Shape-Based Object Localization for Descriptive Classification

Authors:
Geremy Heitz;Gal Elidan;Benjamin Packer;Daphne Koller
Affiliations:
Stanford University, Stanford, USA 94305;Department of Statistics, Hebrew University of Jerusalem, Jerusalem, Israel 91905;Stanford University, Stanford, USA 94305;Stanford University, Stanford, USA 94305
Venue:
International Journal of Computer Vision
Year:
2009

Citing 30
Cited 6

Probabilistic reasoning in intelligent systems: networks of plausible inference

Probabilistic reasoning in intelligent systems: networks of plausible inference
Hierarchical Chamfer Matching: A Parametric Edge Matching Algorithm

IEEE Transactions on Pattern Analysis and Machine Intelligence
Elements of information theory

Elements of information theory
Active shape models—their training and application

Computer Vision and Image Understanding
Improved Boosting Algorithms Using Confidence-rated Predictions

Machine Learning - The Eleventh Annual Conference on computational Learning Theory
Diffusion Snakes: Introducing Statistical Shape Knowledge into the Mumford-Shah Functional

International Journal of Computer Vision
Active Appearance Models

ECCV '98 Proceedings of the 5th European Conference on Computer Vision-Volume II - Volume II
Geodesic active contours

ICCV '95 Proceedings of the Fifth International Conference on Computer Vision
Recognition of Shapes by Editing Their Shock Graphs

IEEE Transactions on Pattern Analysis and Machine Intelligence
Convex Optimization

Convex Optimization
Distinctive Image Features from Scale-Invariant Keypoints

International Journal of Computer Vision
Combining Top-Down and Bottom-Up Segmentation

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 4 - Volume 04
Learning Generative Visual Models from Few Training Examples: An Incremental Bayesian Approach Tested on 101 Object Categories

CVPRW '04 Proceedings of the 2004 Conference on Computer Vision and Pattern Recognition Workshop (CVPRW'04) Volume 12 - Volume 12
OBJ CUT

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
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
Spatial Priors for Part-Based Recognition Using Statistical Models

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
A Sparse Object Category Model for Efficient Learning and Exhaustive Recognition

CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 1 - Volume 01
SCAPE: shape completion and animation of people

ACM SIGGRAPH 2005 Papers
Contour-Based Learning for Object Detection

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
The Pyramid Match Kernel: Discriminative Classification with Sets of Image Features

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Efficient Learning of Relational Object Class Models

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Incremental learning of object detectors using a visual shape alphabet

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
Design and Performance of a Fault-Tolerant Real-Time CORBA Event Service

ECRTS '06 Proceedings of the 18th Euromicro Conference on Real-Time Systems
Learning Object Shape: From Drawings to Images

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Single View Reconstruction of Curved Surfaces

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 2
Groups of Adjacent Contour Segments for Object Detection

IEEE Transactions on Pattern Analysis and Machine Intelligence
From Aardvark to Zorro: A Benchmark for Mammal Image Classification

International Journal of Computer Vision
Shape context and chamfer matching in cluttered scenes

CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Weakly supervised learning of part-based spatial models for visual object recognition

ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Object detection by contour segment networks

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

An Approach to the Parameterization of Structure for Fast Categorization

International Journal of Computer Vision
Boosting chamfer matching by learning chamfer distance normalization

ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Classification and Semantic Mapping of Urban Environments

International Journal of Robotics Research
PMA: Pixel-based multi-anchor algorithm for image recognition on multi-core systems

Proceedings of the 2012 International Workshop on Programming Models and Applications for Multicores and Manycores
A segmentation-free method for image classification based on pixel-wise matching

Journal of Computer and System Sciences
Object class detection: A survey

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

Discriminative tasks, including object categorization and detection, are central components of high-level computer vision. However, sometimes we are interested in a finer-grained characterization of the object's properties, such as its pose or articulation. In this paper we develop a probabilistic method (LOOPS) that can learn a shape and appearance model for a particular object class, and be used to consistently localize constituent elements (landmarks) of the object's outline in test images. This localization effectively projects the test image into an alternative representational space that makes it particularly easy to perform various descriptive tasks. We apply our method to a range of object classes in cluttered images and demonstrate its effectiveness in localizing objects and performing descriptive classification, descriptive ranking, and descriptive clustering.