Supervised Mixed Norm Autoencoder for Kinship Verification in Unconstrained Videos

Identifying kinship relations has garnered interest due to several applications such as organizing and tagging the enormous amount of videos being uploaded on the Internet. Existing research in kinship verification primarily focuses on kinship prediction with image pairs. In this research, we propos...

Full description

Saved in:

Bibliographic Details
Published in:	IEEE transactions on image processing Vol. 28; no. 3; pp. 1329 - 1341
Main Authors:	Kohli, Naman, Yadav, Daksha, Vatsa, Mayank, Singh, Richa, Noore, Afzel
Format:	Journal Article
Language:	English
Published:	United States IEEE 01.03.2019 The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:	Algorithms Feature extraction Frames (data processing) Image reconstruction Lighting Machine learning Measurement Occlusion Videos Weight
ISSN:	1057-7149, 1941-0042, 1941-0042
Online Access:	Get full text
Tags:	Add Tag No Tags, Be the first to tag this record!

Abstract	Identifying kinship relations has garnered interest due to several applications such as organizing and tagging the enormous amount of videos being uploaded on the Internet. Existing research in kinship verification primarily focuses on kinship prediction with image pairs. In this research, we propose a new deep learning framework for kinship verification in unconstrained videos using a novel Supervised Mixed Norm AutoEncoder (SMNAE). This new autoencoder formulation introduces class-specific sparsity in the weight matrix. The proposed three-stage SMNAE based kinship verification framework utilizes the learned spatio-temporal representation in the video frames for verifying kinship in a pair of videos. A new kinship video (KIVI) database of more than 500 individuals with variations due to illumination, pose, occlusion, ethnicity, and expression is collected for this research. It comprises a total of 355 true kin video pairs with over 250 000 still frames. The effectiveness of the proposed framework is demonstrated on the KIVI database and six existing kinship databases. On the KIVI database, SMNAE yields video-based kinship verification accuracy of 83.18% which is at least 3.2% better than existing algorithms. The algorithm is also evaluated on six publicly available kinship databases and compared with best reported results. It is observed that the proposed SMNAE consistently yields best results on all the databases.
AbstractList	Identifying kinship relations has garnered interest due to several applications such as organizing and tagging the enormous amount of videos being uploaded on the Internet. Existing research in kinship verification primarily focuses on kinship prediction with image pairs. In this research, we propose a new deep learning framework for kinship verification in unconstrained videos using a novel Supervised Mixed Norm AutoEncoder (SMNAE). This new autoencoder formulation introduces class-specific sparsity in the weight matrix. The proposed three-stage SMNAE based kinship verification framework utilizes the learned spatio-temporal representation in the video frames for verifying kinship in a pair of videos. A new kinship video (KIVI) database of more than 500 individuals with variations due to illumination, pose, occlusion, ethnicity, and expression is collected for this research. It comprises a total of 355 true kin video pairs with over 250 000 still frames. The effectiveness of the proposed framework is demonstrated on the KIVI database and six existing kinship databases. On the KIVI database, SMNAE yields video-based kinship verification accuracy of 83.18% which is at least 3.2% better than existing algorithms. The algorithm is also evaluated on six publicly available kinship databases and compared with best reported results. It is observed that the proposed SMNAE consistently yields best results on all the databases. Identifying kinship relations has garnered interest due to several applications such as organizing and tagging the enormous amount of videos being uploaded on the Internet. Existing research in kinship verification primarily focuses on kinship prediction with image pairs. In this research, we propose a new deep learning framework for kinship verification in unconstrained videos using a novel Supervised Mixed Norm regularization Autoencoder (SMNAE). This new autoencoder formulation introduces class-specific sparsity in the weight matrix. The proposed three-stage SMNAE based kinship verification framework utilizes the learned spatio-temporal representation in the video frames for verifying kinship in a pair of videos. A new kinship video (KIVI) database of more than 500 individuals with variations due to illumination, pose, occlusion, ethnicity, and expression is collected for this research. It comprises a total of 355 true kin video pairs with over 250,000 still frames. The effectiveness of the proposed framework is demonstrated on the KIVI database and six existing kinship databases. On the KIVI database, SMNAE yields video-based kinship verification accuracy of 83.18% which is at least 3.2% better than existing algorithms. The algorithm is also evaluated on six publicly available kinship databases and compared with best reported results. It is observed that the proposed SMNAE consistently yields best results on all the databases.Identifying kinship relations has garnered interest due to several applications such as organizing and tagging the enormous amount of videos being uploaded on the Internet. Existing research in kinship verification primarily focuses on kinship prediction with image pairs. In this research, we propose a new deep learning framework for kinship verification in unconstrained videos using a novel Supervised Mixed Norm regularization Autoencoder (SMNAE). This new autoencoder formulation introduces class-specific sparsity in the weight matrix. The proposed three-stage SMNAE based kinship verification framework utilizes the learned spatio-temporal representation in the video frames for verifying kinship in a pair of videos. A new kinship video (KIVI) database of more than 500 individuals with variations due to illumination, pose, occlusion, ethnicity, and expression is collected for this research. It comprises a total of 355 true kin video pairs with over 250,000 still frames. The effectiveness of the proposed framework is demonstrated on the KIVI database and six existing kinship databases. On the KIVI database, SMNAE yields video-based kinship verification accuracy of 83.18% which is at least 3.2% better than existing algorithms. The algorithm is also evaluated on six publicly available kinship databases and compared with best reported results. It is observed that the proposed SMNAE consistently yields best results on all the databases. Identifying kinship relations has garnered interest due to several applications such as organizing and tagging the enormous amount of videos being uploaded on the Internet. Existing research in kinship verification primarily focuses on kinship prediction with image pairs. In this research, we propose a new deep learning framework for kinship verification in unconstrained videos using a novel Supervised Mixed Norm regularization Autoencoder (SMNAE). This new autoencoder formulation introduces class-specific sparsity in the weight matrix. The proposed three-stage SMNAE based kinship verification framework utilizes the learned spatio-temporal representation in the video frames for verifying kinship in a pair of videos. A new kinship video (KIVI) database of more than 500 individuals with variations due to illumination, pose, occlusion, ethnicity, and expression is collected for this research. It comprises a total of 355 true kin video pairs with over 250,000 still frames. The effectiveness of the proposed framework is demonstrated on the KIVI database and six existing kinship databases. On the KIVI database, SMNAE yields video-based kinship verification accuracy of 83.18% which is at least 3.2% better than existing algorithms. The algorithm is also evaluated on six publicly available kinship databases and compared with best reported results. It is observed that the proposed SMNAE consistently yields best results on all the databases.
Author	Singh, Richa Kohli, Naman Vatsa, Mayank Noore, Afzel Yadav, Daksha
Author_xml	– sequence: 1 givenname: Naman surname: Kohli fullname: Kohli, Naman email: nakohli@mix.wvu.edu organization: Lane Dept. of Comput. Sci. & Electr. Eng., West Virginia Univ., Morgantown, WV, USA – sequence: 2 givenname: Daksha surname: Yadav fullname: Yadav, Daksha email: dayadav@mix.wvu.edu organization: Lane Dept. of Comput. Sci. & Electr. Eng., West Virginia Univ., Morgantown, WV, USA – sequence: 3 givenname: Mayank surname: Vatsa fullname: Vatsa, Mayank email: mayank@iiitd.ac.in organization: Indraprastha Inst. of Inf. Technol. Delhi, New Delhi, India – sequence: 4 givenname: Richa surname: Singh fullname: Singh, Richa email: rsingh@iiitd.ac.in organization: Indraprastha Inst. of Inf. Technol. Delhi, New Delhi, India – sequence: 5 givenname: Afzel surname: Noore fullname: Noore, Afzel email: afzel.noore@tamuk.edu organization: Texas A&M Univ. - Kingsville, Kingsville, TX, USA
BackLink	https://www.ncbi.nlm.nih.gov/pubmed/29993718$$D View this record in MEDLINE/PubMed
BookMark	eNp9kTtPHDEURq2IiHcfKRIaiSbNbK4fM7ZLhCBBAYISoLWM51ox2rUXewYl_z7e7IaCgsa-xTn21fftka2YIhLygcKMUtCfby9uZgyomjElQCl4R3apFrQFEGyrztDJVlKhd8heKY8AVHS03yY7TGvNJVW75MfPaYn5ORQcmqvwu57XKS-ak2lMGF0aMDc-5eZbiOVXWDb3mIMPzo4hxSbE5q4ysYzZhljV-zBgKgfkvbfzgoebe5_cnZ_dnn5tL79_uTg9uWwdF3JsKXDKGTiPlvmBcic6572wHagHC7KX0EuPkrOBQa95Z6nHOkvHQQjNB75PPq3fXeb0NGEZzSIUh_O5jZimYqqmuOCgRUWPX6GPacqxbmcY5bLrhNKyUkcbanpY4GCWOSxs_mP-p1UBWAMup1Iy-heEglkVYmohZlWI2RRSlf6V4sL4L75VaPO3xI9rMSDiyz-K952ikv8F1IOWFw
CODEN	IIPRE4
CitedBy_id	crossref_primary_10_1109_TCYB_2019_2923756 crossref_primary_10_1016_j_neunet_2022_03_020 crossref_primary_10_1016_j_patcog_2023_109742 crossref_primary_10_1109_TPAMI_2021_3063078 crossref_primary_10_1007_s11042_025_20762_w crossref_primary_10_1109_TIP_2021_3104192 crossref_primary_10_1007_s11263_022_01605_9 crossref_primary_10_1016_j_compeleceng_2024_109375 crossref_primary_10_1016_j_ins_2021_07_046 crossref_primary_10_1109_ACCESS_2025_3582532 crossref_primary_10_1109_TIP_2020_3034027 crossref_primary_10_1109_ACCESS_2025_3605630 crossref_primary_10_1109_TPAMI_2020_3036993 crossref_primary_10_1109_TIP_2021_3077111 crossref_primary_10_1007_s11042_021_11466_y crossref_primary_10_1007_s13748_025_00402_y crossref_primary_10_1016_j_imavis_2023_104727 crossref_primary_10_1016_j_image_2022_116829 crossref_primary_10_1109_ACCESS_2019_2929939 crossref_primary_10_1109_TCYB_2022_3220040 crossref_primary_10_1007_s00371_024_03493_1 crossref_primary_10_1016_j_neucom_2022_12_031 crossref_primary_10_1016_j_jvcir_2021_103265 crossref_primary_10_1016_j_jmsy_2020_05_005 crossref_primary_10_1016_j_neucom_2019_09_089
Cites_doi	10.1109/TMM.2012.2187436 10.1145/2393347.2396297 10.1145/2072298.2071911 10.1109/ICIP.2017.8296446 10.1109/ICASSP.2008.4518498 10.1007/BF00994018 10.1109/ICPR.2014.735 10.1109/ICCV.2013.189 10.1109/ICIP.2016.7532894 10.1109/TPAMI.2016.2522416 10.1109/TIP.2016.2609811 10.1109/FG.2017.35 10.1109/TIFS.2017.2668221 10.1109/TPAMI.2007.1110 10.1109/LSP.2007.898300 10.1109/ICCVW.2011.6130343 10.1109/TPAMI.2016.2569436 10.1109/BTAS.2014.6996299 10.1109/TIP.2017.2717505 10.1109/ICIP.2010.5652590 10.1109/TMM.2015.2461462 10.1145/2964284.2967219 10.1145/2502081.2502142 10.1109/ICCV.2017.269 10.1016/j.imavis.2016.08.009 10.1109/CVPR.2014.227 10.1109/BTAS.2012.6374584 10.1109/WIFS.2016.7823901 10.1109/ICIP.2013.6738614 10.1109/ACCESS.2016.2635147 10.1109/TCYB.2014.2376934 10.1016/j.inffus.2015.08.006 10.1098/rspb.2009.0677 10.1109/TIFS.2014.2327757 10.1109/TIFS.2015.2446438 10.1016/j.imavis.2017.01.005 10.1016/j.cviu.2017.12.003 10.1109/LSP.2015.2490805 10.1109/TPAMI.2013.134 10.1007/978-3-319-41501-7_60 10.1109/CVPRW.2011.5981801 10.1109/BTAS.2015.7358768
ContentType	Journal Article
Copyright	Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
Copyright_xml	– notice: Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2019
DBID	97E RIA RIE AAYXX CITATION NPM 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
DOI	10.1109/TIP.2018.2840880
DatabaseName	IEEE All-Society Periodicals Package (ASPP) 2005–Present IEEE All-Society Periodicals Package (ASPP) 1998–Present IEEE Electronic Library (IEL) CrossRef 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
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
DatabaseTitleList	Technology Research Database MEDLINE - Academic PubMed
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	1341
ExternalDocumentID	29993718 10_1109_TIP_2018_2840880 8365817
Genre	orig-research Journal Article
GrantInformation_xml	– fundername: Nvidia funderid: 10.13039/100007065
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 NPM RIG Z5M 7SC 7SP 8FD JQ2 L7M L~C L~D 7X8
ID	FETCH-LOGICAL-c347t-1031320cfea2fd13c45cff4a508ba0767067fe732d206935a1fe2d27c304493d3
IEDL.DBID	RIE
ISICitedReferencesCount	32
ISICitedReferencesURI	http://www.webofscience.com/api/gateway?GWVersion=2&SrcApp=Summon&SrcAuth=ProQuest&DestLinkType=CitingArticles&DestApp=WOS_CPL&KeyUT=000451258900002&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	Mon Sep 29 05:33:05 EDT 2025 Mon Jun 30 10:22:22 EDT 2025 Wed Feb 19 02:09:29 EST 2025 Tue Nov 18 22:00:27 EST 2025 Sat Nov 29 03:21:08 EST 2025 Wed Aug 27 02:44:22 EDT 2025
IsPeerReviewed	true
IsScholarly	true
Issue	3
Language	English
License	https://ieeexplore.ieee.org/Xplorehelp/downloads/license-information/IEEE.html https://doi.org/10.15223/policy-029 https://doi.org/10.15223/policy-037
LinkModel	DirectLink
MergedId	FETCHMERGED-LOGICAL-c347t-1031320cfea2fd13c45cff4a508ba0767067fe732d206935a1fe2d27c304493d3
Notes	ObjectType-Article-1 SourceType-Scholarly Journals-1 ObjectType-Feature-2 content type line 14 content type line 23
ORCID	0000-0001-5952-2274
PMID	29993718
PQID	2137554897
PQPubID	85429
PageCount	13
ParticipantIDs	pubmed_primary_29993718 crossref_primary_10_1109_TIP_2018_2840880 proquest_journals_2137554897 crossref_citationtrail_10_1109_TIP_2018_2840880 proquest_miscellaneous_2068343094 ieee_primary_8365817
PublicationCentury	2000
PublicationDate	2019-03-01
PublicationDateYYYYMMDD	2019-03-01
PublicationDate_xml	– month: 03 year: 2019 text: 2019-03-01 day: 01
PublicationDecade	2010
PublicationPlace	United States
PublicationPlace_xml	– name: United States – name: New York
PublicationTitle	IEEE transactions on image processing
PublicationTitleAbbrev	TIP
PublicationTitleAlternate	IEEE Trans Image Process
PublicationYear	2019
Publisher	IEEE The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Publisher_xml	– name: IEEE – name: The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
References	ref12 ref15 ref52 ref11 ref10 ref17 ref16 ref19 ref18 ref51 ref50 hu (ref14) 2014 ref45 ref47 ref41 ref49 ref8 ref7 ref4 ref3 ref6 ref5 ref40 boutellaa (ref46) 2017 lu (ref13) 2014; 36 ref35 ref34 ref37 wagner (ref2) 2017 ref31 ref30 ref33 ref32 nesterov (ref43) 2007 ref39 zhang (ref44) 2014 ref38 parkhi (ref48) 2015 kofman (ref1) 2016 ref24 ref23 ref26 ref25 ref20 ref22 ref21 ref28 ref27 ref29 ng (ref36) 2011 xia (ref9) 2011 jenatton (ref42) 2010
References_xml	– ident: ref11 doi: 10.1109/TMM.2012.2187436 – ident: ref5 doi: 10.1145/2393347.2396297 – ident: ref4 doi: 10.1145/2072298.2071911 – ident: ref30 doi: 10.1109/ICIP.2017.8296446 – ident: ref40 doi: 10.1109/ICASSP.2008.4518498 – ident: ref45 doi: 10.1007/BF00994018 – year: 2017 ident: ref46 publication-title: Kinship verification from videos using spatio-temporal texture features and deep learning – start-page: 487 year: 2010 ident: ref42 article-title: Proximal methods for sparse hierarchical dictionary learning publication-title: Proc Int Conf Mach Learn – ident: ref17 doi: 10.1109/ICPR.2014.735 – ident: ref33 doi: 10.1109/ICCV.2013.189 – ident: ref26 doi: 10.1109/ICIP.2016.7532894 – ident: ref25 doi: 10.1109/TPAMI.2016.2522416 – start-page: 1 year: 2011 ident: ref36 article-title: Sparse autoencoder publication-title: Cs294a lecture notes – ident: ref31 doi: 10.1109/TIP.2016.2609811 – ident: ref28 doi: 10.1109/FG.2017.35 – start-page: 2539 year: 2011 ident: ref9 article-title: Kinship verification through transfer learning publication-title: Proc Int Joint Conf Artif Intell – ident: ref52 doi: 10.1109/TIFS.2017.2668221 – ident: ref47 doi: 10.1109/TPAMI.2007.1110 – year: 2017 ident: ref2 publication-title: Facebook Says Video Is Huge-100-Million-Hours-Per-Day Huge – ident: ref39 doi: 10.1109/LSP.2007.898300 – ident: ref35 doi: 10.1109/ICCVW.2011.6130343 – ident: ref38 doi: 10.1109/TPAMI.2016.2569436 – year: 2007 ident: ref43 article-title: Gradient methods for minimizing composite objective function – ident: ref51 doi: 10.1109/BTAS.2014.6996299 – ident: ref29 doi: 10.1109/TIP.2017.2717505 – ident: ref3 doi: 10.1109/ICIP.2010.5652590 – ident: ref20 doi: 10.1109/TMM.2015.2461462 – ident: ref22 doi: 10.1145/2964284.2967219 – start-page: 1355 year: 2014 ident: ref44 article-title: Feature selection at the discrete limit publication-title: Proc AAAI Conf Artif Intell – ident: ref41 doi: 10.1145/2502081.2502142 – ident: ref34 doi: 10.1109/ICCV.2017.269 – ident: ref24 doi: 10.1016/j.imavis.2016.08.009 – start-page: 252 year: 2014 ident: ref14 article-title: Large margin multi-metric learning for face and kinship verification in the wild publication-title: Proc Asian Conf Comput Vis – ident: ref16 doi: 10.1109/CVPR.2014.227 – ident: ref6 doi: 10.1109/BTAS.2012.6374584 – ident: ref8 doi: 10.1109/WIFS.2016.7823901 – ident: ref12 doi: 10.1109/ICIP.2013.6738614 – ident: ref23 doi: 10.1109/ACCESS.2016.2635147 – ident: ref18 doi: 10.1109/TCYB.2014.2376934 – ident: ref21 doi: 10.1016/j.inffus.2015.08.006 – ident: ref50 doi: 10.1098/rspb.2009.0677 – ident: ref15 doi: 10.1109/TIFS.2014.2327757 – ident: ref37 doi: 10.1109/TIFS.2015.2446438 – ident: ref49 doi: 10.1016/j.imavis.2017.01.005 – start-page: 41.1 year: 2015 ident: ref48 article-title: Deep face recognition publication-title: Proc Brit Mach Vis Conf – ident: ref32 doi: 10.1016/j.cviu.2017.12.003 – ident: ref19 doi: 10.1109/LSP.2015.2490805 – volume: 36 start-page: 331 year: 2014 ident: ref13 article-title: Neighborhood repulsed metric learning for kinship verification publication-title: IEEE Trans Pattern Anal Mach Intell doi: 10.1109/TPAMI.2013.134 – ident: ref27 doi: 10.1007/978-3-319-41501-7_60 – ident: ref10 doi: 10.1109/CVPRW.2011.5981801 – ident: ref7 doi: 10.1109/BTAS.2015.7358768 – year: 2016 ident: ref1 publication-title: The Troubling Rise of Rapid DNA Testing
SSID	ssj0014516
Score	2.4673684
Snippet	Identifying kinship relations has garnered interest due to several applications such as organizing and tagging the enormous amount of videos being uploaded on...
SourceID	proquest pubmed crossref ieee
SourceType	Aggregation Database Index Database Enrichment Source Publisher
StartPage	1329
SubjectTerms	Algorithms Feature extraction Frames (data processing) Image reconstruction Lighting Machine learning Measurement Occlusion Videos Weight
Title	Supervised Mixed Norm Autoencoder for Kinship Verification in Unconstrained Videos
URI	https://ieeexplore.ieee.org/document/8365817 https://www.ncbi.nlm.nih.gov/pubmed/29993718 https://www.proquest.com/docview/2137554897 https://www.proquest.com/docview/2068343094
Volume	28
WOSCitedRecordID	wos000451258900002&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/eLvHCXMwlV3fa9UwFD5swwd9cHPzx9VtRPBFsLtpkzbp45ANRb0M3cZ9K7nJCRSkHbe34p_vSdpbFFTYSwn0JA39cnK-5JycALxBW2Yucz5JkaZAYgQuMc7mSa7MKjVYcMSYZ_azWiz0clle7cC76SwMIsbgMzwLxejLd63tw1bZXAuyl6nahV2liuGs1uQxCBfORs9mrhJFtH_rkuTl_PrjVYjh0mc0FZNS8T9MULxT5d_0MpqZy_37dfAAHo90kp0P-D-BHWwOYX-klmxU3O4QHv2Wd_AIvn7r78Ic0ZHMl_onPRdEXdl5v2lDXkuHa0Zcln2qYywXu6VqftzbY3XDbkgmJJ411KJjt7XDtnsKN5cX1-8_JOPlCokVUm2SNCZt5NajybxLhZW59V4aImwrw1WhyIx5VIKQ5EUpcpN6pLKygktZCieewV7TNvgC2EpjrKkdSumE1T4rnCw1t8Z4Ls0M5tv_Xdkx83jo4_cqrkB4WRFCVUCoGhGawdupxt2QdeM_skcBiEluxGAGx1tIq1EtuypLhSL-pEt6_Xp6TQoVvCSmwbYnGV5oIQUte2fwfBgKU9tku0P-QP3y7998BQ-pZ-UQonYMe5t1jyfwwP7Y1N36lEbtUp_GUfsLOKXo5Q
linkProvider	IEEE
linkToHtml	http://cvtisr.summon.serialssolutions.com/2.0.0/link/0/eLvHCXMwlV3fi9QwEB7OU1AfPL3zx-qpEXwR7G3atE36eIjHHbe3HLp33FvJJhMoSHtst-Kf7ySbLQoq-FICnaShk8l8yUy-ALxHU2U2sy5JkaZAQgQ20dYUSSH1MtVYcsTAMzuT87m6uakud-DjeBYGEUPyGR75Yojl284MfqtsqgT5y1Tegbv-5qx4WmuMGfgrZ0Nss5CJJOC_DUryaro4u_RZXOqIJmMyK_6bEwq3qvwdYAZHc7L3f118DI8ioGTHmxHwBHaw3Ye9CC5ZNN1-Hx7-wjx4AF--Drd-luhJ5qL5Qc85gVd2PKw7z2xpccUIzbLzJmRzsWuq5uLuHmtadkUynnpWU4uWXTcWu_4pXJ18Xnw6TeL1CokRuVwnaaBt5MahzpxNhckL41yuCbItNZelJEfmUArSJS8rUejUIZWlETzPK2HFM9htuxZfAFsqDDWVxTy3wiiXlTavFDdaO57rCUy3_7s2kXvc9_FbHdYgvKpJQ7XXUB01NIEPY43bDe_GP2QPvCJGuaiDCRxuVVpHw-zrLBWSEJSq6PW78TWZlI-T6Ba7gWR4qUQuaOE7geeboTC2Td7bMwiql3_-5lu4f7q4mNWzs_n5K3hAvaw2CWuHsLteDfga7pnv66ZfvQlj9ycCUOtG
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=Supervised+Mixed+Norm+Autoencoder+for+Kinship+Verification+in+Unconstrained+Videos&rft.jtitle=IEEE+transactions+on+image+processing&rft.au=Kohli%2C+Naman&rft.au=Yadav%2C+Daksha&rft.au=Vatsa%2C+Mayank&rft.au=Singh%2C+Richa&rft.date=2019-03-01&rft.issn=1057-7149&rft.eissn=1941-0042&rft.volume=28&rft.issue=3&rft.spage=1329&rft.epage=1341&rft_id=info:doi/10.1109%2FTIP.2018.2840880&rft.externalDBID=n%2Fa&rft.externalDocID=10_1109_TIP_2018_2840880
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