Machine Learning - Special issue on inductive transfer
Theoretical models of learning to learn
Learning to learn
ICML '98 Proceedings of the Fifteenth International Conference on Machine Learning
Robust classification of hand postures against complex backgrounds
FG '96 Proceedings of the 2nd International Conference on Automatic Face and Gesture Recognition (FG '96)
Online ensemble learning
Learning Multiple Tasks with Kernel Methods
The Journal of Machine Learning Research
Hand Posture Classification and Recognition using the Modified Census Transform
FGR '06 Proceedings of the 7th International Conference on Automatic Face and Gesture Recognition
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
A Framework for Learning Predictive Structures from Multiple Tasks and Unlabeled Data
The Journal of Machine Learning Research
Online Passive-Aggressive Algorithms
The Journal of Machine Learning Research
Sharing Visual Features for Multiclass and Multiview Object Detection
IEEE Transactions on Pattern Analysis and Machine Intelligence
Online Learning of Multiple Tasks with a Shared Loss
The Journal of Machine Learning Research
Incremental Learning for Robust Visual Tracking
International Journal of Computer Vision
Multitask learning with expert advice
COLT'07 Proceedings of the 20th annual conference on Learning theory
Gesture recognition under small sample size
ACCV'07 Proceedings of the 8th Asian conference on Computer vision - Volume Part I
| Hi-index | 0.00 |
In this paper we present a new approach to online multiple tasks framework using online boosting learning in parallel for object classification in visual objects. The main idea is (a) to learn visual models of object categories require training on hundreds or thousands of images and very large datasets, one-shot learning aims to learn information about object categories from one, or only a few, training images; (2) to employ training tasks in parallel while using a shared representation to one class or multi-class classification. What is learned for each task can help other tasks be learned better; (3) to bridge the gap between data acquisition and model building. We demonstrate robustness, efficient and accuracy of the approach on simultaneously online multiple tasks as one-shot learning complex background models, visual tracking, object detection and recognition on benchmark data sets.