Context by region ancestry
Authors:
- 1 September 2009
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1978-1985
Abstract
In this paper, we introduce a new approach for modeling visual context. For this purpose, we consider the leaves of a hierarchical segmentation tree as elementary units. Each leaf is described by features of its ancestral set, the regions on the path linking the leaf to the root. We construct region trees by using a high-performance segmentation method. We then learn the importance of different descriptors (e.g. color, texture, shape) of the ancestors for classification. We report competitive results on the MSRC segmentation dataset and the MIT scene dataset, showing that region ancestry efficiently encodes information about discriminative parts, objects and scenes.Keywords
This publication has 20 references indexed in Scilit:
- Robust higher order potentials for enforcing label consistency2008
- Using contours to detect and localize junctions in natural images2008
- Discriminative modeling by Boosting on Multilevel Aggregates2008
- Learning subcategory relevances for category recognition2008
- Region Classification with Markov Field Aspect Models2007
- Geometric context from a single image2005
- A hierarchical field framework for unified context-based classification2005
- Representing and Recognizing the Visual Appearance of Materials using Three-dimensional TextonsInternational Journal of Computer Vision, 2001
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001
- HIGH-LEVEL SCENE PERCEPTIONAnnual Review of Psychology, 1999