The paper introduces a new framework for feature learning in classification motivated by information theory. We first systematically study the information structure and present a n...
In spite of the popularity of probabilistic mixture models for latent structure discovery from data, mixture models do not have a natural mechanism for handling sparsity, where ea...
We present an unsupervised algorithm for aligning a pair of shapes in the presence of significant articulated motion and missing data, while assuming no knowledge of a template, u...
Modeling human behavior requires vast quantities of accurately labeled training data, but for ubiquitous people-aware applications such data is rarely attainable. Even researchers...
Daniel Peebles, Hong Lu, Nicholas D. Lane, Tanzeem...
We develop a cache-oblivious data structure for storing a set S of N axis-aligned rectangles in the plane, such that all rectangles in S intersecting a query rectangle or point ca...