Recognition of human gestures is important for analysis and indexing of video. To recognize human gestures on video, generally a large number of training examples for each individu...
We present an approach to tracking human activities in a monocular video. We model the human body by decomposing it into torso and limbs and use simple 3D shapes to approximate th...
Many applications refer to moving objects or phenomena and require spatio-temporal modelling and specific analysis. Unlike conventional data where attributes are simple values (nu...
We propose a technique to make a robot execute free and solitary dance movements on music, in a manner which simulates the dynamic alternations between synchronisation and autonomy...
Jean-Julien Aucouturier, Yuta Ogai, Takashi Ikegam...
In order to populate virtual cities, it is necessary to specify the behaviour of dynamic entities such as pedestrians or car drivers. Since it is not possible to construct in real...