11 search results - page 2 / 3 » Learning Deformable Action Templates from Crowded Videos |
ICCV
2009
IEEE
15 years 2 months ago
2009
IEEE
In this paper, we investigate the detection of semantic
human actions in complex scenes. Unlike conventional
action recognition in well-controlled environments,
action detection...
CVPR
2007
IEEE
14 years 11 months ago
2007
IEEE
The active appearance model (AAM) is a powerful method for modeling deformable visual objects. One of the major drawbacks of the AAM is that it requires a training set of pseudo-d...
GRAPHICSINTERFACE
2011
13 years 1 months ago
2011
Most of existing crowd simulation algorithms focus on the moving trajectories of individual agents, while collective group formations are often roughly learned from video examples...
CVPR
2009
IEEE
15 years 4 months ago
2009
IEEE
We present a new method for classification with structured
latent variables. Our model is formulated using the
max-margin formalism in the discriminative learning literature.
We...
IADIS
2004
13 years 11 months ago
2004
This paper introduces a study, part of a work concerning a tool that enables teachers to create educational materials. Production of such educational materials is based on predefi...