This work describes an approach for the interpretation and explanation of human behavior in image sequences, within the context of a Cognitive Vision System. The information source...
This paper presents a semi-supervised training method for linear-chain conditional random fields that makes use of labeled features rather than labeled instances. This is accompli...
Recent work on organisational knowledge suggests that, in addition to cultivating the 'knowledge spiral', organisations need to focus on facilitating forms of 'know...
Successful image reconstruction requires the recognition of a scene and the generation of a clean image of that scene. We propose to use recurrent neural networks for both analysi...
Log-concavity is an important property in the context of optimization, Laplace approximation, and sampling; Bayesian methods based on Gaussian process priors have become quite pop...