This paper proposes a new concept in hierarchical representations that exploits features of different granularity and specificity coming from all layers of the hierarchy. The conc...
We consider the problem of learning to rank relevant and novel documents so as to directly maximize a performance metric called Expected Global Utility (EGU), which has several de...
Hough transform based object detectors learn a mapping from the image domain to a Hough voting space. Within this space, object hypotheses are formed by local maxima. The votes con...
We investigate a new, convex relaxation of an expectation-maximization (EM) variant that approximates a standard objective while eliminating local minima. First, a cautionary resu...
Most modern computer vision systems for high-level
tasks, such as image classification, object recognition and
segmentation, are based on learning algorithms that are
able to se...