“Energy” models for continuous domains can be applied to many problems, but often suffer from high computational expense in training, due to the need to repeatedly minimize t...
We present SpeedBoost, a natural extension of functional gradient descent, for learning anytime predictors, which automatically trade computation time for predictive accuracy by s...
— Most recent approaches to monocular non-rigid 3D shape recovery rely on exploiting point correspondences and work best when the whole surface is well-textured. The alternative ...
Image denoising can be described as the problem of mapping from a noisy image to a noise-free image. The best currently available denoising methods approximate this mapping with c...
Harold Christopher Burger, Christian J. Schuler, S...
We present a unified occlusion model for object instance detection under arbitrary viewpoint. Whereas previous approaches primarily modeled local coherency of occlusions or attem...