Abstract | ||
---|---|---|
In this paper, we propose a method for video-based human emotion recognition. For each video clip, all frames are represented as an image set, which can be modeled as a linear subspace to be embedded in Grassmannian manifold. After feature extraction, Class-specific One-to-Rest Partial Least Squares (PLS) is learned on video and audio data respectively to distinguish each class from the other confusing ones. Finally, an optimal fusion of classifiers learned from both modalities (video and audio) is conducted at decision level. Our method is evaluated on the Emotion Recognition In The Wild Challenge (EmotiW 2013). The experimental results on both validation set and blind test set are presented for comparison. The final accuracy achieved on test set outperforms the baseline by 26%. |
Year | DOI | Venue |
---|---|---|
2013 | 10.1145/2522848.2531738 | ICMI |
Keywords | Field | DocType |
audio data,image set,emotion recognition,blind test set,validation set,video clip,squares regression,test set,grassmannian manifold,class-specific one-to-rest partial,wild challenge,partial least squares regression | Pattern recognition,Decision level,Computer science,Emotion recognition,Partial least squares regression,Feature extraction,Speech recognition,Linear subspace,Grassmannian,Artificial intelligence,Manifold,Test set | Conference |
Citations | PageRank | References |
30 | 1.42 | 18 |
Authors | ||
5 |
Name | Order | Citations | PageRank |
---|---|---|---|
Mengyi Liu | 1 | 291 | 13.21 |
Ruiping Wang | 2 | 894 | 41.60 |
Zhiwu Huang | 3 | 252 | 15.26 |
Shiguang Shan | 4 | 6322 | 283.75 |
Xilin Chen | 5 | 6291 | 306.27 |