Active Appearance Models (AAMs) typically only use 50-100 mesh vertices because they are usually constructed from a set of training images with the vertices hand-labeled on them. ...
Krishnan Ramnath, Simon Baker, Iain Matthews, Deva...
One of the major challenges in stereo matching is to handle partial occlusions. In this paper, we introduce the Outlier Confidence (OC) which dynamically measures how likely one pi...
This paper discusses how to utilize both magnitude and phase information obtained from the complex directional lter bank (CDFB) for the purpose of texture image retrieval. The rel...
We present methods to obtain computationally efficient proposal distributions for Bayesian reversible jump Markov chain Monte Carlo (RJMCMC) based image segmentation. The slow con...
On-line boosting allows to adapt a trained classifier to changing environmental conditions or to use sequentially available training data. Yet, two important problems in the on-li...
Helmut Grabner, Horst Bischof, Jan Sochman, Jiri M...