1547 search results - page 63 / 310 » Learning a Classification Model for Segmentation |
101
Voted
ICPR
2008
IEEE
15 years 8 months ago
2008
IEEE
This paper develops a weakly supervised algorithm that learns to segment rigid multi-colored objects from a set of training images and key points. The approach uses congealing to ...
136
Voted
ICML
2004
IEEE
16 years 3 months ago
2004
IEEE
In sequence modeling, we often wish to represent complex interaction between labels, such as when performing multiple, cascaded labeling tasks on the same sequence, or when longra...
125
Voted
ICIP
2010
IEEE
15 years 4 days ago
2010
IEEE
Texture classification is a classical yet still active topic in computer vision and pattern recognition. Recently, several new texture classification approaches by modeling textur...
119
click to vote
IDA
2001
Springer
15 years 6 months ago
2001
Springer
Abstract. We propose a new unsupervised training method for acquiring probability models that accurately segment Chinese character sequences into words. By constructing a core lexi...
116
Voted
CVPR
2004
IEEE
16 years 4 months ago
2004
IEEE
In video object classification, insufficient labeled data may at times be easily augmented with pairwise constraints on sample points, i.e, whether they are in the same class or n...