— 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...
Abstract. In numerous content-based video applications, it is important to extract from a video sequence a representation for humans in motion. This task is di cult, because humans...
There are a number of different approaches for automatically selecting video clips from a video database and sequencing them into meaningful presentations for viewers. The video d...
Most existing approaches for learning action models work by extracting suitable low-level features and then training appropriate classifiers. Such approaches require large amount...
Abstract--In this paper we address the problem of unsupervised discovery of action classes in video data. Different from all existing methods thus far proposed for this task, we pr...