We describe a learning based method for recovering 3D human body pose from single images and monocular image sequences. Our approach requires neither an explicit body model nor pri...
Semantic concept detectors are often individually and independently developed. Using peripherally related concepts for leveraging the power of joint detection, which is referred t...
We describe techniques for combining two types of knowledge systems: expert and machine learning. Both the expert system and the learning system represent information by logical d...
For the manual semantic markup of documents to become widespread, users must be able to express annotations that conform to ontologies (or schemas) that have shared meaning. Howev...
Recognition of player actions in broadcast sports video is a challenging task due to low resolution of the players in video frames. In this paper, we present a novel method to rec...