Sciweavers

1956 search results - page 97 / 392
» Learning the Relative Importance of Features in Image Data
Sort
View
170
Voted
CVPR
2011
IEEE
14 years 11 months ago
Learning Object Color Models from Multi-view Constraints
Color is known to be highly discriminative for many object recognition tasks, but is difficult to infer from uncontrolled images in which the illuminant is not known. Traditional...
Trevor Owens, Kate Saenko, Trevor Darrell, Ayan Ch...
133
Voted
ICCV
2009
IEEE
15 years 1 months ago
Learning to predict where humans look
For many applications in graphics, design, and human computer interaction, it is essential to understand where humans look in a scene. Where eye tracking devices are not a viable ...
Tilke Judd, Krista A. Ehinger, Frédo Durand...
168
Voted
CVPR
2010
IEEE
1872views Computer Vision» more  CVPR 2010»
15 years 11 months ago
New Features and Insights for Pedestrian Detection
Despite impressive progress in people detection the performance on challenging datasets like Caltech Pedestrians or TUD-Brussels is still unsatisfactory. In this work we show that...
Stefan Walk, Nikodem Majer, Konrad Schindler, Bern...
ICCV
2009
IEEE
1419views Computer Vision» more  ICCV 2009»
16 years 8 months ago
On Feature Combination for Multiclass Object Classification
A key ingredient in the design of visual object classification systems is the identification of relevant class specific aspects while being robust to intra-class variations. Whil...
Peter Gehler, Sebastian Nowozin
KDD
2009
ACM
153views Data Mining» more  KDD 2009»
16 years 4 months ago
Predicting bounce rates in sponsored search advertisements
This paper explores an important and relatively unstudied quality measure of a sponsored search advertisement: bounce rate. The bounce rate of an ad can be informally defined as t...
D. Sculley, Robert G. Malkin, Sugato Basu, Roberto...