We explore an approach to 3D people tracking with learned motion models and deterministic optimization. The tracking problem is formulated as the minimization of a differentiable ...
We describe a system that successfully transfers value function knowledge across multiple subdomains of realtime strategy games in the context of multiagent reinforcement learning....
Knowledge representations using semantic web technologies often provide information which translates to explicit term and predicate taxonomies in relational learning. We show how t...
Using discrete Hidden-Markov-Models (HMMs) for recognition requires the quantization of the continuous feature vectors. In handwritten whiteboard note recognition it turns out tha...
The flow logic approach to static analysis amounts to specifying the admissibility of solutions to analysis problems; when specified using formulae in stratified alternation-fr...