While process variations are becoming more significant with each new IC technology generation, they are often modeled via linear regression models so that the resulting performanc...
Xin Li, Jiayong Le, Padmini Gopalakrishnan, Lawren...
The performance of a typical speaker verification system degrades significantly in reverberant environments. This degradation is partly due to the conventional feature extractio...
Sriram Ganapathy, Jason W. Pelecanos, Mohamed Kama...
Bayesian networks are directed acyclic graphs that represent dependencies between variables in a probabilistic model. Many time series models, including the hidden Markov models (H...
We present a dynamic inference algorithm in a globally parameterized nonlinear manifold and demonstrate it on the problem of visual tracking. An appearance manifold is usually non...
We investigate dynamical models of human motion that can
support both synthesis and analysis tasks. Unlike coarser
discriminative models that work well when action classes are ...