Abstract. We propose a novel model-based approach to activity recognition using high-level primitives that are derived from a human body model estimated from sensor data. Using sho...
In addition to its technical merits as a challenging non-rigid motion and structural integrity analysis problem, quantitative estimation of cardiac regional functions and material...
Bayesian learning in undirected graphical models--computing posterior distributions over parameters and predictive quantities-is exceptionally difficult. We conjecture that for ge...
Visual tracking, in essence, deals with non-stationary data streams that change over time. While most existing algorithms are able to track objects well in controlled environments,...
Abstract. Accurately evaluating statistical independence among random variables is a key component of Independent Component Analysis (ICA). In this paper, we employ a squared-loss ...