Abstract— This paper describes a novel algorithm for autonomous and incremental learning of motion pattern primitives by observation of human motion. Human motion patterns are ed...
We present a novel stereo vision modeling framework that generates approximate, yet physically-plausible representations of objects rather than creating accurate models that are c...
Krishnanand N. Kaipa, Josh C. Bongard, Andrew N. M...
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...
A recent trend in motion-based segmentation has been to rely on statistical procedures derived from ExpectationMaximization (EM) principles. EM-based approaches have various attra...
The quest for a vision system capable of representing and recognizing arbitrary motions benefits from a low dimensional, non-specific representation of flow fields, to be used in ...