Learning what and how of contextual models for scene labeling

Authors:
Arpit Jain;Abhinav Gupta;Larry S. Davis
Affiliations:
University of Maryland, MD;Carnegie Mellon University, Pittsburgh, PA;University of Maryland, MD
Venue:
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part IV
Year:
2010

Citing 10
Cited 3

Texture Segmentation by Multiscale Aggregation of Filter Responses and Shape Elements

ICCV '03 Proceedings of the Ninth IEEE International Conference on Computer Vision - Volume 2
Large Margin Methods for Structured and Interdependent Output Variables

The Journal of Machine Learning Research
Geometric Context from a Single Image

ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision (ICCV'05) Volume 1 - Volume 01
Model Order Selection and Cue Combination for Image Segmentation

CVPR '06 Proceedings of the 2006 IEEE Computer Society Conference on Computer Vision and Pattern Recognition - Volume 1
More efficiency in multiple kernel learning

Proceedings of the 24th international conference on Machine learning
LabelMe: A Database and Web-Based Tool for Image Annotation

International Journal of Computer Vision
Beyond Nouns: Exploiting Prepositions and Comparative Adjectives for Learning Visual Classifiers

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part I
Learning CRFs Using Graph Cuts

ECCV '08 Proceedings of the 10th European Conference on Computer Vision: Part II
Cautious inference in collective classification

AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 1
The Bayesian structural EM algorithm

UAI'98 Proceedings of the Fourteenth conference on Uncertainty in artificial intelligence

Harmony Potentials

International Journal of Computer Vision
SLEDGE: Sequential Labeling of Image Edges for Boundary Detection

International Journal of Computer Vision
Object class detection: A survey

ACM Computing Surveys (CSUR)

Quantified Score

Hi-index	0.00

Visualization

Abstract

We present a data-driven approach to predict the importance of edges and construct a Markov network for image analysis based on statistical models of global and local image features. We also address the coupled problem of predicting the feature weights associated with each edge of a Markov network for evaluation of context. Experimental results indicate that this scene dependent structure construction model eliminates spurious edges and improves performance over fully-connected and neighborhood connected Markov network.