2117 search results - page 318 / 424 » A Metadata Model for Capturing Presentations |
212
click to vote
HUMO
2007
Springer
16 years 17 days ago
2007
Springer
We present a method to simultaneously estimate 3d body pose and action categories from monocular video sequences. Our approach learns a lowdimensional embedding of the pose manifol...
162
click to vote
SEKE
2007
Springer
16 years 15 days ago
2007
Springer
A number of enterprises are turning towards the Service Oriented Architecture (SOA) approach for their systems due to the number of benefits it offers. A key enabling technology ...
176
click to vote
CVPR
2006
IEEE
16 years 14 days ago
2006
IEEE
This work investigates the use of nonlinear dependencies in natural image sequence statistics to learn higher-order structures in natural videos. We propose a two-layer model that...
268
click to vote
ICARCV
2006
IEEE
16 years 13 days ago
2006
IEEE
— As confirmed by recent neurophysiological studies, the use of dynamic information is extremely important for humans in visual perception of biological forms and motion. Apart ...
173
click to vote
ICPR
2006
IEEE
16 years 13 days ago
2006
IEEE
In this paper, we present a novel method for human action recognition from any arbitrary view image sequence that uses the Cartesian component of optical flow velocity and human ...