—This paper is concerned with the representation and recognition of the observed dynamics (i.e., excluding purely spatial appearance cues) of spacetime texture based on a spatiot...
We propose a solution to the problem of object recognition given a continuous video sequence containing multiple views of an object. Initially, object models are acquired from ima...
Abstract. This paper proposes a solution for the automatic detection and tracking of human motion in image sequences. Due to the complexity of the human body and its motion, automa...
Multi-agent simulations aim at representing the dynamics of complex systems as resulting from multiple interactions between autonomous entities including their own perception of lo...
In soccer videos, most significant actions are usually followed by close–up shots of players that take part in the action itself. Automatically annotating the identity of the p...