Sciweavers

65 search results - page 12 / 13
» Multiple Classifier System Approach to Model Pruning in Obje...
Sort
View
IJCV
2011
264views more  IJCV 2011»
13 years 22 days ago
Cost-Sensitive Active Visual Category Learning
Abstract We present an active learning framework that predicts the tradeoff between the effort and information gain associated with a candidate image annotation, thereby ranking un...
Sudheendra Vijayanarasimhan, Kristen Grauman
PAMI
2006
106views more  PAMI 2006»
13 years 5 months ago
Statistical Analysis of Dynamic Actions
Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actio...
Lihi Zelnik-Manor, Michal Irani
CVPR
2007
IEEE
13 years 9 months ago
On the Performance Prediction and Validation for Multisensor Fusion
Multiple sensors are commonly fused to improve the detection and recognition performance of computer vision and pattern recognition systems. The traditional approach to determine ...
Rong Wang, Bir Bhanu
CVPR
2011
IEEE
13 years 2 months ago
Interactively Building a Discriminative Vocabulary of Nameable Attributes
Human-nameable visual attributes offer many advantages when used as mid-level features for object recognition, but existing techniques to gather relevant attributes can be ineffici...
Devi Parikh, Kristen Grauman
CVPR
2009
IEEE
15 years 26 days ago
What's It Going to Cost You?: Predicting Effort vs. Informativeness for Multi-Label Image Annotations
Active learning strategies can be useful when manual labeling effort is scarce, as they select the most informative examples to be annotated first. However, for visual category ...
Sudheendra Vijayanarasimhan (University of Texas a...