Much computer-based learning is largely passive, based primarily on task-based, exercise-driven interactions. We argue that computers have greater potential for promoting more act...
This paper addresses detection of imperfections in repetitive regular structures (textures). Humans can easily find such defects without prior knowledge of the `good' pattern...
Automatic image tagging is important yet challenging due to the semantic gap and the lack of learning examples to model a tag’s visual diversity. Meanwhile, social user tagging ...
We present a new generalization bound where the use of unlabeled examples results in a better ratio between training-set size and the resulting classifier’s quality and thus red...
This paper addresses new questions around media performance as a result of the rise of centralized content portals such as iTunes or MySpace. We first describe the rise of central...