We present a novel method for the discovery and detection of visual object categories based on decompositions using topic models. The approach is capable of learning a compact and...
Model-based image interpretation extracts high-level information from images using a priori knowledge about the object of interest. The computational challenge in model fitting is...
Automatic non-rigid registration of 3D time-varying data is fundamental in many vision and graphics applications such as facial expression analysis, synthesis, and recognition. De...
Many computer vision and pattern recognition algorithms are very sensitive to the choice of an appropriate distance metric. Some recent research sought to address a variant of the...
The visualization of color images in gray scale has high practical and theoretical importance. Neither the existing local, gradient based methods, nor the fast global techniques g...