This paper studies a novel paradigm for learning formal languages from positive and negative examples which consists of mapping strings to an appropriate highdimensional feature s...
We present a novel method for incorporating prior knowledge about invariances in object recognition for discriminant analysis. In contrast to conventional isotropic regularization...
In this paper, we are interested in the analysis of regularized online algorithms associated with reproducing kernel Hilbert spaces. General conditions on the loss function and st...
We propose a method for removing non-uniform motion blur from multiple blurry images. Traditional methods focus on estimating a single motion blur kernel for the entire image. In ...
Abstract. We present a method for learning feature descriptors using multiple images, motivated by the problems of mobile robot navigation and localization. The technique uses the ...
Jason Meltzer, Ming-Hsuan Yang, Rakesh Gupta, Stef...