Sciweavers

405 search results - page 48 / 81
» Binary Classification Trees for Multi-class Classification P...
Sort
View
TEC
2008
135views more  TEC 2008»
14 years 10 months ago
Evolving Output Codes for Multiclass Problems
In this paper, we propose an evolutionary approach to the design of output codes for multiclass pattern recognition problems. This approach has the advantage of taking into account...
Nicolás García-Pedrajas, Colin Fyfe
CVPR
2004
IEEE
16 years 21 days ago
Joint Feature-Basis Subset Selection
We treat feature selection and basis selection in a unified framework by introducing the masking matrix. If one considers feature selection as finding a binary mask vector that de...
Shai Avidan
ICIP
2008
IEEE
16 years 12 days ago
People re-detection using Adaboost with sift and color correlogram
People re-detection aims at performing re-identification of people who leave the scene and reappear after some time. This is an important problem especially in video surveillance ...
Lei Hu, Shuqiang Jiang, Qingming Huang, Wen Gao
KDD
2002
ACM
187views Data Mining» more  KDD 2002»
15 years 11 months ago
Transforming classifier scores into accurate multiclass probability estimates
Class membership probability estimates are important for many applications of data mining in which classification outputs are combined with other sources of information for decisi...
Bianca Zadrozny, Charles Elkan
CHI
2010
ACM
14 years 8 months ago
A comparative evaluation on tree visualization methods for hierarchical structures with large fan-outs
Hierarchical structures with large fan-outs are hard to browse and understand. In the conventional node-link tree visualization, the screen quickly becomes overcrowded as users op...
Hyunjoo Song, Bo Hyoung Kim, Bongshin Lee, Jinwook...