Sciweavers

712 search results - page 13 / 143
» Pruning Training Sets for Learning of Object Categories
Sort
View
ICCV
2009
IEEE
15 years 21 days ago
Joint learning of visual attributes, object classes and visual saliency
We present a method to learn visual attributes (eg.“red”, “metal”, “spotted”) and object classes (eg. “car”, “dress”, “umbrella”) together. We assume imag...
Gang Wang, David Forsyth
CLOR
2006
13 years 11 months ago
Shared Features for Multiclass Object Detection
Abstract. We consider the problem of detecting a large number of different classes of objects in cluttered scenes. We present a learning procedure, based on boosted decision stumps...
Antonio B. Torralba, Kevin P. Murphy, William T. F...
ICCV
2007
IEEE
14 years 9 months ago
Learning Globally-Consistent Local Distance Functions for Shape-Based Image Retrieval and Classification
We address the problem of visual category recognition by learning an image-to-image distance function that attempts to satisfy the following property: the distance between images ...
Andrea Frome, Yoram Singer, Fei Sha, Jitendra Mali...
ICMI
2009
Springer
162views Biometrics» more  ICMI 2009»
14 years 2 months ago
Multi-modal features for real-time detection of human-robot interaction categories
Social interactions unfold over time, at multiple time scales, and can be observed through multiple sensory modalities. In this paper, we propose a machine learning framework for ...
Ian R. Fasel, Masahiro Shiomi, Pilippe-Emmanuel Ch...
FLAIRS
2006
13 years 9 months ago
Using Validation Sets to Avoid Overfitting in AdaBoost
AdaBoost is a well known, effective technique for increasing the accuracy of learning algorithms. However, it has the potential to overfit the training set because its objective i...
Tom Bylander, Lisa Tate