Deep Belief Networks (DBNs) are hierarchical generative models which have been used successfully to model high dimensional visual data. However, they are not robust to common vari...
This paper proposes a novel framework for robust click-point linking: efficient localized registration that allows users to interactively prescribe where the accuracy has to be hig...
There has been considerable interest in random projections, an approximate algorithm for estimating distances between pairs of points in a high-dimensional vector space. Let A Rn...
This paper proposes a new class-based method to estimate the strength of association in word co-occurrence for the purpose of structural disambiguation. To deal with sparseness of...
This paper presents a method for alignment of images acquired by sensors of di erent modalities (e.g., EO and IR). The paper has two main contributions: (i) It identi es an approp...