Complex human activities occurring in videos can be defined in terms of temporal configurations of primitive actions. Prior work typically hand-picks the primitives, their total...
We present a new representation and recognition method for human activities. An activity is considered to be composed of action threads, each thread being executed by a single act...
This paper presents a new approachto recognizingmultiagent events observed by a static camera. To track objects robustly, knowledgeabout the groundplaneand the events is used. An ...
In this paper, we address the problem of representing human actions using visual cues for the purpose of learning and recognition. Traditional approaches model actions as space-ti...
We propose the use of 3D (2D+time) Shape Context to recognize the spatial and temporal details inherent in human actions. We represent an action in a video sequence by a 3D point ...
Franziska Meier, Irfan A. Essa, Matthias Grundmann