no code implementations • 26 May 2021 • Anna Grim, Pedro Felzenszwalb
We present new message passing algorithms for performing inference with graphical models.
no code implementations • 22 Feb 2021 • Jeova F. S. Rocha Neto, Pedro Felzenszwalb, Marilyn Vazquez
Our approach is based on novel algebraic expressions that relate local image statistics to the appearance of spatially coherent regions.
no code implementations • 16 Dec 2020 • Pedro Felzenszwalb, Caroline Klivans, Alice Paul
We also show the vertices are attractive fixed points of iterated linear optimization.
no code implementations • 25 Jun 2015 • Sobhan Naderi Parizi, Kun He, Reza Aghajani, Stan Sclaroff, Pedro Felzenszwalb
Majorization-Minimization (MM) is a powerful iterative procedure for optimizing non-convex functions that works by optimizing a sequence of bounds on the function.
no code implementations • 20 Dec 2014 • Sobhan Naderi Parizi, Andrea Vedaldi, Andrew Zisserman, Pedro Felzenszwalb
First, a collection of informative parts is discovered, using heuristics that promote part distinctiveness and diversity, and then classifiers are trained on the vector of part responses.