schliessen

Filtern

 

Bibliotheken

Improving image annotation via ranking‐oriented neighbor search and learning‐based keyword propagation

Automatic image annotation plays a critical role in modern keyword‐based image retrieval systems. For this task, the nearest‐neighbor–based scheme works in two phases: first, it finds the most similar neighbors of a new image from the set of labeled images; then, it propagates the keywords associate... Full description

Journal Title: Journal of the Association for Information Science and Technology January 2015, Vol.66(1), pp.82-98
Main Author: Cui, Chaoran
Other Authors: Ma, Jun , Lian, Tao , Chen, Zhumin , Wang, Shuaiqiang
Format: Electronic Article Electronic Article
Language:
Subjects:
ID: ISSN: 2330-1635 ; E-ISSN: 2330-1643 ; DOI: 10.1002/asi.23163
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: wj10.1002/asi.23163
title: Improving image annotation via ranking‐oriented neighbor search and learning‐based keyword propagation
format: Article
creator:
  • Cui, Chaoran
  • Ma, Jun
  • Lian, Tao
  • Chen, Zhumin
  • Wang, Shuaiqiang
subjects:
  • Image Retrieval
  • Machine Learning
ispartof: Journal of the Association for Information Science and Technology, January 2015, Vol.66(1), pp.82-98
description: Automatic image annotation plays a critical role in modern keyword‐based image retrieval systems. For this task, the nearest‐neighbor–based scheme works in two phases: first, it finds the most similar neighbors of a new image from the set of labeled images; then, it propagates the keywords associated with the neighbors to the new image. In this article, we propose a novel approach for image annotation, which simultaneously improves both phases of the nearest‐neighbor–based scheme. In the phase of neighbor search, different from existing work discovering the nearest neighbors with the predicted distance, we introduce a ranking‐oriented neighbor search mechanism (RNSM), where the ordering of labeled images is optimized directly without going through the intermediate step of distance prediction. In the phase of keyword propagation, different from existing work using simple heuristic rules to select the propagated keywords, we present a learning‐based keyword propagation strategy (LKPS), where a scoring function is learned to evaluate the relevance of keywords based on their multiple relations with the nearest neighbors. Extensive experiments on the Corel 5K data set and the Flickr data set demonstrate the effectiveness of our approach.
language:
source:
identifier: ISSN: 2330-1635 ; E-ISSN: 2330-1643 ; DOI: 10.1002/asi.23163
fulltext: fulltext
issn:
  • 2330-1635
  • 23301635
  • 2330-1643
  • 23301643
url: Link


@attributes
ID492749887
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid10.1002/asi.23163
sourceidwj
recordidTN_wj10.1002/asi.23163
sourcesystemPC
pqid1651458814
galeid407650235
display
typearticle
titleImproving image annotation via ranking‐oriented neighbor search and learning‐based keyword propagation
creatorCui, Chaoran ; Ma, Jun ; Lian, Tao ; Chen, Zhumin ; Wang, Shuaiqiang
ispartofJournal of the Association for Information Science and Technology, January 2015, Vol.66(1), pp.82-98
identifier
subjectImage Retrieval ; Machine Learning
descriptionAutomatic image annotation plays a critical role in modern keyword‐based image retrieval systems. For this task, the nearest‐neighbor–based scheme works in two phases: first, it finds the most similar neighbors of a new image from the set of labeled images; then, it propagates the keywords associated with the neighbors to the new image. In this article, we propose a novel approach for image annotation, which simultaneously improves both phases of the nearest‐neighbor–based scheme. In the phase of neighbor search, different from existing work discovering the nearest neighbors with the predicted distance, we introduce a ranking‐oriented neighbor search mechanism (RNSM), where the ordering of labeled images is optimized directly without going through the intermediate step of distance prediction. In the phase of keyword propagation, different from existing work using simple heuristic rules to select the propagated keywords, we present a learning‐based keyword propagation strategy (LKPS), where a scoring function is learned to evaluate the relevance of keywords based on their multiple relations with the nearest neighbors. Extensive experiments on the Corel 5K data set and the Flickr data set demonstrate the effectiveness of our approach.
source
version6
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
search
creatorcontrib
0Cui, Chaoran
1Ma, Jun
2Lian, Tao
3Chen, Zhumin
4Wang, Shuaiqiang
titleImproving image annotation via ranking‐oriented neighbor search and learning‐based keyword propagation
descriptionAutomatic image annotation plays a critical role in modern keyword‐based image retrieval systems. For this task, the nearest‐neighbor–based scheme works in two phases: first, it finds the most similar neighbors of a new image from the set of labeled images; then, it propagates the keywords associated with the neighbors to the new image. In this article, we propose a novel approach for image annotation, which simultaneously improves both phases of the nearest‐neighbor–based scheme. In the phase of neighbor search, different from existing work discovering the nearest neighbors with the predicted distance, we introduce a ranking‐oriented neighbor search mechanism (RNSM), where the ordering of labeled images is optimized directly without going through the intermediate step of distance prediction. In the phase of keyword propagation, different from existing work using simple heuristic rules to select the propagated keywords, we present a learning‐based keyword propagation strategy (LKPS), where a scoring function is learned to evaluate the relevance of keywords based on their multiple relations with the nearest neighbors. Extensive experiments on the Corel 5K data set and the Flickr data set demonstrate the effectiveness of our approach.
subject
0Image Retrieval
1Machine Learning
general
010.1002/asi.23163
1Wiley Online Library
sourceidwj
recordidwj10.1002/asi.23163
issn
02330-1635
123301635
22330-1643
323301643
rsrctypearticle
creationdate2015
addtitle
0Journal of the Association for Information Science and Technology
1J Assn Inf Sci Tec
searchscope
0wj
1wiley
scope
0wj
1wiley
lsr30VSR-Enriched:[galeid, pages, pqid]
sort
titleImproving image annotation via ranking‐oriented neighbor search and learning‐based keyword propagation
authorCui, Chaoran ; Ma, Jun ; Lian, Tao ; Chen, Zhumin ; Wang, Shuaiqiang
creationdate20150100
facets
frbrgroupid8678976677370947993
frbrtype5
creationdate2015
topic
0Image Retrieval
1Machine Learning
collectionWiley Online Library
prefilterarticles
rsrctypearticles
creatorcontrib
0Cui, Chaoran
1Ma, Jun
2Lian, Tao
3Chen, Zhumin
4Wang, Shuaiqiang
jtitleJournal of the Association for Information Science and Technology
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Cui
1Ma
2Lian
3Chen
4Wang
aufirst
0Chaoran
1Jun
2Tao
3Zhumin
4Shuaiqiang
au
0Cui, Chaoran
1Ma, Jun
2Lian, Tao
3Chen, Zhumin
4Wang, Shuaiqiang
atitleImproving image annotation via ranking‐oriented neighbor search and learning‐based keyword propagation
jtitleJournal of the Association for Information Science and Technology
risdate201501
volume66
issue1
spage82
epage98
issn2330-1635
eissn2330-1643
genrearticle
ristypeJOUR
abstractAutomatic image annotation plays a critical role in modern keyword‐based image retrieval systems. For this task, the nearest‐neighbor–based scheme works in two phases: first, it finds the most similar neighbors of a new image from the set of labeled images; then, it propagates the keywords associated with the neighbors to the new image. In this article, we propose a novel approach for image annotation, which simultaneously improves both phases of the nearest‐neighbor–based scheme. In the phase of neighbor search, different from existing work discovering the nearest neighbors with the predicted distance, we introduce a ranking‐oriented neighbor search mechanism (RNSM), where the ordering of labeled images is optimized directly without going through the intermediate step of distance prediction. In the phase of keyword propagation, different from existing work using simple heuristic rules to select the propagated keywords, we present a learning‐based keyword propagation strategy (LKPS), where a scoring function is learned to evaluate the relevance of keywords based on their multiple relations with the nearest neighbors. Extensive experiments on the Corel 5K data set and the Flickr data set demonstrate the effectiveness of our approach.
doi10.1002/asi.23163
pages82-98
date2015-01