In this paper, two novel real-time methods are proposed for facial expression recognition in image sequences. The user manually places some of the Candide grid's points to th...
We present a novel concept, vector restoration, for motion compensated predictive coding of video. Conventional predictive coders generate predictions of the input signal and enco...
J. S. McVeigh, S.-W. Wu, Mel W. Siegel, Angel G. J...
An appearance-based approach to track an object that may undergo appearance change is proposed. Unlike recent methods that store a detailed representation of object's appeara...
We propose a simple framework that utilizes online appearance models for 3D face and facial feature tracking with a deformable model. Adapting the geometrical parameters for each ...
A novel illumination invariant unsupervised multispectral texture segmentation method with unknown number of classes is presented. Multispectral texture mosaics are locally repres...