Skip navigation
Skip navigation

A Generalized Probabilistic Framework for Compact Codebook Creation

Liu, Lingqiao; Wang, Lei; Shen, Chunhua

Description

Compact and discriminative visual codebooks are preferred in many visual recognition tasks. In the literature, a few researchers have taken the approach of hierarchically merging visual words of a initial large-size code-book, but implemented this idea with different merging criteria. In this work, we show that by defining different class-conditional distribution function and parameter estimation method, these merging criteria can be unified under a single probabilistic framework. More...[Show more]

dc.contributor.authorLiu, Lingqiao
dc.contributor.authorWang, Lei
dc.contributor.authorShen, Chunhua
dc.coverage.spatialColorado Springs USA
dc.date.accessioned2015-12-10T23:11:10Z
dc.date.createdJune 21-23 2011
dc.identifier.isbn9781457703942
dc.identifier.urihttp://hdl.handle.net/1885/63703
dc.description.abstractCompact and discriminative visual codebooks are preferred in many visual recognition tasks. In the literature, a few researchers have taken the approach of hierarchically merging visual words of a initial large-size code-book, but implemented this idea with different merging criteria. In this work, we show that by defining different class-conditional distribution function and parameter estimation method, these merging criteria can be unified under a single probabilistic framework. More importantly, by adopting new distribution functions and/or parameter estimation methods, we can generalize this framework to produce a spectrum of novel merging criteria. Two of them are particularly focused in this work. For one criterion, we adopt the multinomial distribution to model each object class, and for the other criterion we propose a max-margin-based parameter estimation method. Both theoretical analysis and experimental study demonstrate the superior performance of the two new merging criteria and the general applicability of our probabilistic framework.
dc.publisherIEEE Computer Society
dc.relation.ispartofseriesIEEE Conference on Computer Vision and Pattern Recognition (CVPR 2011)
dc.sourceGraph connectivity in sparse subspace clustering
dc.subjectKeywords: Codebooks; Experimental studies; Large sizes; Multinomial distributions; Object class; Parameter estimation method; Probabilistic framework; Visual recognition; Visual word; Computer vision; Distribution functions; Estimation; Merging; Probability distrib
dc.titleA Generalized Probabilistic Framework for Compact Codebook Creation
dc.typeConference paper
local.description.notesImported from ARIES
local.description.refereedYes
dc.date.issued2011
local.identifier.absfor080104 - Computer Vision
local.identifier.ariespublicationu4334215xPUB838
local.type.statusPublished Version
local.contributor.affiliationLiu, Lingqiao, College of Engineering and Computer Science, ANU
local.contributor.affiliationWang, Lei, College of Engineering and Computer Science, ANU
local.contributor.affiliationShen, Chunhua, NICTA
local.description.embargo2037-12-31
local.bibliographicCitation.startpage1537
local.bibliographicCitation.lastpage1544
local.identifier.doi10.1109/CVPR.2011.5995628
local.identifier.absseo970109 - Expanding Knowledge in Engineering
dc.date.updated2016-02-24T11:03:26Z
local.identifier.scopusID2-s2.0-80052875474
CollectionsANU Research Publications

Download

File Description SizeFormat Image
01_Liu_A_Generalized_Probabilistic_2011.pdf186.9 kBAdobe PDF    Request a copy


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

Updated:  19 May 2020/ Responsible Officer:  University Librarian/ Page Contact:  Library Systems & Web Coordinator