We propose a new approach for reinforcement learning in problems with continuous actions. Actions are sampled by means of a diffusion tree, which generates samples in the continuou...
Christian Vollmer, Erik Schaffernicht, Horst-Micha...
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...
—A system that could automatically analyze the facial actions in real time has applications in a wide range of different fields. However, developing such a system is always chall...
Recognition of human actions in a video acquired by a moving camera typically requires standard preprocessing steps such as motion compensation, moving object detection and object ...
We investigate a mixed economy of an individual rational expert and several na¨ıve near-sighted agents in the context of security decision making. Agents select between three ca...
Jens Grossklags, Benjamin Johnson, Nicolas Christi...