For purpose of object recognition, we learn one discriminative classifier based on one prototype, using shape context distances as the feature vector. From multiple prototypes, th...
— We present a method for learning activity-based ground models based on a multiple particle filter approach to motion tracking in video acquired from a moving aerial platform. ...
Andrew Lookingbill, David Lieb, David Stavens, Seb...
Abstract. An artificial system that achieves human-level performance on opendomain tasks must have a huge amount of knowledge about the world. We argue that the most feasible way t...
This paper introduces YAYA1, a Description Logic system focused towards learning complex interrelations among objects. YAYA Concept Language (YCL) is quite restricted; although it...
We consider the minimization of a smooth loss with trace-norm regularization, which is a natural objective in multi-class and multitask learning. Even though the problem is convex...