This paper presents an original computational approach to extraction of movie tempo for deriving story sections and events that convey high level semantics of stories portrayed in...
We introduce Gaussian process dynamical models (GPDMs) for nonlinear time series analysis, with applications to learning models of human pose and motion from high-dimensional motio...
Decomposing video frames into coherent two-dimensional motion layers is a powerful method for representing videos. Such a representation provides an intermediate description that e...
We propose novel gaze control algorithms for active perception in mobile autonomous agents with directable, foveated vision sensors. Our agents are realistic artificial animals, o...
— Time-varying graphs are widely used to model communication and sensing in multi-agent systems such as mobile sensor networks and dynamic animal groups. Connectivity is often de...