3D human pose recovery is considered as a fundamental step in view-invariant human action recognition. However, inferring 3D poses from a single view usually is slow due to the la...
We present a distributed representation of pose and appearance of people called the “poselet activation vector”. First we show that this representation can be used to estimate...
This paper presents a new system for recognition, tracking and pose estimation of people in video sequences. It is based on the wavelet transform from the upper body part and uses ...
Philipp Zehnder, Esther Koller-Meier, Luc J. Van G...
Tracking people using movie sequences is not straightforward because of the human body's articulation and the complexity of a person's movements. In this paper we show ho...