Current feature-based object recognition methods use information derived from local image patches. For robustness, features are engineered for invariance to various transformation...
Abstract The cerebral cortex utilizes spatiotemporal continuity in the world to help build invariant representations. In vision, these might be representations of objects. The temp...
Simon M. Stringer, G. Perry, Edmund T. Rolls, J. H...
Novel similarity measures for object recognition and image matching are proposed, which are inherently robust against occlusion, clutter, and nonlinear illumination changes. They c...
We present a novel method for incorporating prior knowledge about invariances in object recognition for discriminant analysis. In contrast to conventional isotropic regularization...
This paper proposes a method to obtain frontoparallel (side-view) body part trajectories for a walk observed from an arbitrary view. The method is based on homography transformati...