We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate...
—We address the problem of comparing sets of images for object recognition, where the sets may represent variations in an object’s appearance due to changing camera pose and li...
Regularities in the world are human defined. Patterns in the observed phenomena are there because we define and recognize them as such. Automatic pattern recognition tries to bridg...
Many approaches to object recognition are founded on probability theory, and can be broadly characterized as either generative or discriminative according to whether or not the dis...
Modeling and recognition of 3D objects by surface is an important problem in machine vision. Given a large number of range data points of an object surface, we present a relaxatio...
Chang Y. Choo, Nasser M. Nasrabadi, William I. Kwa...