We present a method to learn and recognize object class models from unlabeled and unsegmented cluttered scenes in a scale invariant manner. Objects are modeled as flexible constel...
The goal of this work is to take an image such as the one in Figure 1(a), detect a human figure, and localize his joints and limbs (b) along with their associated pixel masks (c)....
Greg Mori, Xiaofeng Ren, Alexei A. Efros, Jitendra...
* We present a method for representing and recognizing visual events using attribute grammars. In contrast to conventional grammars, attribute grammars are capable of describing fe...
Linear Discriminant Analysis(LDA) is widely-used in face recognition systems. However, with the traditional formulation, the available information in the training samples is not su...
This paper introduces a supervised discriminant Hausdorff distance that fits into the framework for automatic face analysis and recognition proposed in [1]. Our proposal relies so...