Sciweavers

2702 search results - page 232 / 541
» Requirements Processes: An Experience Report
Sort
View
CVPR
2012
IEEE
13 years 9 months ago
RALF: A reinforced active learning formulation for object class recognition
Active learning aims to reduce the amount of labels required for classification. The main difficulty is to find a good trade-off between exploration and exploitation of the lab...
Sandra Ebert, Mario Fritz, Bernt Schiele
ICCV
2003
IEEE
16 years 8 months ago
Counting People in Crowds with a Real-Time Network of Simple Image Sensors
Estimating the number of people in a crowded environment is a central task in civilian surveillance. Most vision-based counting techniques depend on detecting individuals in order...
Danny B. Yang, Héctor H. González-Ba...
ECCV
2008
Springer
16 years 8 months ago
Hierarchical Support Vector Random Fields: Joint Training to Combine Local and Global Features
Abstract. Recently, impressive results have been reported for the detection of objects in challenging real-world scenes. Interestingly however, the underlying models vary greatly e...
Paul Schnitzspan, Mario Fritz, Bernt Schiele
ICPR
2004
IEEE
16 years 7 months ago
Decoder Banks: Versatility, Automation, and High Accuracy without Supervised Training
A methodology using decoder banks is proposed for high-accuracy, fully automatic recognition of machine printed text across a wide range of challenging image qualities, without re...
Henry S. Baird, Prateek Sarkar
ICML
2004
IEEE
16 years 7 months ago
Co-EM support vector learning
Multi-view algorithms, such as co-training and co-EM, utilize unlabeled data when the available attributes can be split into independent and compatible subsets. Co-EM outperforms ...
Ulf Brefeld, Tobias Scheffer