In this paper we develop a system for human behaviour recognition in video sequences. Human behaviour is modelled as a stochastic sequence of actions. Actions are described by a f...
While a tracking system is unaware of the identity of any object it tracks, the identity remains the same for the entire tracking sequence. Our system leverages this information b...
It is well-known that Sturmian sequences are the non ultimately periodic sequences that are balanced over a 2-letter alphabet. They are also characterized by their complexity: the...
Convergent scheduling is a general framework for instruction scheduling and cluster assignment for parallel, clustered architectures. A convergent scheduler is composed of many ind...
Walter Lee, Diego Puppin, Shane Swenson, Saman P. ...
We examine a general Bayesian framework for constructing on-line prediction algorithms in the experts setting. These algorithms predict the bits of an unknown Boolean sequence usin...