This paper 1 addresses the problem of efficient visual 2D template tracking in image sequences. We adopt a discriminative approach in which the observations at each frame yield di...
Abstract. In order to investigate the deep structure of Gaussian scale space images, one needs to understand the behaviour of critical points under the influence of parameter-drive...
In this paper we propose a novel nonparametric approach
for object recognition and scene parsing using dense
scene alignment. Given an input image, we retrieve its best
matches ...
Edge detection is one of the most studied problems in computer vision, yet it remains a very challenging task. It is difficult since often the decision for an edge cannot be made ...
We present a random field based model for stereo vision with explicit occlusion labeling in a probabilistic framework. The model employs non-parametric cost functions that can be ...