schliessen

Filtern

 

Bibliotheken

A novel cross-media layered semantic mining model

This paper presents a cross-media semantic mining model (CSMM) based on object semantic. This model obtains object-level semantic information in terms of maximum probability principle. Then semantic templates are trained and constructed with STTS (Semantic Template Training System), which are taken... Full description

Journal Title: Wuhan University Journal of Natural Sciences 2008, Vol.13(1), pp.21-26
Main Author: Zeng, Cheng
Other Authors: Cao, Jiaheng , Peng, Zhiyong , Wang, Ke , Wang, Hui
Format: Electronic Article Electronic Article
Language: English
Subjects:
ID: ISSN: 1007-1202 ; E-ISSN: 1993-4998 ; DOI: 10.1007/s11859-008-0105-5
Link: http://dx.doi.org/10.1007/s11859-008-0105-5
Zum Text:
SendSend as email Add to Book BagAdd to Book Bag
Staff View
recordid: springer_jour10.1007/s11859-008-0105-5
title: A novel cross-media layered semantic mining model
format: Article
creator:
  • Zeng, Cheng
  • Cao, Jiaheng
  • Peng, Zhiyong
  • Wang, Ke
  • Wang, Hui
subjects:
  • cross-media semantic mining model
  • object semantic
  • semantic template
  • semantic template training system
  • metadata
ispartof: Wuhan University Journal of Natural Sciences, 2008, Vol.13(1), pp.21-26
description: This paper presents a cross-media semantic mining model (CSMM) based on object semantic. This model obtains object-level semantic information in terms of maximum probability principle. Then semantic templates are trained and constructed with STTS (Semantic Template Training System), which are taken as the bridge to realize the transition from various low-level media feature to object semantic. Furthermore, we put forward a kind of double layers metadata structure to efficaciously store and manage mined low-level feature and high-level semantic. This model has broad application in lots of domains such as intelligent retrieval engine, medical diagnoses, multimedia design and so on.
language: eng
source:
identifier: ISSN: 1007-1202 ; E-ISSN: 1993-4998 ; DOI: 10.1007/s11859-008-0105-5
fulltext: fulltext
issn:
  • 1993-4998
  • 19934998
  • 1007-1202
  • 10071202
url: Link


@attributes
ID1340423689
RANK0.07
NO1
SEARCH_ENGINEprimo_central_multiple_fe
SEARCH_ENGINE_TYPEPrimo Central Search Engine
LOCALfalse
PrimoNMBib
record
control
sourcerecordid10.1007/s11859-008-0105-5
sourceidspringer_jour
recordidTN_springer_jour10.1007/s11859-008-0105-5
sourcesystemPC
pqid33073344
galeid206237323
display
typearticle
titleA novel cross-media layered semantic mining model
creatorZeng, Cheng ; Cao, Jiaheng ; Peng, Zhiyong ; Wang, Ke ; Wang, Hui
ispartofWuhan University Journal of Natural Sciences, 2008, Vol.13(1), pp.21-26
identifier
subjectcross-media semantic mining model ; object semantic ; semantic template ; semantic template training system ; metadata
descriptionThis paper presents a cross-media semantic mining model (CSMM) based on object semantic. This model obtains object-level semantic information in terms of maximum probability principle. Then semantic templates are trained and constructed with STTS (Semantic Template Training System), which are taken as the bridge to realize the transition from various low-level media feature to object semantic. Furthermore, we put forward a kind of double layers metadata structure to efficaciously store and manage mined low-level feature and high-level semantic. This model has broad application in lots of domains such as intelligent retrieval engine, medical diagnoses, multimedia design and so on.
languageeng
source
version5
lds50peer_reviewed
links
openurl$$Topenurl_article
openurlfulltext$$Topenurlfull_article
backlink$$Uhttp://dx.doi.org/10.1007/s11859-008-0105-5$$EView_full_text_in_Springer_(Subscribers_only)
search
creatorcontrib
0Zeng, Cheng
1Cao, Jiaheng
2Peng, Zhiyong
3Wang, Ke
4Wang, Hui
titleA novel cross-media layered semantic mining model
descriptionThis paper presents a cross-media semantic mining model (CSMM) based on object semantic. This model obtains object-level semantic information in terms of maximum probability principle. Then semantic templates are trained and constructed with STTS (Semantic Template Training System), which are taken as the bridge to realize the transition from various low-level media feature to object semantic. Furthermore, we put forward a kind of double layers metadata structure to efficaciously store and manage mined low-level feature and high-level semantic. This model has broad application in lots of domains such as intelligent retrieval engine, medical diagnoses, multimedia design and so on.
subject
0cross-media semantic mining model
1object semantic
2semantic template
3semantic template training system
4metadata
general
010.1007/s11859-008-0105-5
1English
2Springer Science & Business Media B.V.
3SpringerLink
sourceidspringer_jour
recordidspringer_jour10.1007/s11859-008-0105-5
issn
01993-4998
119934998
21007-1202
310071202
rsrctypearticle
creationdate2008
addtitle
0Wuhan University Journal of Natural Sciences
1Wuhan Univ. J. Nat. Sci.
searchscopespringer_journals_complete
scopespringer_journals_complete
lsr30VSR-Enriched:[pqid, galeid, pages]
sort
titleA novel cross-media layered semantic mining model
authorZeng, Cheng ; Cao, Jiaheng ; Peng, Zhiyong ; Wang, Ke ; Wang, Hui
creationdate20080200
facets
frbrgroupid5815142397047995452
frbrtype5
languageeng
creationdate2008
topic
0Cross-Media Semantic Mining Model
1Object Semantic
2Semantic Template
3Semantic Template Training System
4Metadata
collectionSpringerLink
prefilterarticles
rsrctypearticles
creatorcontrib
0Zeng, Cheng
1Cao, Jiaheng
2Peng, Zhiyong
3Wang, Ke
4Wang, Hui
jtitleWuhan University Journal Of Natural Sciences
toplevelpeer_reviewed
delivery
delcategoryRemote Search Resource
fulltextfulltext
addata
aulast
0Zeng
1Cao
2Peng
3Wang
aufirst
0Cheng
1Jiaheng
2Zhiyong
3Ke
4Hui
au
0Zeng, Cheng
1Cao, Jiaheng
2Peng, Zhiyong
3Wang, Ke
4Wang, Hui
atitleA novel cross-media layered semantic mining model
jtitleWuhan University Journal of Natural Sciences
stitleWuhan Univ. J. Nat. Sci.
risdate200802
volume13
issue1
spage21
epage26
issn1007-1202
eissn1993-4998
genrearticle
ristypeJOUR
abstractThis paper presents a cross-media semantic mining model (CSMM) based on object semantic. This model obtains object-level semantic information in terms of maximum probability principle. Then semantic templates are trained and constructed with STTS (Semantic Template Training System), which are taken as the bridge to realize the transition from various low-level media feature to object semantic. Furthermore, we put forward a kind of double layers metadata structure to efficaciously store and manage mined low-level feature and high-level semantic. This model has broad application in lots of domains such as intelligent retrieval engine, medical diagnoses, multimedia design and so on.
copHeidelberg
pubWuhan University
doi10.1007/s11859-008-0105-5
pages21-26
date2008-02