The distribution of the apparent 3D shape of human faces across the view-sphere is complex, owing to factors such as variations in identity, facial expression, minor occlusions an...
Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
In this paper, we present an efficient algorithm for 3D object recognition in presence of clutter and occlusions in noisy, sparse and unsegmented range data. The method uses a robu...
In the face recognition process, it is important to deal with a facial image of low-resolution. For low-resolution face recognition, we propose a new method of extending the SVDD,...
In this work we present a novel multi-modal mixed-state dynamic Bayesian network (DBN) for robust meeting event classification. The model uses information from lapel microphones,...