Machine learning (ML) is widely used to derive useful information from large-scale data
(such as user activities, pictures, and videos) generated at increasingly rapid rates, all over …

While high-level data parallel frameworks, like MapReduce, simplify the design and
implementation of large-scale data processing systems, they do not naturally or efficiently …

A general framework for constructing and using probabilistic models of complex systems that
would enable a computer to use available information for making decisions. Most tasks …

The formalism of probabilistic graphical models provides a unifying framework for capturing
complex dependencies among random variables, and building large-scale multivariate …

Designing and implementing efficient, provably correct parallel machine learning (ML)
algorithms is challenging. Existing high-level parallel abstractions like MapReduce are …

Many tasks involve predicting a large number of variables that depend on each other as well
as on other observed variables. Structured prediction methods are essentially a combination …

Powerful statistical models that can be learned efficiently from large amounts of data are
currently revolutionizing computer vision. These models possess a rich internal structure …

In this paper, we formulate a stereo matching algorithm with careful handling of disparity,
discontinuity and occlusion. The algorithm works with a global matching stereo model based …

In this paper we present a new approach for establishing correspondences between sparse
image features related by an unknown non-rigid mapping and corrupted by clutter and …

In sequence modeling, we often wish to represent complex interaction between labels, such
as when performing multiple, cascaded labeling tasks on the same sequence, or when long …