We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
We investigate the problem of learning document classifiers in a multilingual setting, from collections where labels are only partially available. We address this problem in the ...
Detecting and diagnosing errors in novice behavior is an important student modeling task. In this paper, we describe MEDD, an unsupervised incremental multistrategy system for the ...
Abstract: Democratic societies throughout the world, it appears, are facing a new type of threat dubbed "asymmetric threat." In this new threat environment the world gove...
The rapid growth of the Internet over the last decade has been startling. However, efforts to track its growth have often fallen afoul of bad data -- for instance, how much traffi...