IJCV
2000
13 years 11 months ago
2000
We propose a Bayesian framework for representing and recognizing local image motion in terms of two basic models: translational motion and motion boundaries. Motion boundaries are ...
NIPS
2000
14 years 26 days ago
2000
We describe a neurally-inspired, unsupervised learning algorithm that builds a non-linear generative model for pairs of face images from the same individual. Individuals are then ...
NIPS
2000
14 years 26 days ago
2000
The product of experts learning procedure [1] can discover a set of stochastic binary features that constitute a non-linear generative model of handwritten images of digits. The q...
ICCV
1999
IEEE
15 years 1 months ago
1999
IEEE
We propose a Bayesian framework for representing and recognizing local image motion in terms of two primitive models: translation and motion discontinuity. Motion discontinuities ...