevost, L. (2012). Facial action recognition combining heterogeneous features via multikernel learning. TSMC-B (pp. 42)."},{"issue":"6","key":"1010_CR37","doi-asserted-by":"crossref","first-page":"803","DOI":"10.1016\/j.imavis.2008.08.005","volume":"27","author":"C Shan","year":"2009","unstructured":"Shan, C., Gong, S., & McOwan, P. W. (2009). Facial expression recognition based on local binary patterns: A comprehensive study. Image and Vision Computing, 27(6), 803\u2013816.","journal-title":"Image and Vision Computing"},{"key":"1010_CR38","doi-asserted-by":"crossref","unstructured":"Sun, Y., & Yin, L. (2008). Facial expression recognition based on 3D dynamic range model sequences. In ECCV (pp. 58\u201371).","DOI":"10.1007\/978-3-540-88688-4_5"},{"key":"1010_CR39","unstructured":"Van de Weijer, J., Ruiz, A., & Binefa, X. (2015). From emotions to action units with hidden and semi-hidden-task learning. In ICCV."},{"key":"1010_CR40","first-page":"3371","volume":"11","author":"P Vincent","year":"2010","unstructured":"Vincent, P., Larochelle, H., Lajoie, I., Bengio, Y., & Manzagol, P.-A. (2010). Stacked denoising autoencoders: Learning useful representations in a deep network with a local denoising criterion. Journal of Machine Learning Research, 11, 3371\u20133408.","journal-title":"Journal of Machine Learning Research"},{"key":"1010_CR41","unstructured":"Wallhoff, F. (2006). Database with facial expressions and emotions from technical university of Munich (feedtum)."},{"key":"1010_CR42","doi-asserted-by":"crossref","unstructured":"Xiong, X., & De\u00a0la Torre, F. (2013). Supervised descent method and its applications to face alignment. In CVPR (pp. 532\u2013539).","DOI":"10.1109\/CVPR.2013.75"},{"key":"1010_CR43","doi-asserted-by":"crossref","unstructured":"Xu, L., & Mordohai, P. (2010). Automatic facial expression recognition using bags of motion words. In BMVC (pp. 1\u201313).","DOI":"10.5244\/C.24.13"},{"key":"1010_CR44","unstructured":"Yin, L., Chen, X., & Sun, Y. (2008). Tony Worm, and Michael Reale. A high-resolution 3D dynamic facial expression database. In FG (pp. 1\u20136)."},{"issue":"1","key":"1010_CR45","doi-asserted-by":"crossref","first-page":"39","DOI":"10.1109\/TPAMI.2008.52","volume":"31","author":"Z Zeng","year":"2009","unstructured":"Zeng, Z., Pantic, M., Roisman, G. I., & Huang, T. S. (2009). A survey of affect recognition methods: Audio, visual, and spontaneous expressions. IEEE Transactions on Pattern Analysis and Machine Intelligence, 31(1), 39\u201358.","journal-title":"IEEE Transactions on Pattern Analysis and Machine Intelligence"},{"key":"1010_CR46","doi-asserted-by":"crossref","first-page":"451","DOI":"10.1016\/j.neucom.2014.05.008","volume":"145","author":"L Zhang","year":"2014","unstructured":"Zhang, L., Tjondronegoro, D., & Chandran, V. (2014). Random Gabor based templates for facial expression recognition in images with facial occlusion. Neurocomputing, 145, 451\u2013464.","journal-title":"Neurocomputing"},{"issue":"10","key":"1010_CR47","doi-asserted-by":"crossref","first-page":"692","DOI":"10.1016\/j.imavis.2014.06.002","volume":"32","author":"X Zhang","year":"2014","unstructured":"Zhang, X., Yin, L., Cohn, J. F., Canavan, S., Reale, M., Horowitz, A., et al. (2014). BP4D-spontaneous a high-resolution spontaneous 3D dynamic facial expression database. Image and Vision Computing, 32(10), 692\u2013706.","journal-title":"Image and Vision Computing"},{"key":"1010_CR48","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.-S., De la Torre, F., Jeffrey, F. C., & Honggang, Z. (2015). Joint patch and multi-label learning for facial action unit detection. In CVPR.","DOI":"10.1109\/CVPR.2015.7298833"},{"key":"1010_CR49","doi-asserted-by":"crossref","unstructured":"Zhao, K., Chu, W.-S., & Zhang, H. (2016). Deep region and multi-label learning for facial action unit detection. In CVPR.","DOI":"10.1109\/CVPR.2016.369"},{"key":"1010_CR50","doi-asserted-by":"crossref","unstructured":"Zhao, X., Kim, T. K., & Luo, W. (2014). Unified face analysis by iterative multi-output random forests. In CVPR (pp. 1765\u20131772).","DOI":"10.1109\/CVPR.2014.228"},{"key":"1010_CR51","unstructured":"Zhong, L., Liu, Q., Yang, P., Liu, B., Huang, J., & Metaxas, D. N. (2012). Learning active facial patches for expression analysis. In CVPR (pp. 2562\u20132569)."}],"container-title":["International Journal of Computer Vision"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/link.springer.com\/article\/10.1007\/s11263-017-1010-1\/fulltext.html","content-type":"text\/html","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-017-1010-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/link.springer.com\/content\/pdf\/10.1007\/s11263-017-1010-1.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2018,2,19]],"date-time":"2018-02-19T23:08:19Z","timestamp":1519081699000},"score":1,"resource":{"primary":{"URL":"http:\/\/link.springer.com\/10.1007\/s11263-017-1010-1"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2017,4,8]]},"references-count":51,"journal-issue":{"issue":"2-4","published-print":{"date-parts":[[2018,4]]}},"alternative-id":["1010"],"URL":"https:\/\/doi.org\/10.1007\/s11263-017-1010-1","relation":{},"ISSN":["0920-5691","1573-1405"],"issn-type":[{"value":"0920-5691","type":"print"},{"value":"1573-1405","type":"electronic"}],"subject":[],"published":{"date-parts":[[2017,4,8]]}}}