This paper presents an interactive image segmentation framework which is ultra-fast and accurate. Our framework, termed "CO3", consists of three components: COupled repr...
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...
In this paper, we study face hallucination, or synthesizing a high-resolution face image from an input low-resolution image, with the help of a large collection of other high-reso...
One of the major strengths of probabilistic topic modeling is the ability to reveal hidden relations via the analysis of co-occurrence patterns on dyadic observations, such as docu...
While basic principles of microtubule organization are well understood, much remains to be learned about the extent and significance of variation in that organization among cell t...