We propose a novel a framework for deriving approximations for intractable probabilistic models. This framework is based on a free energy (negative log marginal likelihood) and ca...
This paper describes two algorithms for the real-time segmentation of foreground from background layers in stereo video sequences. Automatic separation of layers from colour/contr...
Vladimir Kolmogorov, Antonio Criminisi, Andrew Bla...
Abstract. Statistical analysis of spatially uniform signal contexts allows Discrete Universal Denoiser (DUDE) to effectively correct signal errors caused by a discrete symmetric me...
Object detection is challenging partly due to the limited discriminative power of local feature descriptors. We amend this limitation by incorporating spatial constraints among ne...
Abstract--This paper presents a novel and domainindependent approach for graph-based structure learning. The approach is based on solving the Maximum Common SubgraphIsomorphism pro...