We propose a new template-based approach for viewinvariant recognition of body poses, based on geometric constraints derived from the motion of body point triplets. In addition to...
In this paper we develop an algorithm for action recognition and localization in videos. The algorithm uses a figurecentric visual word representation. Different from previous ap...
We describe a robust real-time 3D tracking system of the extreme limbs of the upper human body, i.e., the hands and the face. The goal of the system is that it can be used as a per...
Jose Maria Buades Rubio, Francisco J. Perales L&oa...
The objective of this paper is to estimate 2D human pose as a spatial configuration of body parts in TV and movie video shots. Such video material is uncontrolled and extremely ch...
Abstract. We present a new approach to biometrics that makes probabilistic inferences about matching without ever estimating an identity "template". The biometric data is...
Simon J. D. Prince, Jania Aghajanian, Umar Mohamme...