Abstract. Natural scenes consist of a wide variety of stochastic patterns. While many patterns are represented well by statistical models in two dimensional regions as most image s...
This paper proposes an approach to classification of adjacent segments of a time series as being either of classes. We use a hierarchical model that consists of a feature extract...
Partially Observable Markov Decision Processes (POMDPs) have succeeded in planning domains that require balancing actions that increase an agent's knowledge and actions that ...
Deep belief networks are a powerful way to model complex probability distributions. However, it is difficult to learn the structure of a belief network, particularly one with hidd...
Ryan Prescott Adams, Hanna M. Wallach, Zoubin Ghah...
A Bayesian marked point process (MPP) model is developed
to detect and count people in crowded scenes. The
model couples a spatial stochastic process governing number
and placem...