The effects of multiple query evidences on social image retrieval

Zhiyong Cheng, Jialie Shen, Haiyan Miao

Research output: Contribution to journalArticleResearchpeer-review

Abstract

System performance assessment and comparison are fundamental for large-scale image search engine development. This article documents a set of comprehensive empirical studies to explore the effects of multiple query evidences on large-scale social image search. The search performance based on the social tags, different kinds of visual features and their combinations are systematically studied and analyzed. To quantify the visual query complexity, a novel quantitative metric is proposed and applied to assess the influences of different visual queries based on their complexity levels. Besides, we also study the effects of automatic text query expansion with social tags using a pseudo relevance feedback method on the retrieval performance. Our analysis of experimental results shows a few key research findings: (1) social tag-based retrieval methods can achieve much better results than content-based retrieval methods; (2) a combination of textual and visual features can significantly and consistently improve the search performance; (3) the complexity of image queries has a strong correlation with retrieval results’ quality—more complex queries lead to poorer search effectiveness; and (4) query expansion based on social tags frequently causes search topic drift and consequently leads to performance degradation.

Original languageEnglish
Pages (from-to)509-523
Number of pages15
JournalMultimedia Systems
Volume22
Issue number4
DOIs
Publication statusPublished - 1 Jul 2016
Externally publishedYes

Fingerprint

Image retrieval
Content based retrieval
Engines
Feedback
Degradation

Cite this

Cheng, Zhiyong ; Shen, Jialie ; Miao, Haiyan. / The effects of multiple query evidences on social image retrieval. In: Multimedia Systems. 2016 ; Vol. 22, No. 4. pp. 509-523.
@article{498809a31ba84ec69f1a854d980d37b9,
title = "The effects of multiple query evidences on social image retrieval",
abstract = "System performance assessment and comparison are fundamental for large-scale image search engine development. This article documents a set of comprehensive empirical studies to explore the effects of multiple query evidences on large-scale social image search. The search performance based on the social tags, different kinds of visual features and their combinations are systematically studied and analyzed. To quantify the visual query complexity, a novel quantitative metric is proposed and applied to assess the influences of different visual queries based on their complexity levels. Besides, we also study the effects of automatic text query expansion with social tags using a pseudo relevance feedback method on the retrieval performance. Our analysis of experimental results shows a few key research findings: (1) social tag-based retrieval methods can achieve much better results than content-based retrieval methods; (2) a combination of textual and visual features can significantly and consistently improve the search performance; (3) the complexity of image queries has a strong correlation with retrieval results’ quality—more complex queries lead to poorer search effectiveness; and (4) query expansion based on social tags frequently causes search topic drift and consequently leads to performance degradation.",
keywords = "Evaluation, Experimentation, Performance, Query evidence, Social image retrieval",
author = "Zhiyong Cheng and Jialie Shen and Haiyan Miao",
year = "2016",
month = "7",
day = "1",
doi = "10.1007/s00530-014-0432-7",
language = "English",
volume = "22",
pages = "509--523",
journal = "Multimedia Systems",
issn = "0942-4962",
publisher = "Springer-Verlag London Ltd.",
number = "4",

}

The effects of multiple query evidences on social image retrieval. / Cheng, Zhiyong; Shen, Jialie; Miao, Haiyan.

In: Multimedia Systems, Vol. 22, No. 4, 01.07.2016, p. 509-523.

Research output: Contribution to journalArticleResearchpeer-review

TY - JOUR

T1 - The effects of multiple query evidences on social image retrieval

AU - Cheng, Zhiyong

AU - Shen, Jialie

AU - Miao, Haiyan

PY - 2016/7/1

Y1 - 2016/7/1

N2 - System performance assessment and comparison are fundamental for large-scale image search engine development. This article documents a set of comprehensive empirical studies to explore the effects of multiple query evidences on large-scale social image search. The search performance based on the social tags, different kinds of visual features and their combinations are systematically studied and analyzed. To quantify the visual query complexity, a novel quantitative metric is proposed and applied to assess the influences of different visual queries based on their complexity levels. Besides, we also study the effects of automatic text query expansion with social tags using a pseudo relevance feedback method on the retrieval performance. Our analysis of experimental results shows a few key research findings: (1) social tag-based retrieval methods can achieve much better results than content-based retrieval methods; (2) a combination of textual and visual features can significantly and consistently improve the search performance; (3) the complexity of image queries has a strong correlation with retrieval results’ quality—more complex queries lead to poorer search effectiveness; and (4) query expansion based on social tags frequently causes search topic drift and consequently leads to performance degradation.

AB - System performance assessment and comparison are fundamental for large-scale image search engine development. This article documents a set of comprehensive empirical studies to explore the effects of multiple query evidences on large-scale social image search. The search performance based on the social tags, different kinds of visual features and their combinations are systematically studied and analyzed. To quantify the visual query complexity, a novel quantitative metric is proposed and applied to assess the influences of different visual queries based on their complexity levels. Besides, we also study the effects of automatic text query expansion with social tags using a pseudo relevance feedback method on the retrieval performance. Our analysis of experimental results shows a few key research findings: (1) social tag-based retrieval methods can achieve much better results than content-based retrieval methods; (2) a combination of textual and visual features can significantly and consistently improve the search performance; (3) the complexity of image queries has a strong correlation with retrieval results’ quality—more complex queries lead to poorer search effectiveness; and (4) query expansion based on social tags frequently causes search topic drift and consequently leads to performance degradation.

KW - Evaluation

KW - Experimentation

KW - Performance

KW - Query evidence

KW - Social image retrieval

UR - http://www.scopus.com/inward/record.url?scp=84918504620&partnerID=8YFLogxK

U2 - 10.1007/s00530-014-0432-7

DO - 10.1007/s00530-014-0432-7

M3 - Article

VL - 22

SP - 509

EP - 523

JO - Multimedia Systems

JF - Multimedia Systems

SN - 0942-4962

IS - 4

ER -