One approach to modeling structured discrete data is to describe the probability of states via an energy function and Gibbs distribution. A recurring difficulty in these models is...
Daniel Tarlow, Ryan Prescott Adams, Richard S. Zem...
We present a dynamic tree modeling and representation technique that allows complex tree models to interact with their environment. Our method uses changes in the light distributi...
We present a novel dataset and novel algorithms for the problem of detecting activities of daily living (ADL) in firstperson camera views. We have collected a dataset of 1 millio...
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...
We argue that multilingual parallel data provides a valuable source of indirect supervision for induction of shallow semantic representations. Specifically, we consider unsupervi...