Sciweavers

CVPR
2012
IEEE
12 years 1 months ago
Large-scale knowledge transfer for object localization in ImageNet
ImageNet is a large-scale database of object classes with millions of images. Unfortunately only a small fraction of them is manually annotated with bounding-boxes. This prevents ...
Matthieu Guillaumin, Vittorio Ferrari
CVPR
2012
IEEE
12 years 1 months ago
Learning object class detectors from weakly annotated video
Object detectors are typically trained on a large set of still images annotated by bounding-boxes. This paper introduces an approach for learning object detectors from realworld w...
Alessandro Prest, Christian Leistner, Javier Civer...
ACCV
2010
Springer
13 years 6 months ago
Generic Object Class Detection Using Boosted Configurations of Oriented Edges
Abstract. In this paper we introduce a new representation for shapebased object class detection. This representation is based on very sparse and slightly flexible configurations of...
Oscar M. Danielsson, Stefan Carlsson
PRL
2006
78views more  PRL 2006»
13 years 11 months ago
The interaction between classification and reject performance for distance-based reject-option classifiers
Consider the class of problems in which a target class is well-defined, and an outlier class is ill-defined. In these cases new outlier classes can appear, or the class-conditiona...
Thomas Landgrebe, David M. J. Tax, Pavel Pacl&iacu...
AUSAI
2008
Springer
14 years 1 months ago
Discriminating Against New Classes: One-class versus Multi-class Classification
Many applications require the ability to identify data that is anomalous with respect to a target group of observations, in the sense of belonging to a new, previously unseen `atta...
Kathryn Hempstalk, Eibe Frank
ATAL
2006
Springer
14 years 3 months ago
Learning against multiple opponents
We address the problem of learning in repeated N-player (as opposed to 2-player) general-sum games. We describe an extension to existing criteria focusing explicitly on such setti...
Thuc Vu, Rob Powers, Yoav Shoham
EUROGP
2009
Springer
130views Optimization» more  EUROGP 2009»
14 years 6 months ago
One-Class Genetic Programming
One-class classification naturally only provides one-class of exemplars, the target class, from which to construct the classification model. The one-class approach is constructed...
Robert Curry, Malcolm I. Heywood
MCS
2010
Springer
14 years 6 months ago
Class-Separability Weighting and Bootstrapping in Error Correcting Output Code Ensembles
A method for applying weighted decoding to error-correcting output code ensembles of binary classifiers is presented. This method is sensitive to the target class in that a separa...
Raymond S. Smith, Terry Windeatt