Visualization is often invaluable to understand the behavior of optimization algorithms, identify their bottlenecks or pathological behaviors, and suggest remedial techniques. Yet ...
We introduce a new type of graphical model called a `cumulative distribution network' (CDN), which expresses a joint cumulative distribution as a product of local functions. ...
Objects can exhibit different dynamics at different scales, and this is often exploited by visual tracking algorithms. A local dynamic model is typically used to extract image fea...
Leonid Taycher, John W. Fisher III, Trevor Darrell
We introduce a generative model of dense flow fields within a layered representation of 3-dimensional scenes. Using probabilistic inference and learning techniques (namely, varia...
We present an automatic method to recover high-resolution texture over an object by mapping detailed photographs onto its surface. Such high-resolution detail often reveals inaccu...
Ran Gal, Yonatan Wexler, Eyal Ofek, Hugues Hoppe, ...