Spatial Pooling of Heterogeneous Features for Image Classification

In image classification tasks, one of the most successful algorithms is the bag-of-features (BoFs) model. Although the BoF model has many advantages, such as simplicity, generality, and scalability, it still suffers from several drawbacks, including the limited semantic description of local descript...

Ausführliche Beschreibung

Gespeichert in:

Bibliographische Detailangaben
Veröffentlicht in:	IEEE transactions on image processing Jg. 23; H. 5; S. 1994 - 2008
Hauptverfasser:	Xie, Lingxi, Tian, Qi, Wang, Meng, Zhang, Bo
Format:	Journal Article
Sprache:	Englisch
Veröffentlicht:	New York, NY IEEE 01.05.2014 Institute of Electrical and Electronics Engineers The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Schlagworte:	Accuracy Algorithms Applied sciences Basic converters Construction Exact sciences and technology Feature extraction Image classification Image edge detection Image processing Information, signal and communications theory Mathematical models Oxygen steel making Pattern recognition Quantization (signal) Shape Signal and communications theory Signal processing Signal representation. Spectral analysis Signal, noise Telecommunications and information theory Texture Vectors Visualization BoF model geometric phrases pooling complementary descriptors spatial weighting Image classification Performance evaluation State of the art Image processing Scalability Pattern recognition Signal representation Shape detection Algorithm Modeling Texture Interest region Weighting Semantics Image representation Edge detection
ISSN:	1057-7149, 1941-0042, 1941-0042
Online-Zugang:	Volltext
Tags:	Tag hinzufügen Keine Tags, Fügen Sie den ersten Tag hinzu!

Abstract	In image classification tasks, one of the most successful algorithms is the bag-of-features (BoFs) model. Although the BoF model has many advantages, such as simplicity, generality, and scalability, it still suffers from several drawbacks, including the limited semantic description of local descriptors, lack of robust structures upon single visual words, and missing of efficient spatial weighting. To overcome these shortcomings, various techniques have been proposed, such as extracting multiple descriptors, spatial context modeling, and interest region detection. Though they have been proven to improve the BoF model to some extent, there still lacks a coherent scheme to integrate each individual module together. To address the problems above, we propose a novel framework with spatial pooling of complementary features. Our model expands the traditional BoF model on three aspects. First, we propose a new scheme for combining texture and edge-based local features together at the descriptor extraction level. Next, we build geometric visual phrases to model spatial context upon complementary features for midlevel image representation. Finally, based on a smoothed edgemap, a simple and effective spatial weighting scheme is performed to capture the image saliency. We test the proposed framework on several benchmark data sets for image classification. The extensive results show the superior performance of our algorithm over the state-of-the-art methods.
AbstractList	In image classification tasks, one of the most successful algorithms is the bag-of-features (BoFs) model. Although the BoF model has many advantages, such as simplicity, generality, and scalability, it still suffers from several drawbacks, including the limited semantic description of local descriptors, lack of robust structures upon single visual words, and missing of efficient spatial weighting. To overcome these shortcomings, various techniques have been proposed, such as extracting multiple descriptors, spatial context modeling, and interest region detection. Though they have been proven to improve the BoF model to some extent, there still lacks a coherent scheme to integrate each individual module together. To address the problems above, we propose a novel framework with spatial pooling of complementary features. Our model expands the traditional BoF model on three aspects. First, we propose a new scheme for combining texture and edge-based local features together at the descriptor extraction level. Next, we build geometric visual phrases to model spatial context upon complementary features for midlevel image representation. Finally, based on a smoothed edgemap, a simple and effective spatial weighting scheme is performed to capture the image saliency. We test the proposed framework on several benchmark data sets for image classification. The extensive results show the superior performance of our algorithm over the state-of-the-art methods.In image classification tasks, one of the most successful algorithms is the bag-of-features (BoFs) model. Although the BoF model has many advantages, such as simplicity, generality, and scalability, it still suffers from several drawbacks, including the limited semantic description of local descriptors, lack of robust structures upon single visual words, and missing of efficient spatial weighting. To overcome these shortcomings, various techniques have been proposed, such as extracting multiple descriptors, spatial context modeling, and interest region detection. Though they have been proven to improve the BoF model to some extent, there still lacks a coherent scheme to integrate each individual module together. To address the problems above, we propose a novel framework with spatial pooling of complementary features. Our model expands the traditional BoF model on three aspects. First, we propose a new scheme for combining texture and edge-based local features together at the descriptor extraction level. Next, we build geometric visual phrases to model spatial context upon complementary features for midlevel image representation. Finally, based on a smoothed edgemap, a simple and effective spatial weighting scheme is performed to capture the image saliency. We test the proposed framework on several benchmark data sets for image classification. The extensive results show the superior performance of our algorithm over the state-of-the-art methods. In image classification tasks, one of the most successful algorithms is the bag-of-features (BoFs) model. Although the BoF model has many advantages, such as simplicity, generality, and scalability, it still suffers from several drawbacks, including the limited semantic description of local descriptors, lack of robust structures upon single visual words, and missing of efficient spatial weighting. To overcome these shortcomings, various techniques have been proposed, such as extracting multiple descriptors, spatial context modeling, and interest region detection. Though they have been proven to improve the BoF model to some extent, there still lacks a coherent scheme to integrate each individual module together. To address the problems above, we propose a novel framework with spatial pooling of complementary features. Our model expands the traditional BoF model on three aspects. First, we propose a new scheme for combining texture and edge-based local features together at the descriptor extraction level. Next, we build geometric visual phrases to model spatial context upon complementary features for midlevel image representation. Finally, based on a smoothed edgemap, a simple and effective spatial weighting scheme is performed to capture the image saliency. We test the proposed framework on several benchmark data sets for image classification. The extensive results show the superior performance of our algorithm over the state-of-the-art methods.
Author	Bo Zhang Qi Tian Meng Wang Lingxi Xie
Author_xml	– sequence: 1 givenname: Lingxi surname: Xie fullname: Xie, Lingxi – sequence: 2 givenname: Qi surname: Tian fullname: Tian, Qi – sequence: 3 givenname: Meng surname: Wang fullname: Wang, Meng – sequence: 4 givenname: Bo surname: Zhang fullname: Zhang, Bo
BackLink	http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=28528563$$DView record in Pascal Francis https://www.ncbi.nlm.nih.gov/pubmed/24710400$$D View this record in MEDLINE/PubMed
BookMark	eNqN0ctr3DAQB2BRUppHey8UgiEEcvFWY-thHdMlj4VAA03PYqwdLwpeayPZh_z31WY3LeQQCgLp8P1G0swxOxjCQIx9BT4D4Ob7w-J-VnEQs6oGDqA_sCMwAkrORXWQz1zqUoMwh-w4pUeepQT1iR1WQgMXnB-xH782OHrsi_sQej-sitAVtzRSDCsaKEypuCYcp0ip6EIsFmtcUTHvMSXfeZejYfjMPnbYJ_qy30_Y7-urh_lteffzZjG_vCud0GostUEDbZOv1kJLgaaVhEa0vBMtYSPdsulQtlW1lLRsjaqkU61yhABGkxD1CbvY1d3E8DRRGu3aJ0d9jy8PtSBzE3itav0fFHJBEE2T6dkb-himOOSPbFWltFJSZXW6V1O7pqXdRL_G-GxfG5nB-R5gcth3EQfn0z_XyLxUnZ3aORdDSpE66_z40sYxou8tcLudrM2TtdvJ2v1kc5C_Cb7WfifybRfxRPSXKy01F7L-A102qr4
CODEN	IIPRE4
CitedBy_id	crossref_primary_10_1016_j_neunet_2018_05_015 crossref_primary_10_1016_j_jvcir_2015_07_005 crossref_primary_10_1016_j_neucom_2016_02_045 crossref_primary_10_1007_s11042_018_6712_z crossref_primary_10_1016_j_neucom_2015_12_008 crossref_primary_10_1109_JBHI_2020_2977937 crossref_primary_10_1007_s11042_020_08666_3 crossref_primary_10_1109_JSTARS_2016_2547638 crossref_primary_10_1016_j_patcog_2023_109482 crossref_primary_10_1109_TCSVT_2015_2461978 crossref_primary_10_1007_s42001_017_0009_2 crossref_primary_10_1016_j_neucom_2020_07_147 crossref_primary_10_1109_TIP_2014_2330763 crossref_primary_10_1109_TIP_2015_2432673 crossref_primary_10_1109_TIP_2017_2695884 crossref_primary_10_1016_j_patcog_2019_107094 crossref_primary_10_1109_TPAMI_2019_2933510 crossref_primary_10_1007_s11042_018_6224_x crossref_primary_10_1109_TIP_2017_2686017 crossref_primary_10_1007_s11063_020_10246_3 crossref_primary_10_1155_2018_4945304 crossref_primary_10_1371_journal_pone_0170629 crossref_primary_10_1109_TIP_2015_2509425 crossref_primary_10_1109_JBHI_2017_2775662 crossref_primary_10_1186_s13640_016_0140_7 crossref_primary_10_1109_TIP_2014_2329182 crossref_primary_10_1007_s11042_018_5712_3 crossref_primary_10_1109_TIP_2015_2405337 crossref_primary_10_1109_TMM_2015_2408566 crossref_primary_10_1007_s00530_022_00899_6 crossref_primary_10_3389_fpls_2024_1334362 crossref_primary_10_1016_j_neucom_2017_01_067 crossref_primary_10_1016_j_patrec_2018_09_010 crossref_primary_10_1145_3587253 crossref_primary_10_1016_j_neucom_2015_01_043 crossref_primary_10_1515_amcs_2017_0059 crossref_primary_10_1109_TCSVT_2020_2975845 crossref_primary_10_1007_s11263_016_0970_x crossref_primary_10_1109_TIFS_2023_3234861 crossref_primary_10_1109_TMM_2015_2399851 crossref_primary_10_1016_j_asoc_2020_106310
Cites_doi	10.1109/ICCV.2007.4409066 10.1016/j.imavis.2004.02.006 10.1109/TMM.2010.2046292 10.1145/1873951.1874182 10.1109/CVPR.2005.177 10.1007/s11042-010-0636-6 10.1109/CVPR.1999.784624 10.1109/ICCV.2013.47 10.1109/CVPR.2011.5995528 10.1109/TPAMI.1986.4767851 10.1109/CVPR.2010.5539963 10.1145/1873951.1874019 10.1109/CVPR.2006.68 10.1109/ICCV.2009.5459169 10.1109/CVPR.2006.42 10.1109/CVPR.2009.5206537 10.1145/1631272.1631285 10.1109/ICIP.2013.6738537 10.1023/B:VISI.0000029664.99615.94 10.1145/2393347.2393423 10.1145/1873951.1874018 10.1016/j.imavis.2008.04.022 10.1109/TPAMI.2009.154 10.1109/CVPR.2010.5540018 10.5244/C.18.98 10.1109/CVPR.2011.5995476 10.1109/CVPR.2010.5540021 10.1109/34.730558 10.1145/1873951.1874249 10.1109/ICCV.2013.206 10.1109/CVPR.2014.477 10.1109/34.993558 10.1109/CVPR.2006.264 10.1109/ICCV.2013.215 10.1109/CVPR.2007.383222 10.1016/j.cviu.2005.09.012
ContentType	Journal Article
Copyright	2015 INIST-CNRS Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) May 2014
Copyright_xml	– notice: 2015 INIST-CNRS – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) May 2014
DBID	97E RIA RIE AAYXX CITATION IQODW NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 F28 FR3
DOI	10.1109/TIP.2014.2310117
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Pascal-Francis PubMed Computer and Information Systems Abstracts Electronics & Communications Abstracts Technology Research Database ProQuest Computer Science Collection Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Academic Computer and Information Systems Abstracts Professional MEDLINE - Academic ANTE: Abstracts in New Technology & Engineering Engineering Research Database
DatabaseTitle	CrossRef PubMed Technology Research Database Computer and Information Systems Abstracts – Academic Electronics & Communications Abstracts ProQuest Computer Science Collection Computer and Information Systems Abstracts Advanced Technologies Database with Aerospace Computer and Information Systems Abstracts Professional MEDLINE - Academic Engineering Research Database ANTE: Abstracts in New Technology & Engineering
DatabaseTitleList	MEDLINE - Academic Technology Research Database PubMed Technology Research Database
Database_xml	– sequence: 1 dbid: NPM name: PubMed url: http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: RIE name: IEEE Electronic Library (IEL) url: https://ieeexplore.ieee.org/ sourceTypes: Publisher – sequence: 3 dbid: 7X8 name: MEDLINE - Academic url: https://search.proquest.com/medline sourceTypes: Aggregation Database
DeliveryMethod	fulltext_linktorsrc
Discipline	Applied Sciences Engineering
EISSN	1941-0042
EndPage	2008
ExternalDocumentID	3266337871 24710400 28528563 10_1109_TIP_2014_2310117 6757045
Genre	orig-research Research Support, Non-U.S. Gov't Journal Article
GroupedDBID	--- -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK AENEX AETIX AGQYO AGSQL AHBIQ AI. AIBXA AKJIK AKQYR ALLEH ALMA_UNASSIGNED_HOLDINGS ASUFR ATWAV BEFXN BFFAM BGNUA BKEBE BPEOZ CS3 DU5 E.L EBS EJD F5P HZ~ H~9 ICLAB IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P RIA RIE RNS TAE TN5 VH1 AAYXX CITATION AAYOK IQODW RIG NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8 F28 FR3
ID	FETCH-LOGICAL-c476t-79a91b824774754a9b5ea94b0f4bea85cd8fa5b22d5edb9625c6b6cea1197e443
IEDL.DBID	RIE
ISICitedReferencesCount	69
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000334526000003&url=https%3A%2F%2Fcvtisr.summon.serialssolutions.com%2F%23%21%2Fsearch%3Fho%3Df%26include.ft.matches%3Dt%26l%3Dnull%26q%3D
ISSN	1057-7149 1941-0042
IngestDate	Sat Sep 27 19:10:38 EDT 2025 Wed Oct 01 14:01:07 EDT 2025 Sun Nov 09 08:27:44 EST 2025 Thu Apr 03 07:01:42 EDT 2025 Wed Apr 02 07:17:46 EDT 2025 Sat Nov 29 03:20:54 EST 2025 Tue Nov 18 22:35:39 EST 2025 Tue Aug 26 16:50:04 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	5
Keywords	BoF model geometric phrases pooling complementary descriptors spatial weighting Image classification Performance evaluation State of the art Image processing Scalability Pattern recognition Signal representation Shape detection Algorithm Modeling Texture Interest region Weighting Semantics Image representation Edge detection
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html CC BY 4.0
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c476t-79a91b824774754a9b5ea94b0f4bea85cd8fa5b22d5edb9625c6b6cea1197e443
Notes	ObjectType-Article-2 SourceType-Scholarly Journals-1 ObjectType-Feature-1 content type line 14 ObjectType-Article-1 ObjectType-Feature-2 content type line 23
PMID	24710400
PQID	1512676656
PQPubID	85429
PageCount	15
ParticipantIDs	crossref_primary_10_1109_TIP_2014_2310117 proquest_miscellaneous_1531003637 pascalfrancis_primary_28528563 ieee_primary_6757045 proquest_miscellaneous_1514431488 proquest_journals_1512676656 crossref_citationtrail_10_1109_TIP_2014_2310117 pubmed_primary_24710400
PublicationCentury	2000
PublicationDate	2014-05-01
PublicationDateYYYYMMDD	2014-05-01
PublicationDate_xml	– month: 05 year: 2014 text: 2014-05-01 day: 01
PublicationDecade	2010
PublicationPlace	New York, NY
PublicationPlace_xml	– name: New York, NY – name: United States – name: New York
PublicationTitle	IEEE transactions on image processing
PublicationTitleAbbrev	TIP
PublicationTitleAlternate	IEEE Trans Image Process
PublicationYear	2014
Publisher	IEEE Institute of Electrical and Electronics Engineers The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: Institute of Electrical and Electronics Engineers – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref13 ref15 ref14 ref52 ref11 ref10 ref17 ref16 ref18 yang (ref25) 0 ref50 ref46 wah (ref37) 2011 lee (ref24) 0 ref48 ref47 ref42 ref41 nowak (ref3) 0 everingham (ref43) 2011 ref8 ref9 ref4 ref6 ref5 ref40 ref36 ref31 csurka (ref1) 0 ref33 ref32 lu (ref7) 2010; 12 ref39 ref38 bo (ref51) 2011; 1 fan (ref34) 2008 ref23 ref26 ref20 ref22 ref21 bosch (ref19) 0 perronnin (ref35) 0 ref28 ref27 gao (ref45) 0 ref29 griffin (ref44) 2007 li (ref49) 2010 marszalek (ref2) 0 liu (ref30) 0 feng (ref12) 0
References_xml	– start-page: 2609 year: 0 ident: ref12 article-title: Geometric $\ell{\rm p}$ norm feature pooling for image classification publication-title: Proc Comput Vis Pattern Recognit – ident: ref9 doi: 10.1109/ICCV.2007.4409066 – ident: ref18 doi: 10.1016/j.imavis.2004.02.006 – volume: 1 start-page: 1 year: 2011 ident: ref51 article-title: Hierarchical matching pursuit for image classification: Architecture and fast algorithms publication-title: Neural Inf Process Syst – volume: 12 start-page: 288 year: 2010 ident: ref7 article-title: Constructing lexica of high-level concepts with small semantic gap publication-title: IEEE Trans Multimedia doi: 10.1109/TMM.2010.2046292 – ident: ref21 doi: 10.1145/1873951.1874182 – start-page: 2118 year: 0 ident: ref2 article-title: Spatial weighting for bag-of-features publication-title: Proc Comput Vis Pattern Recognit – ident: ref17 doi: 10.1109/CVPR.2005.177 – ident: ref22 doi: 10.1007/s11042-010-0636-6 – start-page: 1 year: 0 ident: ref30 article-title: Integrated feature selection and higher-order spatial feature extraction for object categorization publication-title: Proc IEEE Conf Comput Vis Pattern Recognit – ident: ref13 doi: 10.1109/CVPR.1999.784624 – start-page: 1794 year: 0 ident: ref25 article-title: Linear spatial pyramid matching using sparse coding for image classification publication-title: Proc Comput Vis Pattern Recognit – start-page: 1817 year: 2008 ident: ref34 article-title: LIBLINEAR: A library for large linear classification publication-title: J Mach Learn Res – ident: ref39 doi: 10.1109/ICCV.2013.47 – ident: ref11 doi: 10.1109/CVPR.2011.5995528 – ident: ref14 doi: 10.1109/TPAMI.1986.4767851 – start-page: 1 year: 2010 ident: ref49 article-title: Object bank: A high-level image representation for scene classification and semantic feature sparsification publication-title: Neuron Inf Process Syst – ident: ref10 doi: 10.1109/CVPR.2010.5539963 – ident: ref27 doi: 10.1145/1873951.1874019 – ident: ref15 doi: 10.1109/CVPR.2006.68 – start-page: 1 year: 0 ident: ref45 article-title: Kernel sparse representation for image classification and face recognition publication-title: Proc Eur Conf Comput Vis – ident: ref48 doi: 10.1109/ICCV.2009.5459169 – ident: ref36 doi: 10.1109/CVPR.2006.42 – year: 2011 ident: ref37 publication-title: The Caltech-UCSD Birds-200-2011 Dataset – ident: ref50 doi: 10.1109/CVPR.2009.5206537 – ident: ref31 doi: 10.1145/1631272.1631285 – ident: ref33 doi: 10.1109/ICIP.2013.6738537 – start-page: 490 year: 0 ident: ref3 article-title: Sampling strategies for bag-of-features image classification publication-title: Proc Comput Vis Pattern Recognit – year: 2007 ident: ref44 publication-title: Caltech-256 Object Category Dataset – start-page: 517 year: 0 ident: ref19 article-title: Scene classification via pLSA publication-title: Proc Int Conf Comput Vis – ident: ref5 doi: 10.1023/B:VISI.0000029664.99615.94 – ident: ref16 doi: 10.1145/2393347.2393423 – ident: ref23 doi: 10.1145/1873951.1874018 – ident: ref47 doi: 10.1016/j.imavis.2008.04.022 – ident: ref20 doi: 10.1109/TPAMI.2009.154 – ident: ref26 doi: 10.1109/CVPR.2010.5540018 – ident: ref46 doi: 10.5244/C.18.98 – ident: ref32 doi: 10.1109/CVPR.2011.5995476 – ident: ref4 doi: 10.1109/CVPR.2010.5540021 – ident: ref41 doi: 10.1109/34.730558 – ident: ref42 doi: 10.1145/1873951.1874249 – start-page: 1 year: 0 ident: ref1 article-title: Visual Categorization with Bags of Keypoints publication-title: Proc Workshop Statist Learn Comput Vis Eur Con Comput Vis – ident: ref38 doi: 10.1109/ICCV.2013.206 – ident: ref28 doi: 10.1109/CVPR.2014.477 – ident: ref52 doi: 10.1109/34.993558 – start-page: 801 year: 0 ident: ref24 article-title: Efficient sparse coding algorithms publication-title: Proc Neural Inf Process Syst – ident: ref6 doi: 10.1109/CVPR.2006.264 – ident: ref40 doi: 10.1109/ICCV.2013.215 – year: 2011 ident: ref43 publication-title: The PASCAL Visual Object Classes Challenge 2007 (VOC2007) Results – ident: ref8 doi: 10.1109/CVPR.2007.383222 – start-page: 143 year: 0 ident: ref35 article-title: Improving the fisher kernel for large-scale image classification publication-title: Proc Eur Conf Comput Vis – ident: ref29 doi: 10.1016/j.cviu.2005.09.012
SSID	ssj0014516
Score	2.4428318
Snippet	In image classification tasks, one of the most successful algorithms is the bag-of-features (BoFs) model. Although the BoF model has many advantages, such as...
SourceID	proquest pubmed pascalfrancis crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1994
SubjectTerms	Accuracy Algorithms Applied sciences Basic converters Construction Exact sciences and technology Feature extraction Image classification Image edge detection Image processing Information, signal and communications theory Mathematical models Oxygen steel making Pattern recognition Quantization (signal) Shape Signal and communications theory Signal processing Signal representation. Spectral analysis Signal, noise Telecommunications and information theory Texture Vectors Visualization
Title	Spatial Pooling of Heterogeneous Features for Image Classification
URI	https://ieeexplore.ieee.org/document/6757045 https://www.ncbi.nlm.nih.gov/pubmed/24710400 https://www.proquest.com/docview/1512676656 https://www.proquest.com/docview/1514431488 https://www.proquest.com/docview/1531003637
Volume	23
WOSCitedRecordID	wos000334526000003&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: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1941-0042 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014516 issn: 1057-7149 databaseCode: RIE dateStart: 19920101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE
link	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV1Li9swEB52Qw_toftIH-5mgwq9FOpNbMuSfewuGxIoIYdtyc3IslQKbVziuL-_M7LibaANFHwwWAZ5Hp5vPOP5AN5hzDO8EiKMUqlDHseWioQ6rCKJ8c_GiXCjlL58kstltl7nqxP40P8LY4xxzWfmhk5dLb-qdUufyiYIbiVCkFM4lVJ2_2r1FQMinHWVzVSGEmH_viQ5zScPixX1cPEbwjJRRLx7Mb6TyXwPopGjV6HmSNWgfGxHbPFv5Oki0Ozs__Z-Ds890mQfO9O4gBOzuYQzjzqZ9-nmEp79MZJwCLfEUYw2yVY10fl8ZbVlc2qZqdHSTN02jEBji0k6Q7jLFj_wfcQcsyb1HDk1v4DPs_uHu3noeRZCzaXYhTJXeVRmKBPMLVKu8jI1Kufl1PLSqIzGB1iVlnFcpaYqc8yYtCiFNopKkIbz5CUMNvXGvAZWYcJoU4t-nWDYk1GZaOEmxkR2qiItA5js5V1oP4ScuDC-Fy4ZmeYFKqsgZRVeWQG87-_42Q3gOLJ2SILv13mZBzA-UGl_Pc5SPEQSwGiv48K7cFMQFBJSIN4N4G1_GZ2PKirKSZzW4ONjRpkdW0M1FLR53N6rzn4eN-DN8M3fN34FT-nxuv7KEQx229ZcwxP9a_et2Y7RC9bZ2HnBb3Ff_hE
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3da9RAEB9qFbQPrbZVU2tdwRfB9G6T_UgeVSx3eB73cErfwmazK4JepLnz7-_MZi9a0IKQh0A2sJmPzG8yk_kBvMKY50SjVMqltqnIMk9FQps2XGP881muwiilLzM9nxeXl-ViB94M_8I450LzmTun01DLb1q7oU9lIwS3GiHIHbgrhch4_7fWUDMgytlQ25Q61Qj8t0XJcTlaThfUxSXOCc1wTsx7Gb6VyYBvxKNAsELtkaZDCfme2uLf2DPEoIuD_9v9Q9iPWJO97Y3jEey41SEcRNzJold3h7D3x1DCI3hHLMVolWzREqHPV9Z6NqGmmRZtzbWbjhFs3GCazhDwsukPfCOxwK1JXUdB0cfw-eLD8v0kjUwLqRVarVNdmpLXBcoEswspTFlLZ0pRj72onSlogIA3ss6yRrqmLjFnsqpW1hkqQjoh8sewu2pX7imwBlNGLz16do6BT_M6tyrMjOF-bLjVCYy28q5sHENObBjfq5COjMsKlVWRsqqorAReD3f87Edw3LL2iAQ_rIsyT-DshkqH61kh8VB5AqdbHVfRibuKwJDSChFvAi-Hy-h-VFMxQeK0Bh8fc8ritjVURUGrx-096e3n9waiGZ78feMv4P5k-WlWzabzj8_gAT1q3215Crvrq417Dvfsr_W37uos-MI1zosAfw
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=Spatial+Pooling+of+Heterogeneous+Features+for+Image+Classification&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=LINGXI+XIE&rft.au=QI+TIAN&rft.au=MENG+WANG&rft.au=BO+ZHANG&rft.date=2014-05-01&rft.pub=Institute+of+Electrical+and+Electronics+Engineers&rft.issn=1057-7149&rft.volume=23&rft.issue=5-6&rft.spage=1994&rft.epage=2008&rft_id=info:doi/10.1109%2Ftip.2014.2310117&rft.externalDBID=n%2Fa&rft.externalDocID=28528563
thumbnail_l	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=1057-7149&client=summon
thumbnail_m	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=1057-7149&client=summon
thumbnail_s	http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=1057-7149&client=summon