A new "herding" algorithm is proposed which directly converts observed moments into a sequence of pseudo-samples. The pseudosamples respect the moment constraints and ma...
When learning a mixture model, we suffer from the local optima and model structure determination problems. In this paper, we present a method for simultaneously solving these prob...
Traditional Markov network structure learning algorithms perform a search for globally useful features. However, these algorithms are often slow and prone to finding local optima d...
This paper presents a novel motion localization approach for recognizing actions and events in real videos. Examples include StandUp and Kiss in Hollywood movies. The challenge ca...
Probabilistic models have been previously shown to be efficient and effective for modeling and recognition of human motion. In particular we focus on methods which represent the h...