563 search results - page 29 / 113 » Feature Space Trajectory Methods for Active Computer Vision |
103
click to vote
HUMO
2007
Springer
15 years 3 months 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...
138
click to vote
CVPR
2009
IEEE
16 years 4 months ago
2009
IEEE
Scarcity and infeasibility of human supervision for large
scale multi-class classification problems necessitates active
learning. Unfortunately, existing active learning methods
...
118
Voted
CVPR
2001
IEEE
15 years 11 months ago
2001
IEEE
To utilize CT or MRI images for computer aided diagnosis applications, robust features that represent 3-D image data need to be constructed and subsequently used by a classificati...
65
Voted
ICPR
2010
IEEE
14 years 7 months ago
2010
IEEE
We report performance evaluation of our automatic feature discovery method on the publicly available Gisette dataset: a set of 29 features discovered by our method ranks 129 among...
84
Voted
ICCV
2005
IEEE
15 years 11 months ago
2005
IEEE
Human action in video sequences can be seen as silhouettes of a moving torso and protruding limbs undergoing articulated motion. We regard human actions as three-dimensional shapes...