Learning a Family of Detectors via Multiplicative Kernels
Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two k...
Saved in:
| Published in | IEEE transactions on pattern analysis and machine intelligence Vol. 33; no. 3; pp. 514 - 530 |
|---|---|
| Main Authors | , , , |
| Format | Journal Article |
| Language | English |
| Published |
Los Alamitos, CA
IEEE
01.03.2011
IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Subjects | |
| Online Access | Get full text |
| ISSN | 0162-8828 1939-3539 1939-3539 |
| DOI | 10.1109/TPAMI.2010.117 |
Cover
| Abstract | Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two kernel functions. Model training is accomplished via standard SVM learning. When the foreground object masks are provided in training, the detectors can also produce object segmentations. A tracking-by-detection framework to recover foreground state in video sequences is also proposed with our model. The advantages of our method are demonstrated on tasks of object detection, view angle estimation, and tracking. Our approach compares favorably to existing methods on hand and vehicle detection tasks. Quantitative tracking results are given on sequences of moving vehicles and human faces. |
|---|---|
| AbstractList | Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two kernel functions. Model training is accomplished via standard SVM learning. When the foreground object masks are provided in training, the detectors can also produce object segmentations. A tracking-by-detection framework to recover foreground state in video sequences is also proposed with our model. The advantages of our method are demonstrated on tasks of object detection, view angle estimation, and tracking. Our approach compares favorably to existing methods on hand and vehicle detection tasks. Quantitative tracking results are given on sequences of moving vehicles and human faces.Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two kernel functions. Model training is accomplished via standard SVM learning. When the foreground object masks are provided in training, the detectors can also produce object segmentations. A tracking-by-detection framework to recover foreground state in video sequences is also proposed with our model. The advantages of our method are demonstrated on tasks of object detection, view angle estimation, and tracking. Our approach compares favorably to existing methods on hand and vehicle detection tasks. Quantitative tracking results are given on sequences of moving vehicles and human faces. Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification (detection) and within-class classification of the foreground class (pose estimation) can be jointly learned in a multiplicative form of two kernel functions. Model training is accomplished via standard SVM learning. When the foreground object masks are provided in training, the detectors can also produce object segmentations. A tracking-by-detection framework to recover foreground state in video sequences is also proposed with our model. The advantages of our method are demonstrated on tasks of object detection, view angle estimation, and tracking. Our approach compares favorably to existing methods on hand and vehicle detection tasks. Quantitative tracking results are given on sequences of moving vehicles and human faces. |
| Author | Thangali, Ashwin Ablavsky, Vitaly Sclaroff, Stan Quan Yuan |
| Author_xml | – sequence: 1 surname: Quan Yuan fullname: Quan Yuan email: quan.yuan@am.sony.com organization: US Res. Center, Sony Electron., Inc., San Jose, CA, USA – sequence: 2 givenname: Ashwin surname: Thangali fullname: Thangali, Ashwin email: tvashwin@cs.bu.edu organization: Comput. Sci. Dept., Boston Univ., Boston, MA, USA – sequence: 3 givenname: Vitaly surname: Ablavsky fullname: Ablavsky, Vitaly email: ablavsky@cs.bu.edu organization: Comput. Sci. Dept., Boston Univ., Boston, MA, USA – sequence: 4 givenname: Stan surname: Sclaroff fullname: Sclaroff, Stan email: sclaroffj@cs.bu.edu organization: Comput. Sci. Dept., Boston Univ., Boston, MA, USA |
| BackLink | http://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=23854089$$DView record in Pascal Francis https://www.ncbi.nlm.nih.gov/pubmed/20548107$$D View this record in MEDLINE/PubMed |
| BookMark | eNqNkd1rFDEUxYNU7Lb11RdBhoL4NGu-Px5LtVrcYh_a55DN3JGUbGZNZgr97810txUKguQhXPidk5tzjtBBGhIg9I7gJSHYfL65Pru6XFL8OKtXaEEMMy0TzBygBSaStlpTfYiOSrnDmHCB2Rt0SLHgmmC1QGYFLqeQfjWuuXCbEB-aoW--wAh-HHJp7oNrrqY4hm0M3o3hHpofkBPEcoJe9y4WeLu_j9Htxdeb8-_t6ue3y_OzVeu5NGPrJAbAwCnXsjPCd7LDvTFCSKkoBabq6STriBBeKbUWnq6l7jvdw9oQrtgx-rTz3ebh9wRltJtQPMToEgxTsVoyzqjS5D9IUnPRdCZPX5B3w5RT_YbVdWuqpJ4f_rCHpvUGOrvNYePyg30KrwIf94Ar3sU-u-RD-csxLTjWpnJ8x_k8lJKhtz6MNcshjdmFaAm2c5f2sUs7d1nn2X75Qvbk_E_B-50gAMAzXJdVgnL2B0bBpTg |
| CODEN | ITPIDJ |
| CitedBy_id | crossref_primary_10_1109_TITS_2013_2264314 crossref_primary_10_1109_TITS_2018_2838132 crossref_primary_10_1109_TCSVT_2014_2358031 crossref_primary_10_1109_MIS_2020_2993557 crossref_primary_10_1177_1729881417692311 crossref_primary_10_3390_s151229838 crossref_primary_10_1049_iet_ipr_2015_0333 crossref_primary_10_1109_TITS_2013_2266661 crossref_primary_10_1587_transfun_E98_A_1727 crossref_primary_10_1109_ACCESS_2021_3093698 crossref_primary_10_1109_TITS_2015_2466109 crossref_primary_10_1016_j_eswa_2015_01_032 crossref_primary_10_1109_TITS_2016_2597299 crossref_primary_10_1109_TITS_2020_3041278 crossref_primary_10_1016_j_image_2018_09_002 crossref_primary_10_1155_2019_3808064 crossref_primary_10_1007_s11042_020_08757_1 crossref_primary_10_1186_s13640_016_0143_4 crossref_primary_10_1109_TITS_2015_2465296 crossref_primary_10_1007_s11042_023_16065_7 crossref_primary_10_3390_su13031210 crossref_primary_10_1109_TITS_2015_2413971 crossref_primary_10_1109_TCSVT_2013_2265571 crossref_primary_10_1109_TVT_2019_2961625 crossref_primary_10_1007_s10043_015_0067_8 crossref_primary_10_1109_TITS_2019_2918227 crossref_primary_10_2478_ttj_2019_0017 crossref_primary_10_1109_TITS_2020_2982804 crossref_primary_10_1109_TITS_2022_3160932 crossref_primary_10_1002_ett_4427 crossref_primary_10_1155_2021_5555121 |
| Cites_doi | 10.7551/mitpress/7503.003.0026 10.1109/CVPR.2005.249 10.1007/11736790_8 10.1023/A:1008078328650 10.1109/CVPR.2004.1315241 10.1109/TPAMI.2008.73 10.1007/3-540-45053-X_45 10.1007/978-3-540-76386-4_17 10.1007/3-540-45053-X_3 10.1007/s11263-007-0095-3 10.1109/CVPR.2007.383153 10.1109/CVPR.2007.383129 10.1109/CVPR.2004.1315063 10.1109/CVPR.2008.4587592 10.1109/ICCV.2009.5459346 10.1109/CVPR.2004.1315258 10.1109/CVPR.2003.1211500 10.1109/ICCV.2007.4409006 10.1023/A:1011179004708 10.7551/mitpress/1130.003.0015 10.1023/A:1022627411411 10.1109/TPAMI.2009.167 10.1023/A:1008162616689 10.1109/34.993558 10.1016/j.patrec.2008.08.016 10.1007/s11263-007-0090-8 10.1109/CVPR.2005.177 10.1109/TPAMI.2004.68 10.1007/978-3-540-24670-1_3 10.1007/s11263-008-0137-5 10.1109/ICCV.2007.4408875 10.1109/34.655647 10.1007/3-540-47967-8_8 10.1109/CVPR.2006.169 10.1109/CVPR.2007.383042 10.1109/CVPR.2008.4587583 10.1109/AFGR.2004.1301646 10.1109/CVPR.2006.193 10.1109/AFGR.2008.4813399 10.1109/TPAMI.2007.1011 10.1109/ICCV.2003.1238424 10.1023/B:VISI.0000013087.49260.fb 10.1023/B:VISI.0000042934.15159.49 10.1109/ICCV.2001.937691 10.1109/CVPR.2007.383146 10.1007/978-3-540-88682-2_2 10.1007/BF01421486 10.1109/ICCV.2003.1238467 10.1109/CVPR.2005.335 10.1109/CVPR.1994.323814 10.1126/science.290.5500.2323 10.1109/CVPR.1997.609407 10.1109/CVPRW.2006.114 |
| ContentType | Journal Article |
| Copyright | 2015 INIST-CNRS Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Mar 2011 |
| Copyright_xml | – notice: 2015 INIST-CNRS – notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) Mar 2011 |
| DBID | 97E RIA RIE AAYXX CITATION IQODW CGR CUY CVF ECM EIF NPM 7SC 7SP 8FD JQ2 L7M L~C L~D F28 FR3 7X8 |
| DOI | 10.1109/TPAMI.2010.117 |
| DatabaseName | IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef Pascal-Francis Medline MEDLINE MEDLINE (Ovid) MEDLINE MEDLINE 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 ANTE: Abstracts in New Technology & Engineering Engineering Research Database MEDLINE - Academic |
| DatabaseTitle | CrossRef MEDLINE Medline Complete MEDLINE with Full Text PubMed MEDLINE (Ovid) 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 Engineering Research Database ANTE: Abstracts in New Technology & Engineering MEDLINE - Academic |
| DatabaseTitleList | MEDLINE - Academic MEDLINE Technology Research Database Technology Research Database |
| Database_xml | – sequence: 1 dbid: NPM name: PubMed url: https://proxy.k.utb.cz/login?url=http://www.ncbi.nlm.nih.gov/entrez/query.fcgi?db=PubMed sourceTypes: Index Database – sequence: 2 dbid: EIF name: MEDLINE url: https://proxy.k.utb.cz/login?url=https://www.webofscience.com/wos/medline/basic-search sourceTypes: Index Database – sequence: 3 dbid: RIE name: IEEE Electronic Library (IEL) url: https://proxy.k.utb.cz/login?url=https://ieeexplore.ieee.org/ sourceTypes: Publisher |
| DeliveryMethod | fulltext_linktorsrc |
| Discipline | Engineering Computer Science Applied Sciences |
| EISSN | 1939-3539 |
| EndPage | 530 |
| ExternalDocumentID | 2246779801 20548107 23854089 10_1109_TPAMI_2010_117 5487524 |
| Genre | orig-research Research Support, U.S. Gov't, Non-P.H.S Journal Article |
| GroupedDBID | --- -DZ -~X .DC 0R~ 29I 4.4 53G 5GY 5VS 6IK 97E 9M8 AAJGR AARMG AASAJ AAWTH ABAZT ABFSI ABQJQ ABVLG ACGFO ACGFS ACIWK ACNCT ADRHT AENEX AETEA 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 FA8 HZ~ H~9 IBMZZ ICLAB IEDLZ IFIPE IFJZH IPLJI JAVBF LAI M43 MS~ O9- OCL P2P PQQKQ RIA RIE RNI RNS RXW RZB TAE TN5 UHB VH1 XJT ~02 AAYXX CITATION IQODW RIG AAYOK CGR CUY CVF ECM EIF NPM 7SC 7SP 8FD JQ2 L7M L~C L~D F28 FR3 7X8 |
| ID | FETCH-LOGICAL-c469t-a60ee0e42486d95cd6d0f995566722e37373d63d155c777b5c2b68fd8feb91473 |
| IEDL.DBID | RIE |
| ISSN | 0162-8828 1939-3539 |
| IngestDate | Sat Sep 27 19:49:17 EDT 2025 Thu Oct 02 06:48:26 EDT 2025 Sun Jun 29 16:13:39 EDT 2025 Thu Apr 03 07:10:24 EDT 2025 Mon Jul 21 09:18:28 EDT 2025 Thu Apr 24 22:52:09 EDT 2025 Wed Oct 01 06:42:38 EDT 2025 Tue Aug 26 17:18:00 EDT 2025 |
| IsPeerReviewed | true |
| IsScholarly | true |
| Issue | 3 |
| Keywords | Computer vision Target tracking Tracking Segmentation Mask Pattern recognition Object recognition Modeling Kernel method Posture Kernel function Surveillance Image sequence Scene analysis Facies Object detection pose estimation Vector support machine kernel methods object tracking Moving body |
| Language | English |
| License | https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html CC BY 4.0 |
| LinkModel | DirectLink |
| MergedId | FETCHMERGED-LOGICAL-c469t-a60ee0e42486d95cd6d0f995566722e37373d63d155c777b5c2b68fd8feb91473 |
| Notes | ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 ObjectType-Article-2 ObjectType-Feature-1 content type line 23 |
| PMID | 20548107 |
| PQID | 846927687 |
| PQPubID | 85458 |
| PageCount | 17 |
| ParticipantIDs | proquest_miscellaneous_863432781 ieee_primary_5487524 pubmed_primary_20548107 proquest_miscellaneous_861539821 crossref_primary_10_1109_TPAMI_2010_117 pascalfrancis_primary_23854089 crossref_citationtrail_10_1109_TPAMI_2010_117 proquest_journals_846927687 |
| ProviderPackageCode | CITATION AAYXX |
| PublicationCentury | 2000 |
| PublicationDate | 2011-03-01 |
| PublicationDateYYYYMMDD | 2011-03-01 |
| PublicationDate_xml | – month: 03 year: 2011 text: 2011-03-01 day: 01 |
| PublicationDecade | 2010 |
| PublicationPlace | Los Alamitos, CA |
| PublicationPlace_xml | – name: Los Alamitos, CA – name: United States – name: New York |
| PublicationTitle | IEEE transactions on pattern analysis and machine intelligence |
| PublicationTitleAbbrev | TPAMI |
| PublicationTitleAlternate | IEEE Trans Pattern Anal Mach Intell |
| PublicationYear | 2011 |
| Publisher | IEEE IEEE Computer Society The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| Publisher_xml | – name: IEEE – name: IEEE Computer Society – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE) |
| References | ref13 ref12 ref56 ref15 ref59 ref14 ref58 ref53 ref52 ref11 ref55 ref54 Platt (ref41) 1999 Neidle (ref33) 2003 ref17 ref16 ref19 ref18 Rosales (ref44) 2002 Viola (ref57) ref51 ref50 ref46 ref45 ref48 ref47 ref42 Nocedal (ref34) 2006 ref49 ref8 ref7 ref9 ref4 ref3 ref6 ref5 ref40 Rifkin (ref43) 2004 Marszalek (ref31) ref35 ref37 Osadchy (ref38) 2004 ref36 ref32 ref2 ref1 ref39 ref24 ref23 ref26 ref25 ref20 ref22 ref21 Everingham (ref30) 2006 ref28 ref27 ref29 Zhu (ref63) 2007 ref60 ref62 ref61 Crasborn (ref10) 2004 |
| References_xml | – start-page: 101 year: 2004 ident: ref43 article-title: In Defense of One-vs-All Classification publication-title: J. Machine Learning Research – ident: ref5 doi: 10.7551/mitpress/7503.003.0026 – volume-title: technical report year: 2004 ident: ref10 article-title: ECHO Data Set for Sign Language of the Netherlands – ident: ref24 doi: 10.1109/CVPR.2005.249 – volume-title: Machine Learning Challenges. Evaluating Predictive Uncertainty, Visual Object Classification, and Recognising Textual Entailment year: 2006 ident: ref30 article-title: The 2005 PASCAL Visual Object Class Challenge doi: 10.1007/11736790_8 – ident: ref22 doi: 10.1023/A:1008078328650 – ident: ref55 doi: 10.1109/CVPR.2004.1315241 – ident: ref29 doi: 10.1109/TPAMI.2008.73 – ident: ref51 doi: 10.1007/3-540-45053-X_45 – ident: ref59 doi: 10.1007/978-3-540-76386-4_17 – ident: ref16 doi: 10.1007/3-540-45053-X_3 – ident: ref26 doi: 10.1007/s11263-007-0095-3 – ident: ref62 doi: 10.1109/CVPR.2007.383153 – ident: ref6 doi: 10.1109/CVPR.2007.383129 – ident: ref52 doi: 10.1109/CVPR.2004.1315063 – ident: ref13 doi: 10.1109/CVPR.2008.4587592 – ident: ref21 doi: 10.1109/ICCV.2009.5459346 – ident: ref1 doi: 10.1109/CVPR.2004.1315258 – ident: ref3 doi: 10.1109/CVPR.2003.1211500 – ident: ref60 doi: 10.1109/ICCV.2007.4409006 – volume-title: Advances in Neural Information Processing Systems year: 2002 ident: ref44 article-title: Learning Body Pose via Specialized Maps – ident: ref20 doi: 10.1023/A:1011179004708 – volume-title: SLLRP Signstream Databases year: 2003 ident: ref33 – ident: ref23 doi: 10.7551/mitpress/1130.003.0015 – ident: ref9 doi: 10.1023/A:1022627411411 – ident: ref14 doi: 10.1109/TPAMI.2009.167 – ident: ref39 doi: 10.1023/A:1008162616689 – ident: ref4 doi: 10.1109/34.993558 – ident: ref12 doi: 10.1016/j.patrec.2008.08.016 – ident: ref47 doi: 10.1007/s11263-007-0090-8 – volume-title: Advances in Neural Information Processing Systems year: 2004 ident: ref38 article-title: Synergistic Face Detection and Pose Estimation with Energy-Based Model – ident: ref11 doi: 10.1109/CVPR.2005.177 – ident: ref28 doi: 10.1109/TPAMI.2004.68 – ident: ref36 doi: 10.1007/978-3-540-24670-1_3 – ident: ref18 doi: 10.1007/s11263-008-0137-5 – volume-title: Numerical Optimization year: 2006 ident: ref34 – ident: ref56 doi: 10.1109/ICCV.2007.4408875 – ident: ref46 doi: 10.1109/34.655647 – ident: ref8 doi: 10.1007/3-540-47967-8_8 – volume-title: Advances in Large Margin Classifiers year: 1999 ident: ref41 article-title: Probabilistic Outputs for Support Vector Machines and Comparisons to Regularized Likelihood Methods – ident: ref53 doi: 10.1109/CVPR.2006.169 – ident: ref61 doi: 10.1109/CVPR.2007.383042 – volume-title: Advances in Neural Information Processing Systems year: 2007 ident: ref63 article-title: Rapid Inference on a Novel and/or Graph: Detection, Segmentation and Parsing of Articulated Deformable Objects in Cluttered Backgrounds – volume-title: Proc. Visual Recognition Challange Workshop, in Conjunction with IEEE Int’l Conf. Computer Vision ident: ref31 article-title: Learning Object Representations for Visual Object Class Recognition – ident: ref2 doi: 10.1109/CVPR.2008.4587583 – ident: ref37 doi: 10.1109/AFGR.2004.1301646 – ident: ref48 doi: 10.1109/CVPR.2006.193 – ident: ref17 doi: 10.1109/AFGR.2008.4813399 – ident: ref19 doi: 10.1109/TPAMI.2007.1011 – ident: ref49 doi: 10.1109/ICCV.2003.1238424 – ident: ref58 doi: 10.1023/B:VISI.0000013087.49260.fb – ident: ref15 doi: 10.1023/B:VISI.0000042934.15159.49 – ident: ref27 doi: 10.1109/ICCV.2001.937691 – ident: ref25 doi: 10.1109/CVPR.2007.383146 – ident: ref7 doi: 10.1007/978-3-540-88682-2_2 – ident: ref32 doi: 10.1007/BF01421486 – volume-title: Proc. IEEE Conf. Computer Vision and Pattern Recognition ident: ref57 article-title: Fast Multi-View Face Detection – ident: ref54 doi: 10.1109/ICCV.2003.1238467 – ident: ref42 doi: 10.1109/CVPR.2005.335 – ident: ref40 doi: 10.1109/CVPR.1994.323814 – ident: ref45 doi: 10.1126/science.290.5500.2323 – ident: ref50 doi: 10.1109/CVPR.1997.609407 – ident: ref35 doi: 10.1109/CVPRW.2006.114 |
| SSID | ssj0014503 |
| Score | 2.2953851 |
| Snippet | Object detection is challenging when the object class exhibits large within-class variations. In this work, we show that foreground-background classification... |
| SourceID | proquest pubmed pascalfrancis crossref ieee |
| SourceType | Aggregation Database Index Database Enrichment Source Publisher |
| StartPage | 514 |
| SubjectTerms | Algorithms Applied sciences Artificial Intelligence Classification Computer science; control theory; systems Computer Simulation Detectors Exact sciences and technology Humans Image Enhancement - methods Image Interpretation, Computer-Assisted - instrumentation Imaging, Three-Dimensional - instrumentation Kernel kernel methods Learning Markov Chains Mathematical models Motion Motor Vehicles Numerical Analysis, Computer-Assisted - instrumentation Object detection Object recognition Object segmentation object tracking Pattern Recognition, Automated - methods Pattern recognition. Digital image processing. Computational geometry Phantoms, Imaging pose estimation Reproducibility of Results Sensitivity and Specificity Subtraction Technique - instrumentation Support vector machine classification Support vector machines Tasks Tracking Training Vehicle detection Vehicles Video sequences |
| Title | Learning a Family of Detectors via Multiplicative Kernels |
| URI | https://ieeexplore.ieee.org/document/5487524 https://www.ncbi.nlm.nih.gov/pubmed/20548107 https://www.proquest.com/docview/846927687 https://www.proquest.com/docview/861539821 https://www.proquest.com/docview/863432781 |
| Volume | 33 |
| hasFullText | 1 |
| inHoldings | 1 |
| isFullTextHit | |
| isPrint | |
| journalDatabaseRights | – providerCode: PRVIEE databaseName: IEEE Electronic Library (IEL) customDbUrl: eissn: 1939-3539 dateEnd: 99991231 omitProxy: false ssIdentifier: ssj0014503 issn: 0162-8828 databaseCode: RIE dateStart: 19790101 isFulltext: true titleUrlDefault: https://ieeexplore.ieee.org/ providerName: IEEE |
| link | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Lb9QwEB61PcGBlhbotlD5gMSFbBOv48exAqoCWsShlXqLHHuCEChbdbM99Nd3_NhQEEUol0ge5eHxyN_Y4-8DeE05A00TnSu0kbYQgWyo9RR4znbe8BIt5-E08vyLPLsQny7ryw14O56FQcRYfIbTcBv38v3CrcJS2XFE11xswqbSMp3VGncMRB1VkAnBUIRTGpEJGqvSHJ9_PZl_TFVcVRVU9zjhFF0FBdl7c1EUVwmlkXZJvdMlWYuHcWecf063Yb7-8lR28mO6Gtqpu_2D1PF_f20HnmQgyk7SyHkKG9jvwvZa5IHlmN-Fx_cYC_fAZD7Wb8yypJnBFh17j0Nc_F-ym--WzVONYlwMvEH2Ga97moCfwcXph_N3Z0VWXygcpcxDYWWJWKLgQktvauelLztjasJ_inOcKbq8nHkCJE4p1daOt1J3XnfYmkqo2XPY6hc97gOrtZwJG2h9CJ5J4VuDYbdXKt9qGipuAsXaD43L1ORBIeNnE1OU0jTRhU1wYWAnn8Cb0f4qkXI8aLkX-nq0yt08gaPf3Dy2E4AhCKvNBA7Xfm9yUC8bgmqGU3pGT2VjK0Vj2GKxPS5WZBLws9G8-pdJOMurNJm8SAPq19vzuDz4-1cfwqO0oh0q4F7C1nC9wlcEiYb2KMbCHZBeA2I |
| linkProvider | IEEE |
| linkToHtml | http://utb.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwjV1Nb9QwEB2VcoAeKLRQlpbiAxIXsk28jmMfq5ZqS5uKw1bqLXLsSYVAWdTN9sCvZ2xn04IoQrlE8igfHo_8xh6_B_CecgaaJhqbKC1NIjzZUO0o8KxpnOYpGs79aeTyQk4vxeer_GoNPg5nYRAxFJ_h2N-GvXw3t0u_VHYQ0DUXj-BxLoTI42mtYc9A5EEHmTAMxTglEj1FY5bqg9mXw_I01nFlmdfd44RUVOY1ZO_NRkFexRdHmgX1TxOFLR5GnmEGOtmEcvXtsfDk23jZ1WP78w9ax__9uefwrIei7DCOnRewhu0WbK5kHlgf9VuwcY-zcBt0z8h6zQyLqhls3rBj7MLy_4LdfjWsjFWKYTnwFtkZ3rQ0Bb-Ey5NPs6Np0usvJJaS5i4xMkVMUXChpNO5ddKljdY5IcCCc5wUdDk5cQRJbFEUdW55LVXjVIO1zkQxeQXr7bzF18ByJSfCeGIfAmhSuFqj3--VhasVDRY7gmTlh8r25OReI-N7FZKUVFfBhZV3oecnH8GHwf5HpOV40HLb9_Vg1XfzCPZ_c_PQThCGQKzSI9hd-b3qw3pREVjTnBI0eiobWike_SaLaXG-JBOPoLXi2b9M_GneQpHJThxQd2_vx-Wbv3_1O3gynZXn1fnpxdkuPI3r274ebg_Wu5slviWA1NX7IS5-AUifBq8 |
| 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+a+Family+of+Detectors+via+Multiplicative+Kernels&rft.jtitle=IEEE+transactions+on+pattern+analysis+and+machine+intelligence&rft.au=QUAN+YUAN&rft.au=THANGALI%2C+Ashwin&rft.au=ABLAVSKY%2C+Vitaly&rft.au=SCLAROFF%2C+Stan&rft.date=2011-03-01&rft.pub=IEEE+Computer+Society&rft.issn=0162-8828&rft.volume=33&rft.issue=3&rft.spage=514&rft.epage=530&rft_id=info:doi/10.1109%2FTPAMI.2010.117&rft.externalDBID=n%2Fa&rft.externalDocID=23854089 |
| thumbnail_l | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/lc.gif&issn=0162-8828&client=summon |
| thumbnail_m | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/mc.gif&issn=0162-8828&client=summon |
| thumbnail_s | http://covers-cdn.summon.serialssolutions.com/index.aspx?isbn=/sc.gif&issn=0162-8828&client=summon |