Sciweavers

626 search results - page 1 / 126
» Adaptive figure-ground classification
Sort
View
WSOM
2009
Springer
13 years 11 months ago
Incremental Figure-Ground Segmentation Using Localized Adaptive Metrics in LVQ
Vector quantization methods are confronted with a model selection problem, namely the number of prototypical feature representatives to model each class. In this paper we present a...
Alexander Denecke, Heiko Wersing, Jochen J. Steil,...
ECCV
2002
Springer
14 years 6 months ago
Probabilistic and Voting Approaches to Cue Integration for Figure-Ground Segmentation
This paper describes techniques for fusing the output of multiple cues to robustly and accurately segment foreground objects from the background in image sequences. Two different m...
Eric Hayman, Jan-Olof Eklundh
CVPR
2009
IEEE
1148views Computer Vision» more  CVPR 2009»
14 years 11 months ago
Shape Constrained Figure-Ground Segmentation and Tracking
Global shape information is an effective top-down complement to bottom-up figure-ground segmentation as well as a useful constraint to avoid drift during adaptive tracking. We p...
Zhaozheng Yin, Robert T. Collins
ICML
2005
IEEE
14 years 5 months ago
Adapting two-class support vector classification methods to many class problems
A geometric construction is presented which is shown to be an effective tool for understanding and implementing multi-category support vector classification. It is demonstrated ho...
Simon I. Hill, Arnaud Doucet
IADIS
2003
13 years 6 months ago
Hypertext Classification: A Multiagent Model for Adaptive Learning Algorithm
The problem of hypertext classification deals with objects possessing more complex information structure than the plain text has. Present hypertext classification systems show the...
Stanislav Baglei