DocumentCode :
3297268
Title :
Evaluating Gaussian Like Image Representations over Local Features
Author :
Su, Yu-Chuan ; Wu, Guan-Long ; Chiu, Tzu-Hsuan ; Hsu, Winston H. ; Chang, Kuo-Wei
Author_Institution :
Dept. of Comput. Sci. & Inf. Eng., Nat. Taiwan Univ., Taipei, Taiwan
fYear :
2012
fDate :
9-13 July 2012
Firstpage :
979
Lastpage :
984
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.
Keywords :
Gaussian processes; feature extraction; image representation; quantisation (signal); Gaussian like image representation; Holiday datasets; Web video datasets; bag-of-word representation; extended hierarchical Gaussianization; feature extraction; fisher kernel; locally aggregated descriptor vector; quantization error problem; signature like representation; Feature extraction; Image representation; Kernel; Upper bound; Vectors; Visualization; Vocabulary; Extended Hierarchical Gaussianization; Fisher Kernel; Gaussian Mixture Model; Image Representation; Local Feature; Performance Comparison; Vector of Locally Aggregated Descriptors;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Multimedia and Expo (ICME), 2012 IEEE International Conference on
Conference_Location :
Melbourne, VIC
ISSN :
1945-7871
Print_ISBN :
978-1-4673-1659-0
Type :
conf
DOI :
10.1109/ICME.2012.23
Filename :
6298530
Link To Document :
بازگشت