Geotag propagation in social networks based on user trust model

Ivan Ivanov, Peter Vajda, Jong-Seok Lee, Lutz Goldmann, Touradj Ebrahimi

Research output: Contribution to journalArticle

16 Citations (Scopus)

Abstract

In the past few years sharing photos within social networks has become very popular. In order to make these huge collections easier to explore, images are usually tagged with representative keywords such as persons, events, objects, and locations. In order to speed up the time consuming tag annotation process, tags can be propagated based on the similarity between image content and context. In this paper, we present a system for efficient geotag propagation based on a combination of object duplicate detection and user trust modeling. The geotags are propagated by training a graph based object model for each of the landmarks on a small tagged image set and finding its duplicates within a large untagged image set. Based on the established correspondences between these two image sets and the reliability of the user, tags are propagated from the tagged to the untagged images. The user trust modeling reduces the risk of propagating wrong tags caused by spamming or faulty annotation. The effectiveness of the proposed method is demonstrated through a set of experiments on an image database containing various landmarks.

Original languageEnglish
Pages (from-to)155-177
Number of pages23
JournalMultimedia Tools and Applications
Volume56
Issue number1
DOIs
Publication statusPublished - 2012 Jan 1

Fingerprint

Spamming
Experiments
Object detection

All Science Journal Classification (ASJC) codes

  • Software
  • Media Technology
  • Hardware and Architecture
  • Computer Networks and Communications

Cite this

Ivanov, Ivan ; Vajda, Peter ; Lee, Jong-Seok ; Goldmann, Lutz ; Ebrahimi, Touradj. / Geotag propagation in social networks based on user trust model. In: Multimedia Tools and Applications. 2012 ; Vol. 56, No. 1. pp. 155-177.
@article{e53ca2cd53ed446dab65c2cadd708555,
title = "Geotag propagation in social networks based on user trust model",
abstract = "In the past few years sharing photos within social networks has become very popular. In order to make these huge collections easier to explore, images are usually tagged with representative keywords such as persons, events, objects, and locations. In order to speed up the time consuming tag annotation process, tags can be propagated based on the similarity between image content and context. In this paper, we present a system for efficient geotag propagation based on a combination of object duplicate detection and user trust modeling. The geotags are propagated by training a graph based object model for each of the landmarks on a small tagged image set and finding its duplicates within a large untagged image set. Based on the established correspondences between these two image sets and the reliability of the user, tags are propagated from the tagged to the untagged images. The user trust modeling reduces the risk of propagating wrong tags caused by spamming or faulty annotation. The effectiveness of the proposed method is demonstrated through a set of experiments on an image database containing various landmarks.",
author = "Ivan Ivanov and Peter Vajda and Jong-Seok Lee and Lutz Goldmann and Touradj Ebrahimi",
year = "2012",
month = "1",
day = "1",
doi = "10.1007/s11042-010-0570-7",
language = "English",
volume = "56",
pages = "155--177",
journal = "Multimedia Tools and Applications",
issn = "1380-7501",
publisher = "Springer Netherlands",
number = "1",

}

Geotag propagation in social networks based on user trust model. / Ivanov, Ivan; Vajda, Peter; Lee, Jong-Seok; Goldmann, Lutz; Ebrahimi, Touradj.

In: Multimedia Tools and Applications, Vol. 56, No. 1, 01.01.2012, p. 155-177.

Research output: Contribution to journalArticle

TY - JOUR

T1 - Geotag propagation in social networks based on user trust model

AU - Ivanov, Ivan

AU - Vajda, Peter

AU - Lee, Jong-Seok

AU - Goldmann, Lutz

AU - Ebrahimi, Touradj

PY - 2012/1/1

Y1 - 2012/1/1

N2 - In the past few years sharing photos within social networks has become very popular. In order to make these huge collections easier to explore, images are usually tagged with representative keywords such as persons, events, objects, and locations. In order to speed up the time consuming tag annotation process, tags can be propagated based on the similarity between image content and context. In this paper, we present a system for efficient geotag propagation based on a combination of object duplicate detection and user trust modeling. The geotags are propagated by training a graph based object model for each of the landmarks on a small tagged image set and finding its duplicates within a large untagged image set. Based on the established correspondences between these two image sets and the reliability of the user, tags are propagated from the tagged to the untagged images. The user trust modeling reduces the risk of propagating wrong tags caused by spamming or faulty annotation. The effectiveness of the proposed method is demonstrated through a set of experiments on an image database containing various landmarks.

AB - In the past few years sharing photos within social networks has become very popular. In order to make these huge collections easier to explore, images are usually tagged with representative keywords such as persons, events, objects, and locations. In order to speed up the time consuming tag annotation process, tags can be propagated based on the similarity between image content and context. In this paper, we present a system for efficient geotag propagation based on a combination of object duplicate detection and user trust modeling. The geotags are propagated by training a graph based object model for each of the landmarks on a small tagged image set and finding its duplicates within a large untagged image set. Based on the established correspondences between these two image sets and the reliability of the user, tags are propagated from the tagged to the untagged images. The user trust modeling reduces the risk of propagating wrong tags caused by spamming or faulty annotation. The effectiveness of the proposed method is demonstrated through a set of experiments on an image database containing various landmarks.

UR - http://www.scopus.com/inward/record.url?scp=84857359557&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84857359557&partnerID=8YFLogxK

U2 - 10.1007/s11042-010-0570-7

DO - 10.1007/s11042-010-0570-7

M3 - Article

VL - 56

SP - 155

EP - 177

JO - Multimedia Tools and Applications

JF - Multimedia Tools and Applications

SN - 1380-7501

IS - 1

ER -