Modeling spatial layout with fisher vectors for image categorization
- 1 November 2011
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- No. 15505499,p. 1487-1494
- https://doi.org/10.1109/iccv.2011.6126406
Abstract
We introduce an extension of bag-of-words image representations to encode spatial layout. Using the Fisher kernel framework we derive a representation that encodes the spatial mean and the variance of image regions associated with visual words. We extend this representation by using a Gaussian mixture model to encode spatial layout, and show that this model is related to a soft-assign version of the spatial pyramid representation. We also combine our representation of spatial layout with the use of Fisher kernels to encode the appearance of local features. Through an extensive experimental evaluation, we show that our representation yields state-of-the-art image categorization results, while being more compact than spatial pyramid representations. In particular, using Fisher kernels to encode both appearance and spatial layout results in an image representation that is computationally efficient, compact, and yields excellent performance while using linear classifiers.Keywords
This publication has 22 references indexed in Scilit:
- Towards a more discriminative and semantic visual vocabularyComputer Vision and Image Understanding, 2011
- Lost in quantization: Improving particular object retrieval in large scale image databasesPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Integrated feature selection and higher-order spatial feature extraction for object categorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2008
- Fisher Kernels on Visual Vocabularies for Image CategorizationPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Object retrieval with large vocabularies and fast spatial matchingPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Efficient Mining of Frequent and Distinctive Feature ConfigurationsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2007
- Scalable Recognition with a Vocabulary TreePublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Discriminative Object Class Models of Appearance and Shape by CorrelatonsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2006
- Facial expression recognition using fisher weight mapsPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2004
- Video Google: a text retrieval approach to object matching in videosPublished by Institute of Electrical and Electronics Engineers (IEEE) ,2003