Abstract—Whole-book recognition is a document image analysis strategy that operates on the complete set of a book’s page images using automatic adaptation to improve accuracy. ...
Abstract. Learned, activity-specific motion models are useful for human pose and motion estimation. Nevertheless, while the use of activityspecific models simplifies monocular t...
Abstract. This paper studies the properties and performance of models for estimating local probability distributions which are used as components of larger probabilistic systems ...
Kristina Toutanova, Mark Mitchell, Christopher D. ...
Typical domains used in machine learning analyses only partially cover the complexity space, remaining a large proportion of problem difficulties that are not tested. Since the ac...
This paper analyzes the behavior of the XCS classifier system on imbalanced datasets. We show that XCS with standard parameter settings is quite robust to considerable class imbal...