Abstract. In this paper we present a new approach for establishing correspondences between sparse image features related by an unknown non-rigid mapping and corrupted by clutter an...
Lorenzo Torresani, Vladimir Kolmogorov, Carsten Ro...
Classification in imbalanced domains is a recent challenge in machine learning. We refer to imbalanced classification when data presents many examples from one class and few from ...
— In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene g...
Eren Erdal Aksoy, Alexey Abramov, Florentin Wö...
We present a unified framework for reasoning about worst-case regret bounds for learning algorithms. This framework is based on the theory of duality of convex functions. It brin...
3dm is a three dimensional (3D) surface modeling program that draws techniques of model manipulation from both CAD and drawing programs and applies them to modeling in an intuitiv...
Jeff Butterworth, Andrew Davidson, Stephen Hench, ...