no code implementations • CVPR 2014 • Thomas Berg, Jiongxin Liu, Seung Woo Lee, Michelle L. Alexander, David W. Jacobs, Peter N. Belhumeur
We show how these priors can be used to significantly improve performance.
no code implementations • CVPR 2013 • Thomas Berg, Peter N. Belhumeur
From a set of images in a particular domain, labeled with part locations and class, we present a method to automatically learn a large and diverse set of highly discriminative intermediate features that we call Part-based One-vs-One Features (POOFs).