Our objective is to improve the performance of keyword based image search engines by re-ranking their baseline results. To this end, we address three limitations of existing searc...
To build autonomous robots able to live and interact with humans in a real-world dynamic and uncertain environment, the design of architectures permitting robots to develop attachm...
A recent dominating trend in tracking called tracking-by-detection uses on-line classifiers in order to redetect objects over succeeding frames. Although these methods usually deli...
Bernhard Zeisl, Christian Leistner, Amir Saffari, ...
Time varying environments or model selection problems lead to crucial dilemmas in identification and control science. In this paper, we propose a modular prediction scheme consisti...
We target the problem of closed-loop learning of control policies that map visual percepts to continuous actions. Our algorithm, called Reinforcement Learning of Joint Classes (RLJ...