In this paper, we aim to reconstruct free-form 3D models from only one or few silhouettes by learning the prior knowledge of a specific class of objects. Instead of heuristically...
We present an approach for dictionary learning of action attributes via information maximization. We unify the class distribution and appearance information into an objective func...
This paper presents a general, trainable system for object detection in unconstrained, cluttered scenes. The system derives much of its power from a representation that describes a...
Object recognition is challenging due to high intra-class
variability caused, e.g., by articulation, viewpoint changes,
and partial occlusion. Successful methods need to strike a...
Pseudo-likelihood and contrastive divergence are two well-known examples of contrastive methods. These algorithms trade off the probability of the correct label with the probabili...