Sciweavers

603 search results - page 106 / 121
» A discriminative model for semi-supervised learning
Sort
View
CVPR
2008
IEEE
14 years 11 months ago
Auto-context and its application to high-level vision tasks
The notion of using context information for solving highlevel vision problems has been increasingly realized in the field. However, how to learn an effective and efficient context...
Zhuowen Tu
CVPR
2009
IEEE
1002views Computer Vision» more  CVPR 2009»
15 years 4 months ago
Classifier Grids for Robust Adaptive Object Detection
In this paper we present an adaptive but robust object detector for static cameras by introducing classifier grids. Instead of using a sliding window for object detection we pro...
Peter M. Roth, Sabine Sternig, Helmut Grabner, Hor...
ICML
2007
IEEE
14 years 9 months ago
Piecewise pseudolikelihood for efficient training of conditional random fields
Discriminative training of graphical models can be expensive if the variables have large cardinality, even if the graphical structure is tractable. In such cases, pseudolikelihood...
Charles A. Sutton, Andrew McCallum
KDD
2002
ACM
160views Data Mining» more  KDD 2002»
14 years 9 months ago
Scaling multi-class support vector machines using inter-class confusion
Support vector machines (SVMs) excel at two-class discriminative learning problems. They often outperform generative classifiers, especially those that use inaccurate generative m...
Shantanu Godbole, Sunita Sarawagi, Soumen Chakraba...
MIR
2006
ACM
141views Multimedia» more  MIR 2006»
14 years 2 months ago
Mining temporal patterns of movement for video content classification
Scalable approaches to video content classification are limited by an inability to automatically generate representations of events ode abstract temporal structure. This paper pre...
Michael Fleischman, Philip DeCamp, Deb Roy