The goal of this paper is to find sparse and representative spatial priors that can be applied to part-based object localization. Assuming a GMRF prior over part configurations, w...
We propose to solve the combinatorial problem of finding the highest scoring Bayesian network structure from data. This structure learning problem can be viewed as an inference pr...
Tommi Jaakkola, David Sontag, Amir Globerson, Mari...
Markov logic networks (MLNs) combine logic and probability by attaching weights to first-order clauses, and viewing these as templates for features of Markov networks. Learning ML...
The visual world demonstrates organized spatial patterns,
among objects or regions in a scene, object-parts
in an object, and low-level features in object-parts. These
classes o...
Devi Parikh (Carnegie Mellon University), C. Lawre...
Powerful statistical models that can be learned efficiently from large amounts of data are currently revolutionizing computer vision. These models possess a rich internal structur...