Recently developed video editing techniques have enabled us to create realistic synthesized videos. Therefore, using video data as evidence in places such as courts of law requires...
Deep Belief Networks (DBN's) are generative models that contain many layers of hidden variables. Efficient greedy algorithms for learning and approximate inference have allow...
We introduce a computationally efficient method to estimate the validity of the BP method as a function of graph topology, the connectivity strength, frustration and network size....
Recent research has made significant progress on the problem of bounding log partition functions for exponential family graphical models. Such bounds have associated dual paramete...
The likelihood models used in probabilistic visual tracking applications are often complex non-linear and/or nonGaussian functions, leading to analytically intractable inference. ...