This paper shows (i) improvements over state-of-the-art local feature recognition systems, (ii) how to formulate principled models for automatic local feature selection in object c...
Online target tracking requires to solve two problems: data association and online dynamic estimation. Usually, association effectiveness is based on prior information and observa...
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 reformulate the 3D reconstruction of deformable surfaces from monocular video sequences as a labeling problem. We solve simultaneously for the assignment of featu...
We describe (and demonstrate) the execution model of a computing platform where computation is both incremental and data-driven. We call such an approach delta-driven. The platfor...