In this paper, we approach the problem of understanding human actions from still images. Our method involves representing the pose with a spatial and orientational histogramming o...
Nazli Ikizler, Pinar Duygulu, Ramazan Gokberk Cinb...
This paper presents a novel representation for human actions which encodes the variations in the shape and motion of the performing actor. When an actor performs an action, at eac...
We present a method to learn models of human heads for the purpose of detection from different viewing angles. We focus on a model where objects are represented as constellations ...
Modeling, characterization and analysis of biological shapes and forms are important in many computational biology studies. Shape representation challenges span the spectrum from s...
Bin Dong, Yu Mao, Ivo D. Dinov, Zhuowen Tu, Yongga...
We advocate the use of Gaussian Process Dynamical Models (GPDMs) for learning human pose and motion priors for 3D people tracking. A GPDM provides a lowdimensional embedding of hu...