—In this work we propose a dynamic-texture-based approach to the recognition of facial Action Units (AUs, atomic facial gestures) and their temporal models (i.e., sequences of te...
Current two-dimensional image based face recognition systems encounter difficulties with large facial appearance variations due to the pose, illumination and expression changes. ...
Data collection for both training and testing a classifier is a tedious but essential step towards face detection and recognition. All of the statistical methods suffer from this ...
—When automatically analyzing images of human faces, either for recognition in biometry applications or facial expression analysis in human machine interaction, one has to cope w...
Action recognition is a popular and important research topic in computer vision. However, it is challenging when facing viewpoint variance. So far, most researches in action recogn...