We present an automated planning application for generating 3D tasks demonstrations involving a teleoperated robot arm on the International Space Station (ISS). A typical task dem...
— In this work we introduce a novel approach for detecting spatiotemporal object-action relations, leading to both, action recognition and object categorization. Semantic scene g...
Eren Erdal Aksoy, Alexey Abramov, Florentin Wö...
In recent years, several systems have been proposed that learn the rules of a simple card or board game solely from visual demonstration. These systems were constructed for speci...
Conversations provide rich opportunities for interactive, continuous learning. When something goes wrong, a system can ask for clarification, rewording, or otherwise redirect the...
The existing Multi-View Learning (MVL) learns how to process patterns with multiple information sources. In generalization this MVL is proven to have a significant advantage over...