The power of amnesia: learning probabilistic automata with variable memory length
Machine Learning - Special issue on COLT '94
Learning to Recognize 3D Objects with SNoW
ECCV '00 Proceedings of the 6th European Conference on Computer Vision-Part I
Discriminative Feature Selection via Multiclass Variable Memory Markov Model
ICML '02 Proceedings of the Nineteenth International Conference on Machine Learning
Distinctive Image Features from Scale-Invariant Keypoints
International Journal of Computer Vision
Joint Spatial and Temporal Structure Learning for Task based Control
ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Real-time Hand Tracking With Variable-Length Markov Models of Behaviour
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Workshops - Volume 03
Q-learning of sequential attention for visual object recognition from informative local descriptors
ICML '05 Proceedings of the 22nd international conference on Machine learning
Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Multimedia Tools and Applications
| Hi-index | 0.00 |
This paper explores the use of alternating sequential patterns of local features and saccading actions to learn robust and compact object representations. The temporal encoding represents the spatial relations between local features. We view the problem of object recognition as a sequential prediction task. Our method uses a Discriminative Variable Memory Markov (DVMM) model that precisely captures underlying characteristics of multiple statistical sources that generate sequential patterns in a stochastic manner. By pruning out long sequential patterns when there is no further information gain over shorter and discriminative ones, the DVMM model is able to represent multiple objects succinctly. Experimental results show that the DVMM model performs significantly better compared to various other supervised learning algorithms that use a bag-of-features approach.