We develope a technique to perform e cient and accurate matching to detect the occurences of a template in a scene. The template may describe an object or a textured surface. Repr...
In this paper, we introduce a generic framework for semi-supervised kernel learning. Given pairwise (dis-)similarity constraints, we learn a kernel matrix over the data that respe...
In this paper we present a statistical learning scheme for image classification based on a mixture of old fashioned ideas and state of the art learning tools. We represent input i...
We propose two Euclidean minimum spanning tree based clustering algorithms — one a k-constrained, and the other an unconstrained algorithm. Our k-constrained clustering algorith...
We propose the use of attentional cascades based on the DCT and motion information contained in an MPEG coded stream. An attentional cascade is a sequence of very efficient class...