Please use this identifier to cite or link to this item: http://hdl.handle.net/2440/103133
Citations
Scopus Web of Science® Altmetric
?
?
Type: Journal article
Title: A generalized probabilistic framework for compact codebook creation
Author: Liu, L.
Wang, L.
Shen, C.
Citation: IEEE Transactions on Pattern Analysis and Machine Intelligence, 2016; 38(2):224-237
Publisher: Institute of Electrical and Electronics Engineers (IEEE)
Issue Date: 2016
ISSN: 0162-8828
2160-9292
Statement of
Responsibility: 
Lingqiao Liu, Lei Wang and Chunhua Shen
Abstract: Compact and discriminative visual codebooks are preferred in many visual recognition tasks. In the literature, a number of works have taken the approach of hierarchically merging visual words of an initial large-sized codebook, but implemented this approach with different merging criteria. In this work, we propose a single probabilistic framework to unify these merging criteria, by identifying two key factors: the function used to model the class-conditional distribution and the method used to estimate the distribution parameters. More importantly, by adopting new distribution functions and/or parameter estimation methods, our framework can readily produce a spectrum of novel merging criteria. Three of them are specifically discussed in this paper. For the first criterion, we adopt the multinomial distribution with the Bayesian method; For the second criterion, we integrate the Gaussian distribution with maximum likelihood parameter estimation. For the third criterion, which shows the best merging performance, we propose a max-margin-based parameter estimation method and apply it with the multinomial distribution. Extensive experimental study is conducted to systematically analyze the performance of the above three criteria and compare them with existing ones. As demonstrated, the best criterion within our framework achieves the overall best merging performance among the compared merging criteria developed in the literature.
Keywords: Merging; visualization; histograms; parameter estimation; probabilistic logic; Bayes methods; training
Rights: © 2015 IEEE. Personal use is permitted, but republication/redistribution requires IEEE permission.
RMID: 0030047803
DOI: 10.1109/TPAMI.2015.2441069
Grant ID: http://purl.org/au-research/grants/arc/LP0991757
http://purl.org/au-research/grants/arc/FT120100969
Appears in Collections:Computer Science publications

Files in This Item:
File Description SizeFormat 
RA_hdl_103133.pdfRestricted Access835.61 kBAdobe PDFView/Open


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.