Shape Matching and Object Recognition Using Shape Contexts
IEEE Transactions on Pattern Analysis and Machine Intelligence
Towards a Mathematical Theory of Primal Sketch and Sketchability
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Estimation of probabilistic context-free grammars
Computational Linguistics
Pictorial Structures for Object Recognition
International Journal of Computer Vision
Random Subwindows for Robust Image Classification
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Histograms of Oriented Gradients for Human Detection
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
Generative versus Discriminative Methods for Object Recognition
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
A Bayesian Hierarchical Model for Learning Natural Scene Categories
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Creating Efficient Codebooks for Visual Recognition
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
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
Supervised Learning of Edges and Object Boundaries
CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Layered Graph Matching with Composite Cluster Sampling
IEEE Transactions on Pattern Analysis and Machine Intelligence
Learning Active Basis Model for Object Detection and Recognition
International Journal of Computer Vision
Representing and recognizing objects with massive local image patches
Pattern Recognition
Evolutionary optimization of a hierarchical object recognition model
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Learning from examples in the small sample case: face expression recognition
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Constructing PCA Baseline Algorithms to Reevaluate ICA-Based Face-Recognition Performance
IEEE Transactions on Systems, Man, and Cybernetics, Part B: Cybernetics
Learning contour-fragment-based shape model with And-Or tree representation
CVPR '12 Proceedings of the 2012 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
A jointly distributed semi-supervised topic model
Neurocomputing
| Hi-index | 0.01 |
In this paper, we present a framework for object categorization via sketch graphs 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). Considering the computation efficiency, we generalize instances from the And-Or graph models and perform a set of sequential tests for cascaded object categorization, rather than directly inferring with the And-Or graph models. We study 33 categories, each consisting of a small data set of 30 instances, and 30 additional templates with varied appearance are generalized from the learned And-Or graph model. These samples better span the appearance space and form an augmented training set @W"T of 1980 (60x33) training templates. To perform recognition on a testing image, we use a set of sequential tests to project @W"T into different representation spaces to narrow the number of candidate matches in @W"T. We use ''graphlets'' (structural elements), as our local features and model @W"T at each stage using histograms of graphlets over categories, histograms of graphlets over object instances, histograms of pairs of graphlets over objects, and shape context. Each test is increasingly computationally expensive, and by the end of the cascade we have a small candidate set remaining to use with our most powerful test, a top-down graph matching algorithm. We apply the proposed approach on the challenging public dataset including 33 object categories, and achieve state-of-the-art performance.