NIPS
2000
13 years 5 months ago
2000
We present techniques for rendering and animation of realistic scenes by analyzing and training on short video sequences. This work extends the new paradigm for computer animation...
NIPS
2000
13 years 5 months ago
2000
Source separation, or computational auditory scene analysis, attempts to extract individual acoustic objects from input which contains a mixture of sounds from different sources, ...
NIPS
2000
13 years 5 months ago
2000
An eigenvalue method is developed for analyzing periodic structure in speech. Signals are analyzed by a matrix diagonalization reminiscent of methods for principal component analy...
NIPS
2000
13 years 5 months ago
2000
The problem of reinforcement learning in large factored Markov decision processes is explored. The Q-value of a state-action pair is approximated by the free energy of a product o...
NIPS
2000
13 years 5 months ago
2000
The Bayesian paradigm apparently only sometimes gives rise to Occam's Razor; at other times very large models perform well. We give simple examples of both kinds of behaviour...
NIPS
2000
13 years 5 months ago
2000
We study the problem of combining the outcomes of several different classifiers in a way that provides a coherent inference that satisfies some constraints. In particular, we deve...
NIPS
2000
13 years 5 months ago
2000
A Bayes network based classifier for distinguishing terrestrial rocks from meteorites is implemented onboard the Nomad robot. Equipped with a camera, spectrometer and eddy current...
NIPS
2000
13 years 5 months ago
2000
The human figure exhibits complex and rich dynamic behavior that is both nonlinear and time-varying. Effective models of human dynamics can be learned from motion capture data usi...
NIPS
2000
13 years 5 months ago
2000
We present methods for learning and tracking human motion in video. We estimate a statistical model of typical activities from a large set of 3D periodic human motion data by segm...
NIPS
2000
13 years 5 months ago
2000
In this work, we introduce an Interactive Parts (IP) model as an alternative to Hidden Markov Models (HMMs). We tested both models on a database of on-line cursive script. We show...