The product of experts learning procedure [1] can discover a set of stochastic binary features that constitute a non-linear generative model of handwritten images of digits. The q...
—The field of Action Recognition has seen a large increase in activity in recent years. Much of the progress has been through incorporating ideas from single frame object recogn...
Trajectory classification, i.e., model construction for predicting the class labels of moving objects based on their trajectories and other features, has many important, real-worl...
In this paper we present a method for learning a curve model for detection and segmentation by closely integrating a hierarchical curve representation using generative and discrim...
Adrian Barbu, Vassilis Athitsos, Bogdan Georgescu,...
In patch-based object recognition, there are two important issues on the codebook generation: (1) resolution: a coarse codebook lacks sufficient discriminative power, and an over-...