Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search

We introduce an approach to image retrieval and auto-tagging that leverages the implicit information about object importance conveyed by the list of keyword tags a person supplies for an image. We propose an unsupervised learning procedure based on Kernel Canonical Correlation Analysis that discover...

Celý popis

Uložené v:

Podrobná bibliografia
Vydané v:	International journal of computer vision Ročník 100; číslo 2; s. 134 - 153
Hlavní autori:	Hwang, Sung Ju, Grauman, Kristen
Médium:	Journal Article
Jazyk:	English
Vydavateľské údaje:	Boston Springer US 01.11.2012 Springer Springer Nature B.V
Predmet:	Analysis Artificial Intelligence Computer Imaging Computer Science Correlation analysis Experiments Human subjects Image Processing and Computer Vision Image retrieval Information management Information retrieval International Keywords Learning Learning strategies Pattern Recognition Pattern Recognition and Graphics Perceptions Queries Semantics Studies Vision Vision systems United Kingdom > UK Image search Cross-modal retrieval Image tags Image retrieval Multi-modal retrieval Kernelized canonical correlation analysis Object recognition Auto annotation
ISSN:	0920-5691, 1573-1405
On-line prístup:	Získať plný text
Tagy:	Pridať tag Žiadne tagy, Buďte prvý, kto otaguje tento záznam!

Abstract	We introduce an approach to image retrieval and auto-tagging that leverages the implicit information about object importance conveyed by the list of keyword tags a person supplies for an image. We propose an unsupervised learning procedure based on Kernel Canonical Correlation Analysis that discovers the relationship between how humans tag images (e.g., the order in which words are mentioned) and the relative importance of objects and their layout in the scene. Using this discovered connection, we show how to boost accuracy for novel queries, such that the search results better preserve the aspects a human may find most worth mentioning. We evaluate our approach on three datasets using either keyword tags or natural language descriptions, and quantify results with both ground truth parameters as well as direct tests with human subjects. Our results show clear improvements over approaches that either rely on image features alone, or that use words and image features but ignore the implied importance cues. Overall, our work provides a novel way to incorporate high-level human perception of scenes into visual representations for enhanced image search.
AbstractList	We introduce an approach to image retrieval and auto-tagging that leverages the implicit information about object importance conveyed by the list of keyword tags a person supplies for an image. We propose an unsupervised learning procedure based on Kernel Canonical Correlation Analysis that discovers the relationship between how humans tag images (e.g., the order in which words are mentioned) and the relative importance of objects and their layout in the scene. Using this discovered connection, we show how to boost accuracy for novel queries, such that the search results better preserve the aspects a human may find most worth mentioning. We evaluate our approach on three datasets using either keyword tags or natural language descriptions, and quantify results with both ground truth parameters as well as direct tests with human subjects. Our results show clear improvements over approaches that either rely on image features alone, or that use words and image features but ignore the implied importance cues. Overall, our work provides a novel way to incorporate high-level human perception of scenes into visual representations for enhanced image search. We introduce an approach to image retrieval and auto-tagging that leverages the implicit information about object importance conveyed by the list of keyword tags a person supplies for an image. We propose an unsupervised learning procedure based on Kernel Canonical Correlation Analysis that discovers the relationship between how humans tag images (e.g., the order in which words are mentioned) and the relative importance of objects and their layout in the scene. Using this discovered connection, we show how to boost accuracy for novel queries, such that the search results better preserve the aspects a human may find most worth mentioning. We evaluate our approach on three datasets using either keyword tags or natural language descriptions, and quantify results with both ground truth parameters as well as direct tests with human subjects. Our results show clear improvements over approaches that either rely on image features alone, or that use words and image features but ignore the implied importance cues. Overall, our work provides a novel way to incorporate high-level human perception of scenes into visual representations for enhanced image search. We introduce an approach to image retrieval and auto-tagging that leverages the implicit information about object importance conveyed by the list of keyword tags a person supplies for an image. We propose an unsupervised learning procedure based on Kernel Canonical Correlation Analysis that discovers the relationship between how humans tag images (e.g., the order in which words are mentioned) and the relative importance of objects and their layout in the scene. Using this discovered connection, we show how to boost accuracy for novel queries, such that the search results better preserve the aspects a human may find most worth mentioning. We evaluate our approach on three datasets using either keyword tags or natural language descriptions, and quantify results with both ground truth parameters as well as direct tests with human subjects. Our results show clear improvements over approaches that either rely on image features alone, or that use words and image features but ignore the implied importance cues. Overall, our work provides a novel way to incorporate high-level human perception of scenes into visual representations for enhanced image search.[PUBLICATION ABSTRACT] We introduce an approach to image retrieval and auto-tagging that leverages the implicit information about object importance conveyed by the list of keyword tags a person supplies for an image. We propose an unsupervised learning procedure based on Kernel Canonical Correlation Analysis that discovers the relationship between how humans tag images (e.g., the order in which words are mentioned) and the relative importance of objects and their layout in the scene. Using this discovered connection, we show how to boost accuracy for novel queries, such that the search results better preserve the aspects a human may find most worth mentioning. We evaluate our approach on three datasets using either keyword tags or natural language descriptions, and quantify results with both ground truth parameters as well as direct tests with human subjects. Our results show clear improvements over approaches that either rely on image features alone, or that use words and image features but ignore the implied importance cues. Overall, our work provides a novel way to incorporate high-level human perception of scenes into visual representations for enhanced image search. Keywords Image retrieval * Image tags * Multi-modal retrieval * Cross-modal retrieval * Image search * Object recognition * Auto annotation * Kernelized canonical correlation analysis
Audience	Academic
Author	Grauman, Kristen Hwang, Sung Ju
Author_xml	– sequence: 1 givenname: Sung Ju surname: Hwang fullname: Hwang, Sung Ju email: sjhwang@cs.utexas.edu organization: Department of Computer Science, University of Texas at Austin – sequence: 2 givenname: Kristen surname: Grauman fullname: Grauman, Kristen organization: Department of Computer Science, University of Texas at Austin
BookMark	eNp9kU1r3DAQhkVJoZu0P6A3Q089OJmRLH8cw9KPhS2BZO9ClkeOF6-0lbSh-ffV4h6SQosOQsPzzKB5L9mF844Y-4hwjQDNTUTktSgBsYSqq0rxhq1QNqLECuQFW0HHoZR1h-_YZYx7AOAtFytmtqSDm9xYpEcq7mnWaXqiYnM4-pC0M1R4W9z1ezIpFjb4Q7HT40hDJvRIueRDtlKY6EnPhXZDsQ4-xvKHH_L7ITc3j-_ZW6vnSB_-3Fds9_XLbv293N5926xvt6WppEylaSU2vYFewNAB9i3qoQFdDVRZrlvQDdfGUFdX1Fq0HXLR9mg6C1KIwYgr9mlpewz-54liUnt_Ci5PVFhh1_KKyzpT1ws16pnU5KxPQZt8BjpMJi_VTrl-K5pWyhZryMLnV0JmEv1Koz7FqDYP969ZXFhzXkIgq45hOujwrBDUOSe15KRyTuqckxLZaf5yzJRyCnlM0NP8X5MvZsxT3EjhxYf_Kf0Gtg-nVg
CitedBy_id	crossref_primary_10_1109_TPAMI_2019_2942028 crossref_primary_10_1007_s11263_015_0862_5 crossref_primary_10_1016_j_patcog_2019_04_017 crossref_primary_10_1016_j_patcog_2017_05_019 crossref_primary_10_1016_j_sigpro_2015_10_010 crossref_primary_10_1109_TCYB_2016_2519449 crossref_primary_10_1109_TPAMI_2015_2408354 crossref_primary_10_1109_TIP_2017_2676345 crossref_primary_10_1109_TVCG_2016_2515614 crossref_primary_10_1016_j_knosys_2021_108014 crossref_primary_10_1016_j_neucom_2020_01_017 crossref_primary_10_1109_ACCESS_2020_2992063 crossref_primary_10_1109_TETC_2021_3115625 crossref_primary_10_3233_IDA_205162 crossref_primary_10_1007_s11042_019_08312_7 crossref_primary_10_1109_TCYB_2017_2712798 crossref_primary_10_1109_ACCESS_2024_3444817 crossref_primary_10_1007_s11036_014_0511_1 crossref_primary_10_1007_s11042_018_5719_9 crossref_primary_10_1109_TASLP_2024_3358048 crossref_primary_10_1016_j_jvcir_2018_12_028 crossref_primary_10_1016_j_artint_2017_05_002 crossref_primary_10_1109_TMM_2017_2723841 crossref_primary_10_1016_j_eswa_2022_118375 crossref_primary_10_1109_TKDE_2018_2872063 crossref_primary_10_1109_TPAMI_2018_2852750 crossref_primary_10_1016_j_cviu_2016_10_001 crossref_primary_10_1109_TPAMI_2017_2651818 crossref_primary_10_1109_TCYB_2014_2327960 crossref_primary_10_1007_s11704_017_6377_1 crossref_primary_10_1007_s00500_019_03973_w crossref_primary_10_1109_TIP_2015_2395816 crossref_primary_10_1007_s00530_014_0397_6 crossref_primary_10_1109_TMM_2016_2646180 crossref_primary_10_1007_s11042_020_09983_3 crossref_primary_10_1109_TMM_2020_3004963 crossref_primary_10_1016_j_jvcir_2018_10_006 crossref_primary_10_1016_j_neucom_2022_02_007 crossref_primary_10_1109_TPAMI_2014_2366143 crossref_primary_10_1016_j_cviu_2017_05_017 crossref_primary_10_1016_j_neucom_2017_09_059 crossref_primary_10_1109_TCSVT_2017_2771247 crossref_primary_10_1016_j_neucom_2015_11_133 crossref_primary_10_1109_TMM_2021_3060955 crossref_primary_10_1109_TAFFC_2020_3026095 crossref_primary_10_1007_s12559_021_09822_z crossref_primary_10_1007_s11280_024_01249_4 crossref_primary_10_1016_j_cosrev_2020_100336 crossref_primary_10_1016_j_patcog_2018_03_033 crossref_primary_10_1007_s11042_018_5767_1 crossref_primary_10_7233_jksc_2024_74_4_092 crossref_primary_10_1007_s11045_017_0505_9 crossref_primary_10_1007_s11042_021_11701_6 crossref_primary_10_3390_s22010285 crossref_primary_10_1109_TCSVT_2016_2606648
Cites_doi	10.1109/34.895972 10.1167/8.14.18 10.1023/A:1023052124951 10.1023/A:1012460413855 10.1037/h0031619 10.1145/1348246.1348248 10.1145/582415.582418 10.1016/j.visres.2004.09.017 10.1167/8.3.3 10.1167/8.14.1 10.1093/biomet/28.3-4.321 10.1162/0899766042321814 10.1167/8.3.1 10.1023/B:VISI.0000029664.99615.94 10.1007/s10844-006-1627-y
ContentType	Journal Article
Copyright	Springer Science+Business Media, LLC 2011 COPYRIGHT 2012 Springer Springer Science+Business Media, LLC 2012
Copyright_xml	– notice: Springer Science+Business Media, LLC 2011 – notice: COPYRIGHT 2012 Springer – notice: Springer Science+Business Media, LLC 2012
DBID	AAYXX CITATION ISR 3V. 7SC 7WY 7WZ 7XB 87Z 8AL 8FD 8FE 8FG 8FK 8FL ABUWG AFKRA ARAPS AZQEC BENPR BEZIV BGLVJ CCPQU DWQXO FRNLG F~G GNUQQ HCIFZ JQ2 K60 K6~ K7- L.- L7M L~C L~D M0C M0N P5Z P62 PHGZM PHGZT PKEHL PQBIZ PQBZA PQEST PQGLB PQQKQ PQUKI PYYUZ Q9U
DOI	10.1007/s11263-011-0494-3
DatabaseName	CrossRef Gale In Context: Science ProQuest Central (Corporate) Computer and Information Systems Abstracts ABI/INFORM Collection ABI/INFORM Global (PDF only) ProQuest Central (purchase pre-March 2016) ABI/INFORM Collection Computing Database (Alumni Edition) Technology Research Database ProQuest SciTech Collection ProQuest Technology Collection ProQuest Central (Alumni) (purchase pre-March 2016) ABI/INFORM Collection (Alumni) ProQuest Central (Alumni) ProQuest Central Advanced Technologies & Computer Science Collection ProQuest Central Essentials ProQuest Central Business Premium Collection Technology collection ProQuest One Community College ProQuest Central Korea Business Premium Collection (Alumni) ABI/INFORM Global (Corporate) ProQuest Central Student SciTech Premium Collection ProQuest Computer Science Collection ProQuest Business Collection (Alumni Edition) ProQuest Business Collection Computer Science Database ABI/INFORM Professional Advanced Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional ABI/INFORM Global Computing Database Advanced Technologies & Aerospace Database ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Premium ProQuest One Academic (New) ProQuest One Academic Middle East (New) ProQuest One Business (UW System Shared) ProQuest One Business (Alumni) ProQuest One Academic Eastern Edition (DO NOT USE) ProQuest One Applied & Life Sciences ProQuest One Academic (retired) ProQuest One Academic UKI Edition ABI/INFORM Collection China ProQuest Central Basic
DatabaseTitle	CrossRef ABI/INFORM Global (Corporate) ProQuest Business Collection (Alumni Edition) ProQuest One Business Computer Science Database ProQuest Central Student Technology Collection Technology Research Database Computer and Information Systems Abstracts – Academic ProQuest One Academic Middle East (New) ProQuest Advanced Technologies & Aerospace Collection ProQuest Central Essentials ProQuest Computer Science Collection Computer and Information Systems Abstracts ProQuest Central (Alumni Edition) SciTech Premium Collection ProQuest One Community College ABI/INFORM Complete ProQuest Central ABI/INFORM Professional Advanced ProQuest One Applied & Life Sciences ProQuest Central Korea ProQuest Central (New) Advanced Technologies Database with Aerospace ABI/INFORM Complete (Alumni Edition) Advanced Technologies & Aerospace Collection Business Premium Collection ABI/INFORM Global ProQuest Computing ABI/INFORM Global (Alumni Edition) ProQuest Central Basic ProQuest Computing (Alumni Edition) ProQuest One Academic Eastern Edition ABI/INFORM China ProQuest Technology Collection ProQuest SciTech Collection ProQuest Business Collection Computer and Information Systems Abstracts Professional Advanced Technologies & Aerospace Database ProQuest One Academic UKI Edition ProQuest One Business (Alumni) ProQuest One Academic ProQuest Central (Alumni) ProQuest One Academic (New) Business Premium Collection (Alumni)
DatabaseTitleList	ABI/INFORM Global (Corporate)
Database_xml	– sequence: 1 dbid: BENPR name: ProQuest Central url: https://www.proquest.com/central sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Computer Science
EISSN	1573-1405
EndPage	153
ExternalDocumentID	3043238201 A378558160 10_1007_s11263_011_0494_3
Genre	Feature
GeographicLocations	United Kingdom--UK
GeographicLocations_xml	– name: United Kingdom--UK
GroupedDBID	-4Z -59 -5G -BR -EM -Y2 -~C .4S .86 .DC .VR 06D 0R~ 0VY 199 1N0 1SB 2.D 203 28- 29J 2J2 2JN 2JY 2KG 2KM 2LR 2P1 2VQ 2~H 30V 3V. 4.4 406 408 409 40D 40E 5GY 5QI 5VS 67Z 6NX 6TJ 78A 7WY 8FE 8FG 8FL 8TC 8UJ 95- 95. 95~ 96X AAAVM AABHQ AACDK AAHNG AAIAL AAJBT AAJKR AANZL AAOBN AARHV AARTL AASML AATNV AATVU AAUYE AAWCG AAYIU AAYQN AAYTO AAYZH ABAKF ABBBX ABBXA ABDBF ABDZT ABECU ABFTD ABFTV ABHLI ABHQN ABJNI ABJOX ABKCH ABKTR ABMNI ABMQK ABNWP ABQBU ABQSL ABSXP ABTEG ABTHY ABTKH ABTMW ABULA ABUWG ABWNU ABXPI ACAOD ACBXY ACDTI ACGFO ACGFS ACHSB ACHXU ACIHN ACKNC ACMDZ ACMLO ACOKC ACOMO ACPIV ACREN ACUHS ACZOJ ADHHG ADHIR ADIMF ADINQ ADKNI ADKPE ADMLS ADRFC ADTPH ADURQ ADYFF ADYOE ADZKW AEAQA AEBTG AEFIE AEFQL AEGAL AEGNC AEJHL AEJRE AEKMD AEMSY AENEX AEOHA AEPYU AESKC AETLH AEVLU AEXYK AFBBN AFEXP AFGCZ AFKRA AFLOW AFQWF AFWTZ AFYQB AFZKB AGAYW AGDGC AGGDS AGJBK AGMZJ AGQEE AGQMX AGRTI AGWIL AGWZB AGYKE AHAVH AHBYD AHKAY AHSBF AHYZX AIAKS AIGIU AIIXL AILAN AITGF AJBLW AJRNO AJZVZ ALMA_UNASSIGNED_HOLDINGS ALWAN AMKLP AMTXH AMXSW AMYLF AMYQR AOCGG ARAPS ARCSS ARMRJ ASPBG AVWKF AXYYD AYJHY AZFZN AZQEC B-. B0M BA0 BBWZM BDATZ BENPR BEZIV BGLVJ BGNMA BPHCQ BSONS CAG CCPQU COF CS3 CSCUP DDRTE DL5 DNIVK DPUIP DU5 DWQXO EAD EAP EAS EBLON EBS EDO EIOEI EJD EMK EPL ESBYG ESX F5P FEDTE FERAY FFXSO FIGPU FINBP FNLPD FRNLG FRRFC FSGXE FWDCC GGCAI GGRSB GJIRD GNUQQ GNWQR GQ6 GQ7 GQ8 GROUPED_ABI_INFORM_COMPLETE GXS H13 HCIFZ HF~ HG5 HG6 HMJXF HQYDN HRMNR HVGLF HZ~ I-F I09 IAO IHE IJ- IKXTQ ISR ITC ITM IWAJR IXC IZIGR IZQ I~X I~Y I~Z J-C J0Z JBSCW JCJTX JZLTJ K60 K6V K6~ K7- KDC KOV KOW LAK LLZTM M0C M0N M4Y MA- N2Q N9A NB0 NDZJH NPVJJ NQJWS NU0 O9- O93 O9G O9I O9J OAM OVD P19 P2P P62 P9O PF0 PQBIZ PQBZA PQQKQ PROAC PT4 PT5 QF4 QM1 QN7 QO4 QOK QOS R4E R89 R9I RHV RNI RNS ROL RPX RSV RZC RZE RZK S16 S1Z S26 S27 S28 S3B SAP SCJ SCLPG SCO SDH SDM SHX SISQX SJYHP SNE SNPRN SNX SOHCF SOJ SPISZ SRMVM SSLCW STPWE SZN T13 T16 TAE TEORI TSG TSK TSV TUC TUS U2A UG4 UOJIU UTJUX UZXMN VC2 VFIZW W23 W48 WK8 YLTOR Z45 Z7R Z7S Z7V Z7W Z7X Z7Y Z7Z Z83 Z86 Z88 Z8M Z8N Z8P Z8Q Z8R Z8S Z8T Z8W Z92 ZMTXR ~8M ~EX AAPKM AAYXX ABBRH ABDBE ABFSG ABRTQ ACSTC ADHKG ADKFA AEZWR AFDZB AFFHD AFHIU AFOHR AGQPQ AHPBZ AHWEU AIXLP ATHPR AYFIA CITATION ICD PHGZM PHGZT PQGLB 7SC 7XB 8AL 8FD 8FK AGGLG JQ2 L.- L7M L~C L~D PKEHL PQEST PQUKI Q9U
ID	FETCH-LOGICAL-c455t-c8517bc0b30d901b81ad70a4de4f2a80a72acce964e8f1f91238b1c9f0533dc3
IEDL.DBID	7WY
ISICitedReferencesCount	90
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000308364500003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	0920-5691
IngestDate	Mon Dec 15 19:32:35 EST 2025 Sat Nov 29 09:56:32 EST 2025 Wed Nov 26 09:31:46 EST 2025 Sat Nov 29 06:42:25 EST 2025 Tue Nov 18 19:39:50 EST 2025 Fri Feb 21 02:26:40 EST 2025
IsPeerReviewed	true
IsScholarly	true
Issue	2
Keywords	Image search Cross-modal retrieval Image tags Image retrieval Multi-modal retrieval Kernelized canonical correlation analysis Object recognition Auto annotation
Language	English
License	http://www.springer.com/tdm
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c455t-c8517bc0b30d901b81ad70a4de4f2a80a72acce964e8f1f91238b1c9f0533dc3
Notes	SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 14
PQID	1419824256
PQPubID	1456341
PageCount	20
ParticipantIDs	proquest_journals_1419824256 gale_infotracacademiconefile_A378558160 gale_incontextgauss_ISR_A378558160 crossref_primary_10_1007_s11263_011_0494_3 crossref_citationtrail_10_1007_s11263_011_0494_3 springer_journals_10_1007_s11263_011_0494_3
PublicationCentury	2000
PublicationDate	2012-11-01
PublicationDateYYYYMMDD	2012-11-01
PublicationDate_xml	– month: 11 year: 2012 text: 2012-11-01 day: 01
PublicationDecade	2010
PublicationPlace	Boston
PublicationPlace_xml	– name: Boston – name: New York
PublicationTitle	International journal of computer vision
PublicationTitleAbbrev	Int J Comput Vis
PublicationYear	2012
Publisher	Springer US Springer Springer Nature B.V
Publisher_xml	– name: Springer US – name: Springer – name: Springer Nature B.V
References	Wolfe, Horowitz (CR46) 2004; 5 Smeulders, Worring, Santini, Gupta, Jain (CR41) 2000; 22 Deng, Dong, Socher, Li, Li, Fei-Fei (CR10) 2009 Tatler, Baddeley, Gilchrist (CR43) 2005; 45 Torralba (CR44) 2003; 53 Hwang, Grauman (CR23) 2010 Hotelling (CR22) 1936; 28 CR39 CR14 CR33 CR31 Baeza-Yates, Ribeiro-Neto (CR3) 1999 Monay, Gatica-Perez (CR35) 2003 Quack, Leibe, Gool (CR37) 2008 Duygulu, Barnard, de Freitas, Forsyth (CR11) 2002 Quattoni, Collins, Darrell (CR38) 2007 Datta, Joshi, Li, Wang (CR9) 2008; 40 Schroff, Criminisi, Zisserman (CR40) 2007 Kadir, Brady (CR26) 2001; 45 Vijayanarasimhan, Grauman (CR45) 2008 Gupta, Davis (CR19) 2008 Yakhnenko, Honavar (CR47) 2009 Li, Socher, Fei-Fei (CR30) 2009 Spain, Perona (CR42) 2008 Fyfe, Lai (CR18) 2001; 10 Fleiss (CR17) 1971; 76 Einhauser, Spain, Perona (CR12) 2008; 8 Hardoon, Shawe-Taylor (CR20) 2003 Jarvelin, Kekalainen (CR25) 2002; 20 Bekkerman, Jeon (CR5) 2007 Blaschko, Lampert (CR7) 2008 CR21 Farhadi, Hejrati, Sadeghi, Young, Rashtchian, Hockenmaier, Forsyth (CR15) 2010 Fergus, Fei-Fei, Perona, Zisserman (CR16) 2005 Lavrenko, Manmatha, Jeon (CR28) 2003 Qi, Hua, Zhang (CR36) 2009 Berg, Berg, Edwards, Forsyth (CR6) 2004 Elazary, Itti (CR13) 2008; 8 Loeff, Farhadi (CR32) 2008 Akaho (CR2) 2001 Barnard, Duygulu, de Freitas, Forsyth, Blei, Jordan (CR4) 2003; 3 Makadia, Pavlovic, Kumar (CR34) 2008 von Ahn, Dabbish (CR1) 2004 Hwang, Grauman (CR24) 2010 Kulis, Grauman (CR27) 2009 Li, Wang, Fei-Fei (CR29) 2007 Bruce, Tsotsos (CR8) 2005 R. Baeza-Yates (494_CR3) 1999 S. Vijayanarasimhan (494_CR45) 2008 A. Gupta (494_CR19) 2008 494_CR21 A. Quattoni (494_CR38) 2007 L. Li (494_CR29) 2007 G. J. Qi (494_CR36) 2009 C. Fyfe (494_CR18) 2001; 10 B. Kulis (494_CR27) 2009 K. Jarvelin (494_CR25) 2002; 20 O. Yakhnenko (494_CR47) 2009 R. Bekkerman (494_CR5) 2007 K. Barnard (494_CR4) 2003; 3 D. Hardoon (494_CR20) 2003 H. Hotelling (494_CR22) 1936; 28 494_CR39 494_CR14 R. Fergus (494_CR16) 2005 T. Quack (494_CR37) 2008 W. Einhauser (494_CR12) 2008; 8 A. Torralba (494_CR44) 2003; 53 S. J. Hwang (494_CR24) 2010 J. Deng (494_CR10) 2009 J. L. Fleiss (494_CR17) 1971; 76 T. Berg (494_CR6) 2004 F. Monay (494_CR35) 2003 A. Smeulders (494_CR41) 2000; 22 J. Wolfe (494_CR46) 2004; 5 L. J. Li (494_CR30) 2009 P. Duygulu (494_CR11) 2002 L. Elazary (494_CR13) 2008; 8 A. Farhadi (494_CR15) 2010 494_CR33 A. Makadia (494_CR34) 2008 494_CR31 R. Datta (494_CR9) 2008; 40 V. Lavrenko (494_CR28) 2003 S. Akaho (494_CR2) 2001 M. Spain (494_CR42) 2008 L. Ahn von (494_CR1) 2004 N. Loeff (494_CR32) 2008 N. Bruce (494_CR8) 2005 F. Schroff (494_CR40) 2007 S. J. Hwang (494_CR23) 2010 M. B. Blaschko (494_CR7) 2008 T. Kadir (494_CR26) 2001; 45 B. Tatler (494_CR43) 2005; 45
References_xml	– year: 2009 ident: CR36 article-title: Learning semantic distance from community-tagged media collection publication-title: ACM multimedia – volume: 3 start-page: 1107 year: 2003 end-page: 1135 ident: CR4 article-title: Matching words and pictures publication-title: Journal of Machine Learning Research – year: 2008 ident: CR32 article-title: Scene discovery by matrix factorization publication-title: ECCV – year: 2005 ident: CR8 article-title: Saliency based on information maximization publication-title: NIPS – volume: 22 start-page: 1349 issue: 12 year: 2000 end-page: 1380 ident: CR41 article-title: Content-based image retrieval at the end of the early years publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/34.895972 – year: 2009 ident: CR10 article-title: Imagenet: a large-scale hierarchical image database publication-title: CVPR – year: 2009 ident: CR27 article-title: Kernelized locality-sensitive hashing for scalable image search publication-title: ICCV – ident: CR14 – ident: CR39 – year: 2009 ident: CR47 article-title: Multiple label prediction for image annotation with multiple kernel correlation models publication-title: Workshop on visual context learning, in conjunction with CVPR – year: 2003 ident: CR28 article-title: A model for learning the semantics of pictures publication-title: NIPS – year: 2007 ident: CR5 article-title: Multi-modal clustering for multimedia collections publication-title: CVPR – volume: 8 start-page: 1 issue: 14 year: 2008 end-page: 26 ident: CR12 article-title: Objects predict fixations better than early saliency publication-title: Journal of Vision doi: 10.1167/8.14.18 – year: 2010 ident: CR15 article-title: Every picture tells a story: generating sentences for images publication-title: ECCV – volume: 28 start-page: 321 year: 1936 end-page: 377 ident: CR22 article-title: Relations between two sets of variants publication-title: Biometrika – ident: CR33 – volume: 10 start-page: 365 year: 2001 end-page: 374 ident: CR18 article-title: Kernel and nonlinear canonical correlation analysis publication-title: International Journal of Neural Systems – year: 2008 ident: CR7 article-title: Correlational spectral clustering publication-title: CVPR – year: 2001 ident: CR2 article-title: A kernel method for canonical correlation analysis publication-title: International meeting of Psychometric Society – year: 2002 ident: CR11 article-title: Object recognition as machine translation: learning a lexicon for a fixed image vocabulary publication-title: ECCV – year: 2009 ident: CR30 article-title: Towards total scene understanding: classification, annotation and segmentation in an automatic framework publication-title: CVPR – year: 2003 ident: CR20 article-title: KCCA for different level precision in content-based image retrieval publication-title: Third international workshop on content-based multimedia indexing – year: 2007 ident: CR29 article-title: Optimol: automatic online picture collection via incremental model learning publication-title: CVPR – year: 2007 ident: CR40 article-title: Harvesting image databases from the web publication-title: ICCV – volume: 53 start-page: 169 issue: 2 year: 2003 end-page: 191 ident: CR44 article-title: Contextual priming for object detection publication-title: International Journal of Computer Vision doi: 10.1023/A:1023052124951 – ident: CR21 – year: 2005 ident: CR16 article-title: Learning object categories from Google’s image search publication-title: ICCV – volume: 5 start-page: 495 year: 2004 end-page: 501 ident: CR46 article-title: What attributes guide the deployment of visual attention and how do they do it? publication-title: Neuroscience – year: 2008 ident: CR19 article-title: Beyond nouns: exploiting prepositions and comparative adjectives for learning visual classifiers publication-title: ECCV – volume: 45 start-page: 83 issue: 2 year: 2001 end-page: 105 ident: CR26 article-title: Saliency, scale and image description publication-title: International Journal of Computer Vision doi: 10.1023/A:1012460413855 – year: 2003 ident: CR35 article-title: On image auto-annotation with latent space models publication-title: ACM multimedia – year: 2010 ident: CR23 article-title: Accounting for the relative importance of objects in image retrieval publication-title: British machine vision conference – volume: 76 start-page: 378 issue: 5 year: 1971 end-page: 382 ident: CR17 article-title: Measuring nominal scale agreement among many raters publication-title: Psychological Bulletin doi: 10.1037/h0031619 – year: 2004 ident: CR6 article-title: Who’s in the picture publication-title: NIPS – volume: 40 start-page: 1 issue: 2 year: 2008 end-page: 60 ident: CR9 article-title: Image retrieval: ideas, influences, and trends of the New Age publication-title: ACM Computing Surveys doi: 10.1145/1348246.1348248 – year: 2010 ident: CR24 article-title: Reading between the lines: object localization using implicit cues from image tags publication-title: CVPR – ident: CR31 – year: 2008 ident: CR45 article-title: Keywords to visual categories: multiple-instance learning for weakly supervised object categorization publication-title: CVPR – year: 2008 ident: CR37 article-title: World-scale mining of objects and events from community photo collections publication-title: CIVR – volume: 20 start-page: 422 issue: 4 year: 2002 end-page: 446 ident: CR25 article-title: Cumulated gain-based evaluation of IR techniques publication-title: ACM Transactions on Information Systems doi: 10.1145/582415.582418 – year: 2007 ident: CR38 article-title: Learning visual representations using images with captions publication-title: CVPR – year: 2008 ident: CR34 article-title: A new baseline for image annotation publication-title: ECCV – year: 2004 ident: CR1 article-title: Labeling images with a computer game publication-title: CHI – volume: 45 start-page: 643 year: 2005 end-page: 659 ident: CR43 article-title: Visual correlates of fixation selection: effects of scale and time publication-title: Vision Research doi: 10.1016/j.visres.2004.09.017 – year: 1999 ident: CR3 publication-title: Modern information retrieval – year: 2008 ident: CR42 article-title: Some objects are more equal than others: measuring and predicting importance publication-title: ECCV – volume: 8 start-page: 1 issue: 3 year: 2008 end-page: 15 ident: CR13 article-title: Interesting objects are visually salient publication-title: Journal of Vision doi: 10.1167/8.3.3 – volume-title: CVPR year: 2009 ident: 494_CR30 – volume-title: CHI year: 2004 ident: 494_CR1 – volume-title: Workshop on visual context learning, in conjunction with CVPR year: 2009 ident: 494_CR47 – volume-title: International meeting of Psychometric Society year: 2001 ident: 494_CR2 – volume-title: NIPS year: 2003 ident: 494_CR28 – volume-title: ECCV year: 2008 ident: 494_CR19 – volume-title: British machine vision conference year: 2010 ident: 494_CR23 – volume-title: ECCV year: 2002 ident: 494_CR11 – volume: 8 start-page: 1 issue: 14 year: 2008 ident: 494_CR12 publication-title: Journal of Vision doi: 10.1167/8.14.1 – volume-title: ICCV year: 2005 ident: 494_CR16 – volume: 40 start-page: 1 issue: 2 year: 2008 ident: 494_CR9 publication-title: ACM Computing Surveys doi: 10.1145/1348246.1348248 – volume-title: CVPR year: 2008 ident: 494_CR7 – volume-title: Modern information retrieval year: 1999 ident: 494_CR3 – volume: 28 start-page: 321 year: 1936 ident: 494_CR22 publication-title: Biometrika doi: 10.1093/biomet/28.3-4.321 – volume: 5 start-page: 495 year: 2004 ident: 494_CR46 publication-title: Neuroscience – volume-title: CVPR year: 2007 ident: 494_CR29 – volume-title: CIVR year: 2008 ident: 494_CR37 – volume: 76 start-page: 378 issue: 5 year: 1971 ident: 494_CR17 publication-title: Psychological Bulletin doi: 10.1037/h0031619 – volume: 10 start-page: 365 year: 2001 ident: 494_CR18 publication-title: International Journal of Neural Systems – volume-title: ACM multimedia year: 2003 ident: 494_CR35 – volume-title: ACM multimedia year: 2009 ident: 494_CR36 – volume-title: CVPR year: 2007 ident: 494_CR38 – ident: 494_CR14 – ident: 494_CR21 doi: 10.1162/0899766042321814 – volume: 3 start-page: 1107 year: 2003 ident: 494_CR4 publication-title: Journal of Machine Learning Research – volume: 53 start-page: 169 issue: 2 year: 2003 ident: 494_CR44 publication-title: International Journal of Computer Vision doi: 10.1023/A:1023052124951 – volume-title: ECCV year: 2008 ident: 494_CR34 – volume-title: ICCV year: 2009 ident: 494_CR27 – volume-title: ECCV year: 2008 ident: 494_CR32 – volume: 45 start-page: 643 year: 2005 ident: 494_CR43 publication-title: Vision Research doi: 10.1016/j.visres.2004.09.017 – volume-title: CVPR year: 2007 ident: 494_CR5 – ident: 494_CR39 – volume-title: ECCV year: 2008 ident: 494_CR42 – volume: 8 start-page: 1 issue: 3 year: 2008 ident: 494_CR13 publication-title: Journal of Vision doi: 10.1167/8.3.1 – volume-title: ICCV year: 2007 ident: 494_CR40 – volume-title: NIPS year: 2004 ident: 494_CR6 – volume-title: Third international workshop on content-based multimedia indexing year: 2003 ident: 494_CR20 – volume: 45 start-page: 83 issue: 2 year: 2001 ident: 494_CR26 publication-title: International Journal of Computer Vision doi: 10.1023/A:1012460413855 – volume: 22 start-page: 1349 issue: 12 year: 2000 ident: 494_CR41 publication-title: IEEE Transactions on Pattern Analysis and Machine Intelligence doi: 10.1109/34.895972 – volume-title: ECCV year: 2010 ident: 494_CR15 – volume: 20 start-page: 422 issue: 4 year: 2002 ident: 494_CR25 publication-title: ACM Transactions on Information Systems doi: 10.1145/582415.582418 – volume-title: CVPR year: 2008 ident: 494_CR45 – ident: 494_CR33 doi: 10.1023/B:VISI.0000029664.99615.94 – volume-title: NIPS year: 2005 ident: 494_CR8 – volume-title: CVPR year: 2010 ident: 494_CR24 – ident: 494_CR31 doi: 10.1007/s10844-006-1627-y – volume-title: CVPR year: 2009 ident: 494_CR10
SSID	ssj0002823
Score	2.4378796
Snippet	We introduce an approach to image retrieval and auto-tagging that leverages the implicit information about object importance conveyed by the list of keyword... We introduce an approach to image retrieval and auto-tagging that leverages the implicit information about object importance conveyed by the list of keyword...
SourceID	proquest gale crossref springer
SourceType	Aggregation Database Enrichment Source Index Database Publisher
StartPage	134
SubjectTerms	Analysis Artificial Intelligence Computer Imaging Computer Science Correlation analysis Experiments Human subjects Image Processing and Computer Vision Image retrieval Information management Information retrieval International Keywords Learning Learning strategies Pattern Recognition Pattern Recognition and Graphics Perceptions Queries Semantics Studies Vision Vision systems
SummonAdditionalLinks	– databaseName: SpringerLINK Contemporary 1997-Present dbid: RSV link: http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwnV1bSx0xEA6t7UNf1NqWHqsSSkFoCew1l0eRigfUFj0U30KuB6Huytmjv9-Z3azW2hbs42Ynu8nk9iWZ-YaQT8ryQgXvGI-uZFUdDbPel8xy60WsZVa7njL_SJycyPNz9T35cXejtft4JdnP1PfObnmBd454pFepipXPyQtkf0PC_NOzH3fTL-whhvjxsC-qucrHq8w_feLBYvT7lPzobrRfcg7W_quw62Q1IUy6N3SJ1-RZaDbIWkKbNI3lDpLGgA5j2hviEtvqnAIspIOd3E2g08sepIMIbSP9ZvHopqPomEJnZj6Hr04vYVqCpHYBuTBEF_RfahpP97He7Lj18DxYNr8ls4Ovs_1DlqIwMFfV9ZI5wGTCusyWmQfwYGVuvMhM5UMVCyMzIwrjXFC8CjLmUcFSKG3uVEQvX-_Kd2SlaZvwnlCTu1AFC5hNgFJsKbmPzhouAAYGZ8WEZGNraJcYyjFQxk99z62MatWgVo1q1eWEfL7LcjXQc_xL-CM2sUbaiwbtaubmuuv09OxU75VC1rXMeTYhu0kotvBzZ5KbAlQBmbIeSG6NXUWngd_BTipXErdxfEK-jF3jl9d_K9vmk6Q_kFcA3IrBJ3KLrCwX12GbvHQ3y4tusdOPh1vuygOV priority: 102 providerName: Springer Nature
Title	Learning the Relative Importance of Objects from Tagged Images for Retrieval and Cross-Modal Search
URI	https://link.springer.com/article/10.1007/s11263-011-0494-3 https://www.proquest.com/docview/1419824256
Volume	100
WOSCitedRecordID	wos000308364500003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
hasFullText	1
inHoldings	1
isFullTextHit
isPrint
journalDatabaseRights	– providerCode: PRVPQU databaseName: ABI/INFORM Collection customDbUrl: eissn: 1573-1405 dateEnd: 20171231 omitProxy: false ssIdentifier: ssj0002823 issn: 0920-5691 databaseCode: 7WY dateStart: 19970101 isFulltext: true titleUrlDefault: https://www.proquest.com/abicomplete providerName: ProQuest – providerCode: PRVPQU databaseName: ABI/INFORM Global (OCUL) customDbUrl: eissn: 1573-1405 dateEnd: 20171231 omitProxy: false ssIdentifier: ssj0002823 issn: 0920-5691 databaseCode: M0C dateStart: 19970101 isFulltext: true titleUrlDefault: https://search.proquest.com/abiglobal providerName: ProQuest – providerCode: PRVPQU databaseName: Advanced Technologies & Aerospace Database customDbUrl: eissn: 1573-1405 dateEnd: 20171231 omitProxy: false ssIdentifier: ssj0002823 issn: 0920-5691 databaseCode: P5Z dateStart: 19970101 isFulltext: true titleUrlDefault: https://search.proquest.com/hightechjournals providerName: ProQuest – providerCode: PRVPQU databaseName: Computer Science Database customDbUrl: eissn: 1573-1405 dateEnd: 20171231 omitProxy: false ssIdentifier: ssj0002823 issn: 0920-5691 databaseCode: K7- dateStart: 19970101 isFulltext: true titleUrlDefault: http://search.proquest.com/compscijour providerName: ProQuest – providerCode: PRVPQU databaseName: ProQuest Central customDbUrl: eissn: 1573-1405 dateEnd: 20171231 omitProxy: false ssIdentifier: ssj0002823 issn: 0920-5691 databaseCode: BENPR dateStart: 19970101 isFulltext: true titleUrlDefault: https://www.proquest.com/central providerName: ProQuest – providerCode: PRVAVX databaseName: SpringerLINK Contemporary 1997-Present customDbUrl: eissn: 1573-1405 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0002823 issn: 0920-5691 databaseCode: RSV dateStart: 19970101 isFulltext: true titleUrlDefault: https://link.springer.com/search?facet-content-type=%22Journal%22 providerName: Springer Nature
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwpV1Lb9QwELag5cCF8hRbSmUhJCSQRR52nJxQWbViBV1W2xUULpafKySatJttfz8zidNSEL1wsWTHdpzMePzZngchLytTZJV3lhXB5oyLoJlxLmemME4GUSbCdi7zP8nptDw-rmbxwK2NapWDTOwEtWssnpG_TTlsjxEfF-9OzxhGjcLb1RhC4zbZhIWao0qX_PrtUhLDdqIPJQ9bJFFU6XCr2ZnOpRneYOIBIa84y6-tS39K57-uSbvV52Drf8d9n9yLuJPu9YzygNzy9UOyFTEojTO8haIhzMNQ9ojY6IN1SQEs0l577sLTyUkH3aEKbQL9bPBAp6VorkIXermEXicnIKygqFlBKwzcBVxNde3oGH8BO2wc5Ht958dkcbC_GH9gMTYDs1yINbOA1KSxickTB5DClKl2MtHceR4yXSZaZtpaXxXclyENFSyQpUltFdD219n8Cdmom9o_JVSn1nNvAMlJoITJy8IFa3QhARx6a-SIJANhlI1-yzF8xk915XEZaamAlgppqfIReX3Z5LR32nFT5RdIbYXOMGrUtlnq87ZVk6O52stlKUSZFsmIvIqVQgMvtzoaL8AnoP-sazV3Bj5QURy06ooJRuTNwEm_Pf7X2LZv7uwZuQv4LetNI3fIxnp17p-TO_Zi_aNd7XZzYZdsvt-fzuaQ-ygZpIfJGNKZ-A7p_OjLL7l8E94
linkProvider	ProQuest
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Jb9QwFH4qBQkulFUMtGAhEBLIalYnOVRVVagazXRAMIfeLK8jJJqUybSIH8V_7HtZWgqitx44xrGd2P78FvstAK8KLaLCWcOFNzFPUq-4tjbmWmib-TQPUtOGzJ9k02l-eFh8WoFfgy8MmVUONLEl1LY2dEa-GSaoHpN8LLaPv3PKGkW3q0MKjQ4WY_fzB6pszVb5Htf3dRTtfZjt7vM-qwA3SZouuaFs9NoEOg4sMkOdh8pmgUqsS3yk8kBlkTLGFSJxuQ99gaQ916EpPHmtWhNjtzfgJkX4JF1vnPFzwo_aS5e5HjWyVBThcInaeuqFEV2Y0nlkUiQ8vsQG_2QGf93Ktsxub-0_m6Z7cLeXqtlOtw3uw4qrHsBaL2Gznn41WDQksRjKHoLpI8zOGYrCrLMNPHWsPGoVE6zCas8-ajquahg547CZms-x1_IISTEW1QtsRWnJcM8yVVm2SzPOD2qLz5019yOYXcfgH8NqVVfuCTAVGpc4jXJqhguv41xYb7QSGYq-zuhsBMGAA2n6qOyUHOSbvIgnTdCRCB1J0JHxCN6eNznuQpJcVfklgUtSqI-KbInm6qRpZPnls9yJszxN81AEI3jTV_I1ftyo3jUDh0DRwS7VXB9gJ3ti18gLzI3g3QDc317_69-eXt3ZC7i9PzuYyEk5HT-DOyipRp0T6DqsLhcnbgNumdPl12bxvN2GDOQ14_kMwBNq6g
linkToPdf	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMw1V1Lb9QwEB6VghAXylMstGAhEBLIat6PQ1VVLSuiLUsFe-jN8nOFRJOy2Rbx0_h3nUmcloLorQeOcRwndr55eTwzAK9KlUWlNZpnTsc8SZ3kypiYq0yZ3KVFkOouZf5-Pp0Wh4flwQr8GmJh6FjlwBM7Rm0aTXvkm2GC5jHpx9mm88ciDvbG28ffOVWQIk_rUE6jh8jE_vyB5lu7Ve3hv34dReP3s90P3FcY4DpJ0yXXVJle6UDFgUHBqIpQmjyQibGJi2QRyDySWtsyS2zhQlcimy9UqEtHEaxGxzjsDbhJQpiIa5LzcyGAlkxfxR6tszQrw8Gh2kXthRE5T2lvMikTHl8SiX8Khr88tJ3gG6_9x0t2D-56bZvt9ORxH1Zs_QDWvObNPF9rsWkobjG0PQTtM8_OGarIrD8zeGpZddQZLNiFNY59UrSN1TIK0mEzOZ_jqNURsmhsahb4FJUrQ1pmsjZsl1aff2wMXvenvB_B7Dom_xhW66a2T4DJUNvEKtRfcwSBiovMOK1klqNKbLXKRxAMmBDaZ2unoiHfxEWeaYKRQBgJgpGIR_D2_JHjPlXJVZ1fEtAEpQCpCRlzedK2ovryWezEeZGmRZgFI3jjO7kGX66lD9nAKVDWsEs91wcICs8EW3GBvxG8G0D82-1_fdvTqwd7AbcRxmK_mk6ewR1UYKM-NnQdVpeLE7sBt_Tp8mu7eN5RJANxzXA-A4Pcc6Q
openUrl	ctx_ver=Z39.88-2004&ctx_enc=info%3Aofi%2Fenc%3AUTF-8&rfr_id=info%3Asid%2Fsummon.serialssolutions.com&rft_val_fmt=info%3Aofi%2Ffmt%3Akev%3Amtx%3Ajournal&rft.genre=article&rft.atitle=Learning+the+relative+importance+of+objects+from+tagged+images+for+retrieval+and+cross-modal+search&rft.jtitle=International+journal+of+computer+vision&rft.au=Hwang%2C+Sung+Ju&rft.au=Grauman%2C+Kristen&rft.date=2012-11-01&rft.pub=Springer&rft.issn=0920-5691&rft.volume=100&rft.issue=2&rft.spage=134&rft_id=info:doi/10.1007%2Fs11263-011-0494-3&rft.externalDBID=ISR&rft.externalDocID=A378558160
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0920-5691&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0920-5691&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0920-5691&client=summon