This paper proposes a clustered exemplar-based model for performing viewpoint invariant tracking of the 3D motion of a human subject from a single camera. Each exemplar is associa...
Eng-Jon Ong, Antonio S. Micilotta, Richard Bowden,...
In this paper we present a technique for predicting the 2D human body joints and limbs position in monocular image sequences, and reconstructing its corresponding 3D postures using...
— This paper presents a parallel algorithm of the Level Set Method named the Parallel Fast Level Set Method, and its application for real-time 3D reconstruction of human shape an...
In this paper we present a new bimanual markerless gesture interface for 3D full-body motion tracking sensors, such as the Kinect. Our interface uses a probabilistic algorithm to ...
Per Ola Kristensson, Thomas Nicholson, Aaron J. Qu...
This paper presents two approaches for the representation and recognition of human action in video, aiming for viewpoint invariance. The paper first presents new results using a 2...