The problems of dense stereo reconstruction and object class segmentation can both be formulated as Conditional Random Field based labelling problems, in which every pixel in the ...
Lubor Ladicky, Paul Sturgess, Christopher Russell,...
Recent progress in per-pixel object class labeling of natural images can be attributed to the use of multiple types of image features and sound statistical learning approaches. Wit...
In this paper, we present an overview of generalized expectation criteria (GE), a simple, robust, scalable method for semi-supervised training using weakly-labeled data. GE fits m...
The Conditional Random Fields (CRF) model, using
patch-based classification bound with context information,
has recently been widely adopted for image segmentation/
labeling. In...
We propose a new technique for fusing multiple cues to robustly segment an object from its background in video sequences that suffer from abrupt changes of both illumination and p...
Francesc Moreno-Noguer, Alberto Sanfeliu, Dimitris...