In this paper we address the problem of human body pose estimation from still images. A multi-view set of images of a person sitting at a table is acquired and the pose estimated....
Finding fiducial facial points in any frame of a video showing rich naturalistic facial behaviour is an unsolved problem. Yet this is a crucial step for geometric-featurebased fa...
Michel Valstar, Brais Martinez, Xavier Binefa, Maj...
This paper describes a system for object segmentation and feature extraction for surveillance video. Segmentation is performed by a dynamic vision system that fuses information fr...
Abstract— Scene recognition is a highly valuable perceptual ability for an indoor mobile robot, however, current approaches for scene recognition present a significant drop in p...
Pablo Espinace, Thomas Kollar, Alvaro Soto, Nichol...
We present a three-step post-processing method for increasing the precision of video shot labels in the domain of television news. First, we demonstrate that news shot sequences c...