The effects of heterogeneous information combination on large scale social image search

Zhiyong Cheng; Jing Ren; Jialie Shen; Haiyan Miao

doi:10.1145/2043674.2043686

The effects of heterogeneous information combination on large scale social image search

Zhiyong Cheng, Jing Ren, Jialie Shen, Haiyan Miao

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

Abstract

This paper documents a comprehensive empirical study of the effects of heterogeneous information combination on large scale social image search. Our goal is to investigate how various kinds of information source can contribute the improvement of the retrieval effectiveness. In particular, a linear combination has been applied to merge search results from search module based on textual and visual features. Also, we propose different weighting schemes to integrate different kinds of query evidences in a nonlinear way. A series of experiments have been conducted using two large scale social image collections. Empirical results suggest that the system based on textual features yields much more effective and reliable results comparing to one using visual information. Further, the combination of two information sources can consistently enhance the final accuracy.

Original language	English
Title of host publication	ICIMCS 2011 - 3rd International Conference on Internet Multimedia Computing and Service, Proceedings
Publisher	Association for Computing Machinery (ACM)
Pages	39-42
Number of pages	4
ISBN (Print)	9781450309189
DOIs	https://doi.org/10.1145/2043674.2043686
Publication status	Published - 2011
Externally published	Yes
Event	3rd International Conference on Internet Multimedia Computing and Service, ICIMCS 2011 - Chengdu, China Duration: 5 Aug 2011 → 7 Aug 2011

Conference

Conference	3rd International Conference on Internet Multimedia Computing and Service, ICIMCS 2011
Country/Territory	China
City	Chengdu
Period	5/08/11 → 7/08/11

Access to Document

10.1145/2043674.2043686

Cite this

@inproceedings{8ef5edd8aa794cb393c12f2682838818,

title = "The effects of heterogeneous information combination on large scale social image search",

abstract = "This paper documents a comprehensive empirical study of the effects of heterogeneous information combination on large scale social image search. Our goal is to investigate how various kinds of information source can contribute the improvement of the retrieval effectiveness. In particular, a linear combination has been applied to merge search results from search module based on textual and visual features. Also, we propose different weighting schemes to integrate different kinds of query evidences in a nonlinear way. A series of experiments have been conducted using two large scale social image collections. Empirical results suggest that the system based on textual features yields much more effective and reliable results comparing to one using visual information. Further, the combination of two information sources can consistently enhance the final accuracy.",

keywords = "fundamental study, heterogeneous information, social image",

author = "Zhiyong Cheng and Jing Ren and Jialie Shen and Haiyan Miao",

year = "2011",

doi = "10.1145/2043674.2043686",

language = "English",

isbn = "9781450309189",

pages = "39--42",

booktitle = "ICIMCS 2011 - 3rd International Conference on Internet Multimedia Computing and Service, Proceedings",

publisher = "Association for Computing Machinery (ACM)",

address = "United States",

note = "3rd International Conference on Internet Multimedia Computing and Service, ICIMCS 2011 ; Conference date: 05-08-2011 Through 07-08-2011",

}

Cheng, Z, Ren, J, Shen, J & Miao, H 2011, The effects of heterogeneous information combination on large scale social image search. in ICIMCS 2011 - 3rd International Conference on Internet Multimedia Computing and Service, Proceedings. Association for Computing Machinery (ACM), pp. 39-42, 3rd International Conference on Internet Multimedia Computing and Service, ICIMCS 2011, Chengdu, China, 5/08/11. https://doi.org/10.1145/2043674.2043686

The effects of heterogeneous information combination on large scale social image search. / Cheng, Zhiyong; Ren, Jing; Shen, Jialie; Miao, Haiyan.

ICIMCS 2011 - 3rd International Conference on Internet Multimedia Computing and Service, Proceedings. Association for Computing Machinery (ACM), 2011. p. 39-42.

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper published in Proceedings › peer-review

TY - GEN

T1 - The effects of heterogeneous information combination on large scale social image search

AU - Cheng, Zhiyong

AU - Ren, Jing

AU - Shen, Jialie

AU - Miao, Haiyan

PY - 2011

Y1 - 2011

N2 - This paper documents a comprehensive empirical study of the effects of heterogeneous information combination on large scale social image search. Our goal is to investigate how various kinds of information source can contribute the improvement of the retrieval effectiveness. In particular, a linear combination has been applied to merge search results from search module based on textual and visual features. Also, we propose different weighting schemes to integrate different kinds of query evidences in a nonlinear way. A series of experiments have been conducted using two large scale social image collections. Empirical results suggest that the system based on textual features yields much more effective and reliable results comparing to one using visual information. Further, the combination of two information sources can consistently enhance the final accuracy.

AB - This paper documents a comprehensive empirical study of the effects of heterogeneous information combination on large scale social image search. Our goal is to investigate how various kinds of information source can contribute the improvement of the retrieval effectiveness. In particular, a linear combination has been applied to merge search results from search module based on textual and visual features. Also, we propose different weighting schemes to integrate different kinds of query evidences in a nonlinear way. A series of experiments have been conducted using two large scale social image collections. Empirical results suggest that the system based on textual features yields much more effective and reliable results comparing to one using visual information. Further, the combination of two information sources can consistently enhance the final accuracy.

KW - fundamental study

KW - heterogeneous information

KW - social image

UR - http://www.scopus.com/inward/record.url?scp=80755143963&partnerID=8YFLogxK

UR - https://dl.acm.org/citation.cfm?id=2043674&picked=prox

U2 - 10.1145/2043674.2043686

DO - 10.1145/2043674.2043686

M3 - Conference Paper published in Proceedings

AN - SCOPUS:80755143963

SN - 9781450309189

SP - 39

EP - 42

BT - ICIMCS 2011 - 3rd International Conference on Internet Multimedia Computing and Service, Proceedings

PB - Association for Computing Machinery (ACM)

T2 - 3rd International Conference on Internet Multimedia Computing and Service, ICIMCS 2011

Y2 - 5 August 2011 through 7 August 2011

ER -

The effects of heterogeneous information combination on large scale social image search

Abstract

Conference

Access to Document

Other files and links

Fingerprint

Cite this