In this paper, we propose a robust model selection criterion for mixtures of subspaces called minimum effective dimension (MED). Previous information-theoretic model selection cri...
This paper describes a novel multi-view matching framework based on a new type of invariant feature. Our features are located at Harris corners in discrete scale-space and oriente...
Matthew Brown, Richard Szeliski, Simon A. J. Winde...
In this paper, a new learning framework?probabilistic boosting-tree (PBT), is proposed for learning two-class and multi-class discriminative models. In the learning stage, the pro...
A probabilistic system for recognition of individual objects is presented. The objects to recognize are composed of constellations of features, and features from a same object shar...
Given a set of images of scenes containing multiple object categories (e.g. grass, roads, buildings) our objective is to discover these objects in each image in an unsupervised man...