Beyond Bags of Features: Spatial Pyramid Matching for Recognizing Natural Scene Categories
Top Cited Papers
- 17 June 2006
- proceedings article
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- Vol. 2, 2169-2178
- https://doi.org/10.1109/cvpr.2006.68
Abstract
This paper presents a method for recognizing scene categories based on approximate global geometric correspondence. This technique works by partitioning the image into increasingly fine sub-regions and computing histograms of local features found inside each sub-region. The resulting "spatial pyramid" is a simple and computationally efficient extension of an orderless bag-of-features image representation, and it shows significantly improved performance on challenging scene categorization tasks. Specifically, our proposed method exceeds the state of the art on the Caltech-101 database and achieves high accuracy on a large database of fifteen natural scene categories. The spatial pyramid framework also offers insights into the success of several recently proposed image descriptions, including Torralba's "gist" and Lowe's SIFT descriptors.Keywords
This publication has 19 references indexed in Scilit:
- A maximum entropy framework for part-based texture and object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Modeling scenes with local descriptors and latent aspectsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Discovering objects and their location in imagesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2005
- Context-based vision system for place and object recognitionPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Recognition with local features: the kernel recipePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003
- Indoor-outdoor image classificationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2002
- Modeling the Shape of the Scene: A Holistic Representation of the Spatial EnvelopeInternational Journal of Computer Vision, 2001
- Towards a Computational Model for Object Recognition in IT CortexPublished by Springer Nature ,2000
- Recognition without Correspondence using Multidimensional Receptive Field HistogramsInternational Journal of Computer Vision, 2000
- Color indexingInternational Journal of Computer Vision, 1991