We propose semantic texton forests, efficient and powerful new low-level features. These are ensembles of decision trees that act directly on image pixels, and therefore do not ne...
—When performing predictive data mining, the use of ensembles is known to increase prediction accuracy, compared to single models. To obtain this higher accuracy, ensembles shoul...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...
In this article, we propose a special type of decision tree, called a decision cascade, for binarizing document images. Such images are produced by cameras, resulting in varying de...
The co-occurrence pattern, a combination of binary or local features, is more discriminative than individual features and has shown its advantages in object, scene, and action rec...