Attribute-centric recognition for cross-category generalization
Authors:
- 1 June 2010
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 10636919,p. 2352-2359
Abstract
We propose an approach to find and describe objects within broad domains. We introduce a new dataset that provides annotation for sharing models of appearance and correlation across categories. We use it to learn part and category detectors. These serve as the visual basis for an integrated model of objects. We describe objects by the spatial arrangement of their attributes and the interactions between them. Using this model, our system can find animals and vehicles that it has not seen and infer attributes, such as function and pose. Our experiments demonstrate that we can more reliably locate and describe both familiar and unfamiliar objects, compared to a baseline that relies purely on basic category detectors.Keywords
This publication has 22 references indexed in Scilit:
- Robust Object Detection with Interleaved Categorization and SegmentationInternational Journal of Computer Vision, 2007
- A Stochastic Grammar of ImagesFoundations and Trends in Computer Graphics and Vision, 2007
- Compositional Boosting for Computing Hierarchical Image Structures2007
- An Exemplar Model for Learning Object Classes2007
- Transfer Learning in Sign language2007
- Incremental learning of object detectors using a visual shape alphabet2006
- Semantic feature production norms for a large set of living and nonliving thingsBehavior Research Methods, 2005
- Cross-Generalization: Learning Novel Classes from a Single Example by Feature Replacement2005
- Recognition-by-components: A theory of human image understanding.Psychological Review, 1987
- Basic objects in natural categoriesCognitive Psychology, 1976