On-the-fly specific person retrieval

We describe a method of visual search for finding people in large video datasets. The novelty is that the person of interest can be specified at run time by a text query, and a discriminative classifier for that person is then learnt on-the-fly using images downloaded from Google Image search. The p...

Ausführliche Beschreibung

Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Parkhi, O. M., Vedaldi, A., Zisserman, A.
Format: Tagungsbericht
Sprache:eng
Schlagworte:
Online-Zugang:Volltext bestellen
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
container_end_page 4
container_issue
container_start_page 1
container_title
container_volume
creator Parkhi, O. M.
Vedaldi, A.
Zisserman, A.
description We describe a method of visual search for finding people in large video datasets. The novelty is that the person of interest can be specified at run time by a text query, and a discriminative classifier for that person is then learnt on-the-fly using images downloaded from Google Image search. The performance of the method is evaluated on a ground truth dataset of episodes of Scrubs, and results are also shown for retrieval on the TRECVid 2011 IACC.1.B dataset of over 8k videos. The entire process from specifying the query to receiving the ranked results takes only a matter of seconds.
doi_str_mv 10.1109/WIAMIS.2012.6226775
format Conference Proceeding
fullrecord <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6226775</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6226775</ieee_id><sourcerecordid>6226775</sourcerecordid><originalsourceid>FETCH-LOGICAL-i90t-c3ece936e1e29bdfc8c6e359cb70444ce3b84a2f47df2aae354ec7b41f3a1b893</originalsourceid><addsrcrecordid>eNo1j01LAzEURSMqWOv8gm5m4TZj3ktmkixL8WOg0oUFlyVJXzAy1iEZhP57C9bV5XLgci5jCxANgLAP7_3ytX9rUAA2HWKndXvBKqsNqE5Loa2AS3b7XwCv2AyhNbw1Wt6wqpRPIYQEY6zEGbvfHPj0QTwOx7qMFFJMoR4pl-9DnWnKiX7ccMeuoxsKVeecs-3T43b1wteb5361XPNkxcSDpEBWdgSE1u9jMKEj2drgtVBKBZLeKIdR6X1E505IUdBeQZQO_ElnzhZ_s4mIdmNOXy4fd-eP8hdIyENa</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>On-the-fly specific person retrieval</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Parkhi, O. M. ; Vedaldi, A. ; Zisserman, A.</creator><creatorcontrib>Parkhi, O. M. ; Vedaldi, A. ; Zisserman, A.</creatorcontrib><description>We describe a method of visual search for finding people in large video datasets. The novelty is that the person of interest can be specified at run time by a text query, and a discriminative classifier for that person is then learnt on-the-fly using images downloaded from Google Image search. The performance of the method is evaluated on a ground truth dataset of episodes of Scrubs, and results are also shown for retrieval on the TRECVid 2011 IACC.1.B dataset of over 8k videos. The entire process from specifying the query to receiving the ranked results takes only a matter of seconds.</description><identifier>ISSN: 2158-5873</identifier><identifier>ISBN: 1467307912</identifier><identifier>ISBN: 9781467307918</identifier><identifier>EISBN: 9781467307901</identifier><identifier>EISBN: 1467307890</identifier><identifier>EISBN: 9781467307895</identifier><identifier>EISBN: 1467307904</identifier><identifier>DOI: 10.1109/WIAMIS.2012.6226775</identifier><language>eng</language><publisher>IEEE</publisher><subject>Detectors ; Face ; Facial features ; Feature extraction ; Google ; Training ; Vectors</subject><ispartof>2012 13th International Workshop on Image Analysis for Multimedia Interactive Services, 2012, p.1-4</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6226775$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6226775$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Parkhi, O. M.</creatorcontrib><creatorcontrib>Vedaldi, A.</creatorcontrib><creatorcontrib>Zisserman, A.</creatorcontrib><title>On-the-fly specific person retrieval</title><title>2012 13th International Workshop on Image Analysis for Multimedia Interactive Services</title><addtitle>WIAMIS</addtitle><description>We describe a method of visual search for finding people in large video datasets. The novelty is that the person of interest can be specified at run time by a text query, and a discriminative classifier for that person is then learnt on-the-fly using images downloaded from Google Image search. The performance of the method is evaluated on a ground truth dataset of episodes of Scrubs, and results are also shown for retrieval on the TRECVid 2011 IACC.1.B dataset of over 8k videos. The entire process from specifying the query to receiving the ranked results takes only a matter of seconds.</description><subject>Detectors</subject><subject>Face</subject><subject>Facial features</subject><subject>Feature extraction</subject><subject>Google</subject><subject>Training</subject><subject>Vectors</subject><issn>2158-5873</issn><isbn>1467307912</isbn><isbn>9781467307918</isbn><isbn>9781467307901</isbn><isbn>1467307890</isbn><isbn>9781467307895</isbn><isbn>1467307904</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1j01LAzEURSMqWOv8gm5m4TZj3ktmkixL8WOg0oUFlyVJXzAy1iEZhP57C9bV5XLgci5jCxANgLAP7_3ytX9rUAA2HWKndXvBKqsNqE5Loa2AS3b7XwCv2AyhNbw1Wt6wqpRPIYQEY6zEGbvfHPj0QTwOx7qMFFJMoR4pl-9DnWnKiX7ccMeuoxsKVeecs-3T43b1wteb5361XPNkxcSDpEBWdgSE1u9jMKEj2drgtVBKBZLeKIdR6X1E505IUdBeQZQO_ElnzhZ_s4mIdmNOXy4fd-eP8hdIyENa</recordid><startdate>201205</startdate><enddate>201205</enddate><creator>Parkhi, O. M.</creator><creator>Vedaldi, A.</creator><creator>Zisserman, A.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201205</creationdate><title>On-the-fly specific person retrieval</title><author>Parkhi, O. M. ; Vedaldi, A. ; Zisserman, A.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i90t-c3ece936e1e29bdfc8c6e359cb70444ce3b84a2f47df2aae354ec7b41f3a1b893</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Detectors</topic><topic>Face</topic><topic>Facial features</topic><topic>Feature extraction</topic><topic>Google</topic><topic>Training</topic><topic>Vectors</topic><toplevel>online_resources</toplevel><creatorcontrib>Parkhi, O. M.</creatorcontrib><creatorcontrib>Vedaldi, A.</creatorcontrib><creatorcontrib>Zisserman, A.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan All Online (POP All Online) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP All) 1998-Present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Parkhi, O. M.</au><au>Vedaldi, A.</au><au>Zisserman, A.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>On-the-fly specific person retrieval</atitle><btitle>2012 13th International Workshop on Image Analysis for Multimedia Interactive Services</btitle><stitle>WIAMIS</stitle><date>2012-05</date><risdate>2012</risdate><spage>1</spage><epage>4</epage><pages>1-4</pages><issn>2158-5873</issn><isbn>1467307912</isbn><isbn>9781467307918</isbn><eisbn>9781467307901</eisbn><eisbn>1467307890</eisbn><eisbn>9781467307895</eisbn><eisbn>1467307904</eisbn><abstract>We describe a method of visual search for finding people in large video datasets. The novelty is that the person of interest can be specified at run time by a text query, and a discriminative classifier for that person is then learnt on-the-fly using images downloaded from Google Image search. The performance of the method is evaluated on a ground truth dataset of episodes of Scrubs, and results are also shown for retrieval on the TRECVid 2011 IACC.1.B dataset of over 8k videos. The entire process from specifying the query to receiving the ranked results takes only a matter of seconds.</abstract><pub>IEEE</pub><doi>10.1109/WIAMIS.2012.6226775</doi><tpages>4</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier ISSN: 2158-5873
ispartof 2012 13th International Workshop on Image Analysis for Multimedia Interactive Services, 2012, p.1-4
issn 2158-5873
language eng
recordid cdi_ieee_primary_6226775
source IEEE Electronic Library (IEL) Conference Proceedings
subjects Detectors
Face
Facial features
Feature extraction
Google
Training
Vectors
title On-the-fly specific person retrieval
url https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-12-29T11%3A36%3A00IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=On-the-fly%20specific%20person%20retrieval&rft.btitle=2012%2013th%20International%20Workshop%20on%20Image%20Analysis%20for%20Multimedia%20Interactive%20Services&rft.au=Parkhi,%20O.%20M.&rft.date=2012-05&rft.spage=1&rft.epage=4&rft.pages=1-4&rft.issn=2158-5873&rft.isbn=1467307912&rft.isbn_list=9781467307918&rft_id=info:doi/10.1109/WIAMIS.2012.6226775&rft_dat=%3Cieee_6IE%3E6226775%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781467307901&rft.eisbn_list=1467307890&rft.eisbn_list=9781467307895&rft.eisbn_list=1467307904&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6226775&rfr_iscdi=true