Object category recognition using generative template boosting

Authors:
Shaowu Peng;Liang Lin;Jake Porway;Nong Sang;Song-Chun Zhu
Affiliations:
IPRAI, Huazhong University of Science and Technology, Wuhan, P.R. China and Lotus Hill Institute for Computer Vision and Information Science, Ezhou, P.R. China;School of Information Science and Technology, Beijing Institute of Technology, Beijing, P.R. China and Lotus Hill Institute for Computer Vision and Information Science, Ezhou, P.R. China;Departments of Statistics, University of California, Los Angeles, Los Angeles, California;IPRAI, Huazhong University of Science and Technology, Wuhan, P.R. China and Lotus Hill Institute for Computer Vision and Information Science, Ezhou, P.R. China;Lotus Hill Institute for Computer Vision and Information Science, Ezhou, P.R. China and Departments of Statistics, University of California, Los Angeles, Los Angeles, California
Venue:
EMMCVPR'07 Proceedings of the 6th international conference on Energy minimization methods in computer vision and pattern recognition
Year:
2007

Citing 16
Cited 0

FORMS: a flexible object recognition and modeling system

International Journal of Computer Vision
Early Visual Learning

Early Visual Learning
Shape Matching and Object Recognition Using Shape Contexts

IEEE Transactions on Pattern Analysis and Machine Intelligence
Selection of Scale-Invariant Parts for Object Class Recognition

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Estimation of probabilistic context-free grammars

Computational Linguistics
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Perceptual Grouping for Contour Extraction

ICPR '04 Proceedings of the Pattern Recognition, 17th International Conference on (ICPR'04) Volume 2 - Volume 02
Pictorial Structures for Object Recognition

International Journal of Computer Vision
Shape Matching and Object Recognition Using Low Distortion Correspondences

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Creating Efficient Codebooks for Visual Recognition

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Probabilistic Boosting-Tree: Learning Discriminative Models for Classification, Recognition, and Clustering

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Bottom-up/Top-Down Image Parsing by Attribute Graph Grammar

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Composite Templates for Cloth Modeling and Sketching

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
The Representation and Matching of Pictorial Structures

IEEE Transactions on Computers
A stochastic grammar of images

Foundations and Trends® in Computer Graphics and Vision
Object detection by contour segment networks

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part III

Quantified Score

Hi-index	0.00

Visualization

Abstract

In this paper, we present a framework for object categorization via sketch graphs, structures that incorporate shape and structure information. In this framework, we integrate the learnable And-Or graph model, a hierarchical structure that combines the reconfigurability of a stochastic context free grammar(SCFG) with the constraints of a Markov random field(MRF), and we sample object configurations as training templates from this generative model. Based on these synthesized templates, four steps of discriminative approaches are adopted for cascaded pruning, while a template matching method is developed for top-down verification. These synthesized templates are sampled from the whole configuration space following the maximum entropy constraints. In contrast to manually choosing data, they have a great ability to represent the variability of each object category. The generalizability and flexibility of our framework is illustrated on 20 categories of sketch-based objects under different scales.