Cascades of classifiers constitute an important architecture for fast object detection. While boosting of simple (weak) classifiers provides an established framework, the design of...
Several NLP tasks are characterized by asymmetric data where one class label NONE, signifying the absence of any structure (named entity, coreference, relation, etc.) dominates al...
We investigate how to effectively incorporate spatial structure information into histogram features for boosting visual classification performance motivated by recently proposed M...
Multi-label learning arises in many real-world tasks where an object is naturally associated with multiple concepts. It is well-accepted that, in order to achieve a good performan...
The rise of multi-core processors has shifted performance efforts towards parallel programs. However, single-threaded code, whether from legacy programs or ones difficult to para...