The Extended Cohn-Kanade Dataset (CK+): A complete dataset for action unit and emotion-specified expression
Citations
1,151 citations
Cites methods from "The Extended Cohn-Kanade Dataset (C..."
...In order to reduce the feature dimensionality we use a PCA model trained on a number of facial expression datasets: CK+ [38], DISFA [41], AVEC 2011 [52], FERA 2011 [60], and FERA 2015 [59]....
[...]
984 citations
937 citations
Cites background or methods from "The Extended Cohn-Kanade Dataset (C..."
...Early databases of facial expressions such as JAFFE [7], CohnKanade [8], [9], MMI [10], andMultiPie [11] were captured in a lab-controlled environment where the subjects portrayed different facial expressions....
[...]
...The proposed AU detection approach was trained on CK+ [9], DISFA [14], and CFEE [34] databases, and the accuracy of the automated annotated AUs was reported about 80% on the manually annotated set....
[...]
...CK+ [9] - Frontal and 30 degree images - 123 - Controlled - Posed - 30 AUs - 7 emotion categories...
[...]
...detection approach was trained on CK+ [9], DISFA [14], and CFEE [34] databases, and the accuracy of the automated annotated AUs was reported about 80 percent on the manually annotated set....
[...]
...Researchers have created databases of human actors/subjects portraying basic emotions [7], [8], [9], [10], [11]....
[...]
816 citations
Cites methods from "The Extended Cohn-Kanade Dataset (C..."
...In [49] multiple features are fused via a Multiple Ker- nel Learning algorithm and the cross-database experiment is trained on CK+, evaluated on MMI and vice versa....
[...]
...We evaluate the proposed method on well-known publicly available facial expression databases: CMU MultiPIE [15], MMI [36], Denver Intensity of Spontaneous Facial Actions (DISFA) [29], extended CK+ [27], GEMEPFERA database [5], SFEW [10], and FER2013 [1]....
[...]
...Results in [24] show that the features generated by this “AU-Aware” network are competitive with or superior to handcrafted features such as LBP, SIFT, HoG, and Gabor on the CK+, MMI and databases using a similar SVM....
[...]
...MultiPIE, MMI, CK+, DISFA, FERA, SFEW, and FER2013) and obtain results which are significantly better than, or comparable to, traditional convolutional neural networks or other state-ofthe-art methods in both accuracy and learning time....
[...]
...The reported result in Table 5 is the best result using different SVM kernels trained on the CK+ database and evaluated the model on the MMI database....
[...]
772 citations
References
40,826 citations
"The Extended Cohn-Kanade Dataset (C..." refers methods in this paper
...However, these scores have no real meaning when comparing them from different SVMs....
[...]
...SVMs attempt to find the hyperplane that maximizes the margin between positive and negative observations for a specified class....
[...]
...We then use support vector machines (SVMs) to classify the facial expressions and emotions....
[...]
...LIBSVM was used for the training and testing of SVMs [6]....
[...]
...However, when output from both the SPTS and CAPP SVMs are combined (through summing the output probabilities) it can be seen that the detection of this emotion jumps from just over 20% to over 80% as can be seen in Table 7....
[...]
16,435 citations
9,528 citations
"The Extended Cohn-Kanade Dataset (C..." refers methods in this paper
...Inter-observer agreement was quantified with coefficient kappa, which is the proportion of agreement above what would be expected to occur by chance [10]....
[...]
7,069 citations
"The Extended Cohn-Kanade Dataset (C..." refers methods in this paper
...A linear kernel was used in our experiments due to its ability to generalize well to unseen data in many pattern recognition tasks [13]....
[...]
6,200 citations