We address the problem of learning view-invariant 3D models of human motion from motion capture data, in order to recognize human actions from a monocular video sequence with arbi...
In this paper, we introduce an alternative approach to reasoning about action. The approach provides a solution to the frame and the ramification problem in a uniform manner. The ...
We present a logic for reasoning both about the ability of agents to cooperate to execute complex actions, and how this relates to their ability to reach certain states of affairs...
Luigi Sauro, Jelle Gerbrandy, Wiebe van der Hoek, ...
Retrieving human actions from video databases is a paramount but challenging task in computer vision. In this work, we develop such a framework for robustly recognizing human acti...
— 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...