In this paper, we investigate the hypothesis that plan recognition can significantly improve the performance of a casebased reinforcement learner in an adversarial action selectio...
Abstract. We present a novel approach to detect and classify rare behaviours which are visually subtle and occur sparsely in the presence of overwhelming typical behaviours. We tre...
Jian Li, Timothy M. Hospedales, Shaogang Gong, Tao...
Unsupervised discovery of latent representations, in addition to being useful for density modeling, visualisation and exploratory data analysis, is also increasingly important for...
Jasper Snoek, Ryan Prescott Adams, Hugo Larochelle
In this paper, a new Mixture model of Dynamic pedestrian-Agents (MDA) is proposed to learn the collective behavior patterns of pedestrians in crowded scenes. Collective behaviors ...
A central problem in the analysis of motion capture (Mo-
Cap) data is how to decompose motion sequences into primitives.
Ideally, a description in terms of primitives should
fac...