Digital Manipulatives embed computation in familiar children's toys and provide means for children to design behavior. Some systems use "record and play" as a form ...
Hayes Raffle, Amanda J. Parkes, Hiroshi Ishii, Jos...
Abstract. Multiple-instance learning (MIL) allows for training classifiers from ambiguously labeled data. In computer vision, this learning paradigm has been recently used in many ...
In this paper, we present a novel approach to learning semantic localized patterns with binary projections in a supervised manner. The pursuit of these binary projections is refor...
Abstract. In recent years there has been growing interest in recognition models using local image features for applications ranging from long range motion matching to object class ...
Many perception and multimedia indexing problems involve datasets that are naturally comprised of multiple streams or modalities for which supervised training data is only sparsely...
Ashish Kapoor, Chris Mario Christoudias, Raquel Ur...