Up-propagation is an algorithm for inverting and learning neural network generative models. Sensory input is processed by inverting a model that generates patterns from hidden var...
We present PhysicsBook, a prototype system that enables users to solve physics problems using a sketch-based interface and then animates any diagram used in solving the problem to...
Local experts have been used to great effect for fitting deformable
models to images. Typically, the best location in
an image for the deformable model’s landmarks are found
t...
In many applications of graphical models arising in computer vision, the hidden variables of interest are most naturally specified by continuous, non-Gaussian distributions. There...
Erik B. Sudderth, Alexander T. Ihler, William T. F...
Two major limitations of real-time visual SLAM algorithms are the restricted range of views over which they can operate and their lack of robustness when faced with erratic camera...
Denis Chekhlov, Mark Pupilli, Walterio W. Mayol-Cu...