The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression

By Patrick Lucey, Jeffrey F. Cohn, Takeo Kanade, Jason M. Saragih, Zara Ambadar, Iain Matthews. 2010 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Workshops, 2010

4,044 citations recorded by the source corpus.

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

View Paper: https://www.semanticscholar.org/paper/7dcdfe89a36e4e54d33362c164e09709a19bef7f

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

Citations in the corpus

Video-Based Facial Micro-Expression Analysis: A Survey of Datasets, Features and Algorithms (2021, methodology): “For SAMM, the CK+ dataset [122] are used as macro-expression samples. the micro-expression samples ﬁne-tuning, which solves the problem of the insufﬁcient number of micro-expression samples.”
Max-Margin Early Event Detectors (2012, background): “To the best of our knowledge, this is the first paper in the literature of computer vision that proposes a learning formulation for early event detection.”
Automatic Analysis of Facial Actions: A Survey (2019, background): “The extended CK+ database has a similar function [105].”
Facial Landmark Detection: A Literature Survey (2018, background): “– CK/CK+ (Kanade et al. 2000; Lucey et al. 2010): The Cohn-Kanade AU-coded expression database (CK) contains 486 (593 in CK+) video sequences of frontal faces from 97+ subjects with 6 basic expressions, including happy, surprised, sadness, disgust, fear and anger.”
Reliable Crowdsourcing and Deep Locality-Preserving Learning for Expression Recognition in the Wild (2017, methodology): “We then conducted a CK+ [26] and RAF cross-database study to explore the speciﬁc difference between expression-Algorithm 1 Label reliability estimation algorithm.”
Modeling Stylized Character Expressions via Deep Learning (2016, methodology): “For human facial expression data collection, we combined publicly available annotated facial expression databases: extended CK+ [36], DISFA [37], KDEF [38] and MMI [39].”
Knowledge Augmented Deep Neural Networks for Joint Facial Expression and Action Unit Recognition (2020, methodology): “For CK+, gBN with 80% GT AU annotations achieves average F1-score 0 .”
Classifier learning with hidden information (2015, methodology): “The experiment is performed on extended Cohn-Kanade dataset (CK+) dataset [23] which contains 327 video sequences performed by 210 subjects.”
Learning Discriminative Fisher Kernels (2011, methodology): “We represent each frame by the variation2 of the feature point locations with respect to the first frame (Lucey et al., 2010), leading to time series with a 2× 68 = 136-dimensional feature representation.”
Exploiting sparsity and co-occurrence structure for action unit recognition (2015, methodology): “• Superior performance over the state-of-the-art on the CK+ [19], G.”
Spatial–Temporal Recurrent Neural Network for Emotion Recognition (2017, methodology): “The proposed STRNN method is tested on both SJTU emotion EEG dataset (SEED) [2] and the dataset of CK+ facial expression image sequences [31].”
A Micro-GA Embedded PSO Feature Selection Approach to Intelligent Facial Emotion Recognition (2017, methodology): “The system is evaluated with two facial expression databases, i.e., the extended Cohn Kanade (CK + ) [9] and MMI [10].”
Speeding up the Hyperparameter Optimization of Deep Convolutional Neural Networks (2018, background): “The extended Cohn-Kanade (CK+) data set (Lucey et al., 2010) consists of images depicting facial expressions of 210 adults and the task is to classify the displayed emotion.”
A Brief Review of Facial Emotion Recognition Based on Visual Information (2018, methodology): “EmotioNet [18] 23 basic and compound emotions • Euclidean distances between normalized landmarks • Angles between landmarks • Gabor filters centered at of the landmark points Kernel subclass discriminant analysis CE [17] CK+ [10], DISFA [38],”
Geometry-Contrastive GAN for Facial Expression Transfer. (2018, methodology): “CK+ is composed of 327 image sequences from 118 subjects with seven prototypical emotion labels.”