Evaluating Gaussian like image representations over local features
Journal
IEEE International Conference on Multimedia and Expo
Pages
979-984
Date Issued
2012
Author(s)
Abstract
Recently, several gaussian like image representations are proposed as an alternative of the bag-of-word representation over local features. These representations are proposed to overcome the quantization error problem faced in bag-of-word representation. They are shown to be effective in different applications, the Extended Hierarchical Gaussianization reached excellent performance using single feature in VOC2009, Vector of Locally Aggregated Descriptors and Fisher Kernel reached excellent performance using only signature like representation on Holiday dataset. Despite their success and similarity, no comparative study about these representations has been made. In this paper, we perform a systematic comparison about three emerging different gaussian like representations: Extended Hierarchical Gaussianization, Fisher Kernel and Vector of Locally Aggregated Descriptors. We evaluate the performance and the influence of feature and parameters of these representations on Holiday and CC-Web-Video datasets, and several important properties about these representations have been observed during our investigation. This study provides better understanding about these gaussian like image representations that are believed to be promising in various applications. ? 2012 IEEE.
Subjects
Extended Hierarchical Gaussianization; Fisher Kernel; Gaussian Mixture Model; Image Representation; Local Feature; Performance Comparison; Vector of Locally Aggregated Descriptors
Type
conference paper