In this work we present a unified view on Markov random fields and recently proposed continuous tight convex relaxations for multi-label assignment in the image plane. These rel...
We describe a novel max-margin parameter learning approach for structured prediction problems under certain non-decomposable performance measures. Structured prediction is a commo...
A popular approach to pixel labeling problems, such as multiclass image segmentation, is to construct a pairwise conditional Markov random field (CRF) over image pixels where the...
A new data structure for efficient similarity search in very large datasets of high-dimensional vectors is introduced. This structure called the inverted multi-index generalizes ...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...