A multimodal multimedia retrieval model based on pLSA

Yu Zhang, Ye Yuan, Guoren Wang

Research output: Chapter in Book/Report/Conference proceedingConference contributionpeer-review

1 Citation (Scopus)

Abstract

In this paper, we propose a multimodal multimedia retrieval model based on probabilistic Latent Semantic analysis (pLSA) to achieve multimodal retrieval. Firstly, We employ pLSA, to respectively simulate the generative processes of texts and images in the same documents. Then we employ the multivariate linear regression method to analyze the correlation between representations of texts and images and use the ordinary least squares (OLS) method to obtain the estimation of the regression matrix that can be used to transform between textual and visual modal data. Extensive experiments results demonstrate the effectiveness and efficiency of the proposed model.

Original languageEnglish
Title of host publicationProceedings - 11th Web Information System and Application Conference, WISA 2014
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages33-36
Number of pages4
ISBN (Electronic)9781479957262
DOIs
Publication statusPublished - 10 Mar 2014
Externally publishedYes
Event11th Web Information System and Application Conference, WISA 2014 - Tianjin, China
Duration: 12 Sept 201414 Sept 2014

Publication series

NameProceedings - 11th Web Information System and Application Conference, WISA 2014

Conference

Conference11th Web Information System and Application Conference, WISA 2014
Country/TerritoryChina
CityTianjin
Period12/09/1414/09/14

Keywords

  • Multimodal
  • Retrieval
  • pLSA

Fingerprint

Dive into the research topics of 'A multimodal multimedia retrieval model based on pLSA'. Together they form a unique fingerprint.

Cite this