Modeling the Shape of the Scene: A Holistic Representation of the Spatial Envelope
International Journal of Computer Vision
Contextual Priming for Object Detection
International Journal of Computer Vision
Probability Estimates for Multi-class Classification by Pairwise Coupling
The Journal of Machine Learning Research
A Hierarchical Field Framework for Unified Context-Based Classification
ICCV '05 Proceedings of the Tenth IEEE International Conference on Computer Vision - Volume 2
Semantic Modeling of Natural Scenes for Content-Based Image Retrieval
International Journal of Computer Vision
LabelMe: A Database and Web-Based Tool for Image Annotation
International Journal of Computer Vision
Context based object categorization: A critical survey
Computer Vision and Image Understanding
Semantic label sharing for learning with many categories
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part I
What does classifying more than 10,000 image categories tell us?
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
Non-local characterization of scenery images: statistics, 3D reasoning, and a generative model
ECCV'10 Proceedings of the 11th European conference on Computer vision: Part V
LIBSVM: A library for support vector machines
ACM Transactions on Intelligent Systems and Technology (TIST)
Learning and incorporating top-down cues in image segmentation
ECCV'06 Proceedings of the 9th European conference on Computer Vision - Volume Part I
Factor graphs and the sum-product algorithm
IEEE Transactions on Information Theory
Hi-index | 0.00 |
We present two novel contributions to the problem of region classification in scenery/landscape images. The first is a model that incorporates local cues with global layout cues, following the statistical characteristics recently suggested in [1]. The observation that background regions in scenery images tend to horizontally span the image allows us to represent the contextual dependencies between background region labels with a simple graphical model, on which exact inference is possible. While background is traditionally classified using only local color and textural features, we show that using new layout cues significantly improves background region classification. Our second contribution addresses the problem of correct results being considered as errors in cases where the ground truth provides the structural class of a land region (e.g., mountain), while the classifier provides its coverage class (e.g., grass), or vice versa. We suggest an alternative labeling method that, while trained using ground truth that describes each region with one label, assigns both a structural and a coverage label for each land region in the validation set. By suggesting multiple labels, each describing a different aspect of the region, the method provides more information than that available in the ground truth.