When trying to apply recently developed approaches for updating Description Logic ABoxes in the context of an action programming language, one encounters two problems. First, upda...
Conrad Drescher, Hongkai Liu, Franz Baader, Steffe...
—In this paper we evaluate the use of Restricted Bolzmann Machines (RBM) in the context of learning and recognizing human actions. The features used as basis are binary silhouett...
Manuel Jesus Marin-Jimenez, Nicolas Perez De La Bl...
Software architecture practice is highly complex. Software architects interact with business as well as technical aspects of systems, often embedded in large and changing organiza...
— 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...
Contextual bandit learning is a reinforcement learning problem where the learner repeatedly receives a set of features (context), takes an action and receives a reward based on th...