—This paper presents a procedure for automatic extraction and segmentation of a class-specific object (or region) by learning class-specific boundaries. We describe and evaluat...
Off-line trained class-specific object detectors are designed to detect any instance of the class in a given image or video sequence. In the context of object tracking, however, o...
We describe efficient techniques for construction of large term co-occurrence graphs, and investigate an application to the discovery of numerous fine-grained (specific) topics. A...
We study graph estimation and density estimation in high dimensions, using a family of density estimators based on forest structured undirected graphical models. For density estim...
Anupam Gupta, John D. Lafferty, Han Liu, Larry A. ...
We consider the problem of finding the best arm in a stochastic multi-armed bandit game. The regret of a forecaster is here defined by the gap between the mean reward of the optim...