Recognizing facial expression: machine learning and application to spontaneous behavior

By M. Bartlett, Gwen Littlewort, Mark G. Frank, Claudia Lainscsek, Ian R. Fasel, Javier R. Movellan. Computer Vision and Pattern Recognition, 2005

730 citations recorded by the source corpus.

Subfields: Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology, Signal Processing

View Paper: https://www.semanticscholar.org/paper/1bcbf2a4500d27d036e0f9d36d7af71c72f8ab61

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computer Vision and Pattern Recognition

In Experimental and Cognitive Psychology

In Signal Processing

Citations in the corpus

Exploiting sparsity and co-occurrence structure for action unit recognition (2015, methodology): “Most approaches are direct applications of existing classiﬁcation techniques, such as SVMs [4], [28] and Bayes Nets [26], operating on geometric or appearance features such as histograms of oriented gradients (HOG) and Gabor energy ﬁlters.”
Real-time classification of evoked emotions using facial feature tracking and physiological responses (2008, methodology): “Moreover, recent work in Bartlett et al. (2005) has continued to make use of representations based on a combination of feature geometry and texture features. A system developed by Lyons (2004) automatically translated facial gestures to actions using vision techniques. For a more detailed review of ”
DISFA: A Spontaneous Facial Action Intensity Database (2013, methodology): “Gabor filters are another widely used technique for representing facial textures in face and expression recognition [62], [63].”
Facial expression recognition based on Local Binary Patterns: A comprehensive study (2009, methodology): “Due to their superior performance, Gabor-wavelet representations have been widely adopted in face image analysis [25,7,26,19].”
Facial expression recognition with Convolutional Neural Networks: Coping with few data and the training sample order (2017, methodology): “These changes are usually extracted using geometric feature-based methods [25, 26, 27, 21] or appearance-based methods [25, 9, 28, 8, 11, 10, 13].”
Compound facial expressions of emotion (2014, methodology): “Gabor filters have also been successfully applied to the recognition of the six basic emotion categories (24, 31).”
Automatic Recognition of Facial Actions in Spontaneous Expressions (2006, background): “Mor e recently, [46], applied a dynamical Bayesian model to the output of a front-end FACS recognition system based on the one developed in our laboratory [3], [4].”
Deep-Emotion: Facial Expression Recognition Using Attentional Convolutional Network (2019, background): “Some of the popular hand-crafted features used for facial expression recognition include the histogram of oriented gradients (HOG) [23,24], local binary patterns (LBP) [25], Gabor wavelets [26], and Haar features [27].”
Evidence‐Based Assessment as an Integrative Model for Applying Psychological Science to Guide the Voyage of Treatment (2017, background): “What about empathy? Machine learning has already moved from face recognition to emotion recognition (Bartlett et al., 2005), and cell phone apps are even now monitoring our emotional responses to advertising.”
FaceNet2ExpNet: Regularizing a Deep Face Recognition Net for Expression Recognition (2016, neutral): “Classes CSPL [16] 89.9% Six Classes AdaGabor [35] 93.3% LBPSVM [36] 95.1% 3DCNN-DAP [21] 92.4% BDBN [19] 96.7% STM-ExpLet [20] 94.2% DTAGN [22] 97.3% Inception [23] 93.2% LOMo [37] 95.1% PPDN [9] 97.3% FN2EN 98.6% AUDN [18] 92.1% Eight Classes Train From Scratch (BN) 88.7% VGG Fine-Tune (baseline)…”
Automatic facial expression recognition using features of salient facial patches (2015, neutral): “E-mail: {happy,aroutray}@iitkgp.ac.in. many researchers ( [9], [10], [11], [12], [13], [14], [15]).”
3D Facial Expression Recognition Based on Primitive Surface Feature Distribution (2006, background): “Over the past decade, a number of techniques have been successfully developed for facial expression recognition, including optical flow [28, 10] and Gabor wavelets [16], and FACS-feature based techniques [22, 1, 6, 31].”
Affective Body Expression Perception and Recognition: A Survey (2013, background): “The majority of the automatic affect recognition systems have focused mainly on using facial expressions [106], [107], [108] and voice [109], [110], [111], [112] as the input modality.”
Facial Action Unit Recognition by Exploiting Their Dynamic and Semantic Relationships (2007, methodology): “Compared with the system performance reported by Bartlett et al. at their Web site [40] (with an overall average recognition rate of 93.6 percent), our system achieves a similar average recognition rate (93.33 percent).”