Comprehensive database for facial expression analysis

By Takeo Kanade, Ying-li Tian, Jeffrey F. Cohn. Proceedings Fourth IEEE International Conference on Automatic Face and Gesture Recognition (Cat. No. PR00580), 2000

2,908 citations recorded by the source corpus.

Subfields: Cognitive Neuroscience, Computer Vision and Pattern Recognition, Experimental and Cognitive Psychology

View Paper: https://www.semanticscholar.org/paper/e3f2391513693647e0ea87bfa86cd89e468f51d0

How researchers see this paper

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

In Cognitive Neuroscience

In Computer Vision and Pattern Recognition

In Experimental and Cognitive Psychology

Citations in the corpus

Facial Expression Recognition in Image Sequences Using Geometric Deformation Features and Support Vector Machines (2007, methodology): “The most significant nodes (around the eyes, eyebrows and mouth) should be chosen, since they are responsible for the formation of facial deformations modelled by FACS.”
Heterogeneous Face Attribute Estimation: A Deep Multi-Task Learning Approach (2017, background): “Facial expression recognition accuracy has been substantially improved from less than 80% to over than 93% on the Cohn-Kanade database [38], [39].”
The eNTERFACE05 Audio-Visual Emotion Database (2006, background): “In the past few years, the Cohn-Kanade facial database [1] imposed itself as the main benchmark database for facial expression recognition algorithms.”
Real Time Face Detection and Facial Expression Recognition: Development and Applications to Human Computer Interaction. (2003, methodology): “The system was trained and tested on Cohn and Kanade’s DFAT-504 dataset [7].”
Robust facial expression recognition using local binary patterns (2005, methodology): “The proposed algorithm were trained and tested on the CohnKanade Facial Expression Database [13].”
Adaptive computation and machine learning (1998, methodology): “The data set comprises 375 such pictures made of 140 × 100 pixels (Abboud et al., 2003; Kanade et al., 2000) We tested kernelized logistic regression (Gaussian kernel), its minimum entropy version, nearest neighbor, and the consistency method.”
CREMA-D: Crowd-sourced Emotional Multimodal Actors Dataset (2014, background): “Datasets consisting of emotion expressions are available that contain rated visual displays [16], [17], [18], [19], auditory stimuli [20], [21], [22], [23], [24] and audio-visual clips [25], [26], [27], [28], [29], but these are relatively small, with perceptual rating only from a few raters or do…”
Deeply Learning Deformable Facial Action Parts Model for Dynamic Expression Analysis (2014, background): “CK+ database contains 593 videos of 123 different subjects, which is an extended version of CK database [22].”
Observer-based measurement of facial expression with the Facial Action Coding System. (2007, background): “In all, the action units from the primary (Sayette et al., 2001) and supplementary (Cohn et al., 2003; Kanade et al., 2000) sources include those that have occurred most frequently in studies of both spontaneous and deliberate facial behavior.”
Recognizing facial expression: machine learning and application to spontaneous behavior (2005, positive): “The facial expression system was trained and tested on Cohn and Kanade's DFAT-504 dataset [7].”
Facial Expression Analysis under Partial Occlusion (2018, background): “2) The Cohn-Kanade (CK) database [Kanade et al. 2000] is a popular comprehensive dataset for facial expression benchmark tests.”
Towards Reading Hidden Emotions: A Comparative Study of Spontaneous Micro-Expression Spotting and Recognition Methods (2015, neutral): “Several FE databases exist, such as JAFFE [15], CK [16], MMI [17] and others.”
Region Attention Networks for Pose and Occlusion Robust Facial Expression Recognition (2019, background): “[32] present a comprehensive analysis on occluded FER based on Gabor features and human observers, and find that an occluded mouth degrades FER more than occluded eyes on JAFFE [44] and CK [30].”
Image and Video Retrieval (2003, methodology): “However, detecting the object(s) of interest is an unresolved issue [9].”