We propose a hybrid body representation that represents each typical pose by both template-like view information and part-based structural information. Specifically, each body par...
Finite mixtures of tree-structured distributions have been shown to be efficient and effective in modeling multivariate distributions. Using Dirichlet processes, we extend this ap...
We present an adaptation technique for statistical machine translation, which applies the well-known Bayesian learning paradigm for adapting the model parameters. Since state-of-t...
Many visual search and matching systems represent images using sparse sets of "visual words": descriptors that have been quantized by assignment to the best-matching symb...
We describe a machine learning approach for predicting sponsored search ad relevance. Our baseline model incorporates basic features of text overlap and we then extend the model t...
Dustin Hillard, Stefan Schroedl, Eren Manavoglu, H...