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...
Complex human motion sequences (such as dances) are typically analyzed by segmenting them into shorter motion sequences, called gestures. However, this segmentation process is sub...
Abstract— This paper describes a feasibility study for a selfcontained, wearable full-body motion capture system based on time-of-flight measurements that provide absolute dista...
Christopher Einsmann, Meghan Quirk, Ben Muzal, Bha...
This paper presents a Bayesian framework for 3D facial reconstruction. The framework iteratively deforms a generic face mesh to fit a set of range points representing a face. The...
Abstract We describe a method of representing human activities that allows a collection of motions to be queried without examples, using a simple and effective query language. Our ...