We present a method to learn object class models from unlabeled and unsegmented cluttered scenes for the purpose of visual object recognition. We focus on a particular type of mode...
In this paper, we present a perceptual distortion measure that predicts image integrity far better than mean-squared error. This perceptual distortion measure is based on a model ...
The problem of finding clusters in data is challenging when clusters are of widely differing sizes, densities and shapes, and when the data contains large amounts of noise and out...
The increasing power of techniques to model complex geometry and extract meaning from 3D information create complex data that must be described, stored, and displayed to be useful...
Abstract. We describe an efficient approach to construct shape models composed of contour parts with partially-supervised learning. The proposed approach can easily transfer parts ...