12610 search results - page 393 / 2522 » Recognition using Regions |
244
click to vote
ECCV
2008
Springer
16 years 8 months ago
2008
Springer
We propose an algorithm for semantic segmentation based on 3D point clouds derived from ego-motion. We motivate five simple cues designed to model specific patterns of motion and 3...
162
click to vote
CVPR
2007
IEEE
16 years 1 months ago
2007
IEEE
In this work, we systematically study the problem of visual event recognition in unconstrained news video sequences. We adopt the discriminative kernel-based method for which vide...
166
click to vote
ICPR
2008
IEEE
16 years 1 months ago
2008
IEEE
Most successful object recognition systems are based on a visual alphabet of quantised gradient orientations. Here, we introduce two richer image feature alphabets for use in obje...
173
click to vote
EP
1998
Springer
15 years 11 months ago
1998
Springer
This paper deals with the representation of document models used in the field of document recognition. A novel formalism called generalized n-gram is presented, which is shown to b...
149
click to vote
MVA
1990
15 years 8 months ago
1990
: We present a symbol recognition method without segmentation of the document. Our approach uses Zernike moments for the coding and a multilayered Perceptron for the classifier. Re...