Visual tracking is a challenging problem, as an object may change its appearance due to viewpoint variations, illumination changes, and occlusion. Also, an object may leave the fie...
Most existing appearance models for visual tracking usually construct a pixel-based representation of object appearance so that they are incapable of fully capturing both global an...
This paper presents a Bayesian framework for multi-cue 3D object tracking of deformable objects. The proposed spatio-temporal object representation involves a set of distinct linea...
Abstract. We address the problem of comparing sets of images for object recognition, where the sets may represent arbitrary variations in an object's appearance due to changin...
Principal ComponentAnalysis (PCA) has been successfully applied to construct linear models of shape, graylevel, and motion. In particular, PCA has been widely used to model the var...