Context by region ancestry
- 1 September 2009
- conference paper
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE) in 2009 IEEE 12th International Conference on Computer Vision
- p. 1978-1985
- https://doi.org/10.1109/iccv.2009.5459436
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 consistencyPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Using contours to detect and localize junctions in natural imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Discriminative modeling by Boosting on Multilevel AggregatesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Learning subcategory relevances for category recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Region Classification with Markov Field Aspect ModelsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Geometric context from a single imagePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- A hierarchical field framework for unified context-based classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- 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