We present a theory for constructing linear subspace approximations to face-recognition algorithms and empirically demonstrate that a surprisingly diverse set of face-recognition a...
In this work, we propose a new robust and edge-preserving superresolution algorithm to simultaneously estimate all frames of a sequence. The new algorithm is based on the regulari...
Relation models have treated multi-holed regions relations either the same as hole-free regions relations, loosing this way the peculiarities of the holed topology, or with methods...
Abstract. We propose a new scheme for novelty detection in image sequences capable of handling non-stationary background scenarious, such as waving trees, rain and snow. Novelty de...
Fredrik Kahl, Richard I. Hartley, Volker Hilsenste...
Abstract. We address the problem of learning good features for understanding video data. We introduce a model that learns latent representations of image sequences from pairs of su...