This paper investigates several issues in the problem of detecting handwritten markings, or annotations, on printed documents. One issue is to define the appropriate units over wh...
In this paper we present a method of parameter optimization, relative trust-region learning, where the trust-region method and the relative optimization [21] are jointly exploited...
A scheme, named tower of knowledge (ToK), is proposed for interpreting 3D scenes. The ToK encapsulates causal dependencies between object appearance and functionality. We demonstr...
We present an algorithm for active learning (adaptive selection of training data) within the context of semi-supervised multi-task classifier design. The semi-supervised multi-ta...
We introduce an exemplar model that can learn and generate a region of interest around class instances in a training set, given only a set of images containing the visual class. T...