Probabilistic reasoning in intelligent systems: networks of plausible inference
Probabilistic reasoning in intelligent systems: networks of plausible inference
An Active Testing Model for Tracking Roads in Satellite Images
IEEE Transactions on Pattern Analysis and Machine Intelligence
Graphical Templates for Model Registration
IEEE Transactions on Pattern Analysis and Machine Intelligence
Filters, Random Fields and Maximum Entropy (FRAME): Towards a Unified Theory for Texture Modeling
International Journal of Computer Vision
Efficient deformable template detection and localization without user initialization
Computer Vision and Image Understanding
Image Segmentation by Data-Driven Markov Chain Monte Carlo
IEEE Transactions on Pattern Analysis and Machine Intelligence
Example-Based Super-Resolution
IEEE Computer Graphics and Applications
Stereo Matching Using Belief Propagation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part II
Finding Deformable Shapes Using Loopy Belief Propagation
ECCV '02 Proceedings of the 7th European Conference on Computer Vision-Part III
A Bayesian Network Framework for Relational Shape Matching
ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Pictorial Structures for Object Recognition
International Journal of Computer Vision
Fields of Experts: A Framework for Learning Image Priors
CVPR '05 Proceedings of the 2005 IEEE Computer Society Conference on Computer Vision and Pattern Recognition (CVPR'05) - Volume 2 - Volume 02
Computer Vision and Image Understanding
The Representation and Matching of Pictorial Structures
IEEE Transactions on Computers
Deformable templates for face recognition
Journal of Cognitive Neuroscience
Multiscale conditional random fields for image labeling
CVPR'04 Proceedings of the 2004 IEEE computer society conference on Computer vision and pattern recognition
Representation and detection of deformable shapes
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Man-made structure detection in natural images using a causal multiscale random field
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Nonparametric belief propagation
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
PAMPAS: real-valued graphical models for computer vision
CVPR'03 Proceedings of the 2003 IEEE computer society conference on Computer vision and pattern recognition
Loopy belief propagation for approximate inference: an empirical study
UAI'99 Proceedings of the Fifteenth conference on Uncertainty in artificial intelligence
Computer Vision and Image Understanding
Guest Editorial: Generative model based vision
Computer Vision and Image Understanding
On the computational rationale for generative models
Computer Vision and Image Understanding
Nonparametric belief propagation
Communications of the ACM
Monte Carlo MCMC: efficient inference by approximate sampling
EMNLP-CoNLL '12 Proceedings of the 2012 Joint Conference on Empirical Methods in Natural Language Processing and Computational Natural Language Learning
The Journal of Machine Learning Research
Hi-index | 0.02 |
Graphical models provide an attractive framework for modeling a variety of problems in computer vision. The advent of powerful inference techniques such as belief propagation (BP) has recently made inference with many of these models tractable. Even so, the enormous size of the state spaces required for some applications can create a heavy computational burden. Pruning is a standard technique for reducing this burden, but since pruning is irreversible it carries the risk of greedily deleting important states, which can subsequently result in gross errors in BP. To address this problem, we propose a novel extension of pruning, which we call dynamic quantization (DQ), that allows BP to adaptively add as well as subtract states as needed. We examine DQ in the context of graphical-model based deformable template matching, in which the state space size is on the order of the number of pixels in an image. The combination of BP and DQ yields deformable templates that are both fast and robust to significant occlusions, without requiring any user initialization. Experimental results are shown on deformable templates of planar shapes. Finally, we argue that DQ is applicable to a variety of graphical models in which the state spaces are sparsely populated.