We propose a novel way to induce a random field from an energy function on discrete labels. It amounts to locally injecting noise to the energy potentials, followed by finding t...
In this paper, we present a set of texture features that are locally invariant to similarity or affinity. The proposed indexing scheme relies on the topographic map, a shape-based...
Using local features with nearest neighbor search and direct voting obtains excellent results for various image classification tasks. In this work we decompose the method into its...
Daniel Keysers, Hermann Ney, Roberto Paredes, Tobi...
Abstract. In this note we study the local behavior of singularities occurring in scale space under Gaussian blurring. Based on ideas from singularity theory for vector fields this...
This paper addresses the problem of simultaneous localization and mapping (SLAM) using vision-based sensing. We present and analyse an implementation of a RaoBlackwellised particl...
Robert Sim, Pantelis Elinas, Matt Griffin, Alex Sh...