We consider online learning where the target concept can change over time. Previous work on expert prediction algorithms has bounded the worst-case performance on any subsequence ...
In the task of adaptive information filtering, a system receives a stream of documents but delivers only those that match a person's information need. As the system filters i...
Multi-view algorithms reduce the amount of required training data by partitioning the domain features into separate subsets or views that are sufficient to learn the target concep...
We present a novel approach, clustering on local image profiles, for statistically characterizing image intensity in object boundary regions. In deformable model segmentation, a d...
Joshua Stough, Stephen M. Pizer, Edward L. Chaney,...
We examine tagging behavior on Flickr, a public photosharing website. We build on previous qualitative research that exposed a taxonomy of tagging motivations, as well as on socia...