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 ...
The power of the unaided, individual mind is highly overrated: The Renaissance scholar no longer exists. Although creative individuals are often thought of as working in isolation...
We present a random field based model for stereo vision with explicit occlusion labeling in a probabilistic framework. The model employs non-parametric cost functions that can be ...
Partial transition systems support abstract model checking of complex temporal propercombining both over- and under-approximatingabstractions into a single model. Over the years, ...
Pointwise consistent, feasible procedures for estimating contemporaneous linear causal structure from time series data have been developed using multiple conditional independence ...