A data driven method for feature transformation
Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented...
Gespeichert in:
| Hauptverfasser: | , , |
|---|---|
| Format: | Tagungsbericht |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 3321 |
|---|---|
| container_issue | |
| container_start_page | 3314 |
| container_title | |
| container_volume | |
| creator | Dikmen, M. Hoiem, D. Huang, T. S. |
| description | Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented dataset. In this work we propose a data driven, local histogram based feature extraction method that reduces the manual intervention during the feature computation process and improves on the performance of widely used gradient histogram based features (e.g., HOG). We demonstrate favorable object detection results against HOG on the Inria Pedestrian[7], Pascal 2007[10] data. |
| doi_str_mv | 10.1109/CVPR.2012.6248069 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6248069</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6248069</ieee_id><sourcerecordid>6248069</sourcerecordid><originalsourceid>FETCH-LOGICAL-i175t-66b0d7a313dd35b5fce53e7bc78940851b82793d7481eb523739a2a2770b60043</originalsourceid><addsrcrecordid>eNo1j91KxDAUhCMquK59APEmL9DuOfnP5bL4BwuKqLdLsjnFim0ljYJvb8F1bob5GAaGsUuEBhH8avP6-NQIQNEYoRwYf8TOURkrUQgnjlnlrfvPRp2wBYKRtfHoz1g1Te8wa26AFwu2WvMUSuApd9808J7K25h4O2beUihfmXjJYZhm0IfSjcMFO23Dx0TVwZfs5eb6eXNXbx9u7zfrbd2h1aU2JkKyQaJMSeqo2z1pSTburfMKnMbohPUyWeWQohbSSh9EENZCNABKLtnV325HRLvP3PUh_-wOf-Uv6-NFAw</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A data driven method for feature transformation</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Dikmen, M. ; Hoiem, D. ; Huang, T. S.</creator><creatorcontrib>Dikmen, M. ; Hoiem, D. ; Huang, T. S.</creatorcontrib><description>Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented dataset. In this work we propose a data driven, local histogram based feature extraction method that reduces the manual intervention during the feature computation process and improves on the performance of widely used gradient histogram based features (e.g., HOG). We demonstrate favorable object detection results against HOG on the Inria Pedestrian[7], Pascal 2007[10] data.</description><identifier>ISSN: 1063-6919</identifier><identifier>ISBN: 9781467312264</identifier><identifier>ISBN: 1467312266</identifier><identifier>EISBN: 1467312282</identifier><identifier>EISBN: 1467312274</identifier><identifier>EISBN: 9781467312271</identifier><identifier>EISBN: 9781467312288</identifier><identifier>DOI: 10.1109/CVPR.2012.6248069</identifier><language>eng</language><publisher>IEEE</publisher><subject>Clustering algorithms ; Dictionaries ; Feature extraction ; Histograms ; Object detection ; Testing ; Training</subject><ispartof>2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, p.3314-3321</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/6248069$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,777,781,786,787,2052,27906,54901</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6248069$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Dikmen, M.</creatorcontrib><creatorcontrib>Hoiem, D.</creatorcontrib><creatorcontrib>Huang, T. S.</creatorcontrib><title>A data driven method for feature transformation</title><title>2012 IEEE Conference on Computer Vision and Pattern Recognition</title><addtitle>CVPR</addtitle><description>Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented dataset. In this work we propose a data driven, local histogram based feature extraction method that reduces the manual intervention during the feature computation process and improves on the performance of widely used gradient histogram based features (e.g., HOG). We demonstrate favorable object detection results against HOG on the Inria Pedestrian[7], Pascal 2007[10] data.</description><subject>Clustering algorithms</subject><subject>Dictionaries</subject><subject>Feature extraction</subject><subject>Histograms</subject><subject>Object detection</subject><subject>Testing</subject><subject>Training</subject><issn>1063-6919</issn><isbn>9781467312264</isbn><isbn>1467312266</isbn><isbn>1467312282</isbn><isbn>1467312274</isbn><isbn>9781467312271</isbn><isbn>9781467312288</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2012</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1j91KxDAUhCMquK59APEmL9DuOfnP5bL4BwuKqLdLsjnFim0ljYJvb8F1bob5GAaGsUuEBhH8avP6-NQIQNEYoRwYf8TOURkrUQgnjlnlrfvPRp2wBYKRtfHoz1g1Te8wa26AFwu2WvMUSuApd9808J7K25h4O2beUihfmXjJYZhm0IfSjcMFO23Dx0TVwZfs5eb6eXNXbx9u7zfrbd2h1aU2JkKyQaJMSeqo2z1pSTburfMKnMbohPUyWeWQohbSSh9EENZCNABKLtnV325HRLvP3PUh_-wOf-Uv6-NFAw</recordid><startdate>201206</startdate><enddate>201206</enddate><creator>Dikmen, M.</creator><creator>Hoiem, D.</creator><creator>Huang, T. S.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201206</creationdate><title>A data driven method for feature transformation</title><author>Dikmen, M. ; Hoiem, D. ; Huang, T. S.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i175t-66b0d7a313dd35b5fce53e7bc78940851b82793d7481eb523739a2a2770b60043</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2012</creationdate><topic>Clustering algorithms</topic><topic>Dictionaries</topic><topic>Feature extraction</topic><topic>Histograms</topic><topic>Object detection</topic><topic>Testing</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Dikmen, M.</creatorcontrib><creatorcontrib>Hoiem, D.</creatorcontrib><creatorcontrib>Huang, T. S.</creatorcontrib><collection>IEEE Electronic Library (IEL) Conference Proceedings</collection><collection>IEEE Proceedings Order Plan (POP) 1998-present by volume</collection><collection>IEEE Xplore All Conference Proceedings</collection><collection>IEEE Electronic Library (IEL)</collection><collection>IEEE Proceedings Order Plans (POP) 1998-present</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Dikmen, M.</au><au>Hoiem, D.</au><au>Huang, T. S.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A data driven method for feature transformation</atitle><btitle>2012 IEEE Conference on Computer Vision and Pattern Recognition</btitle><stitle>CVPR</stitle><date>2012-06</date><risdate>2012</risdate><spage>3314</spage><epage>3321</epage><pages>3314-3321</pages><issn>1063-6919</issn><isbn>9781467312264</isbn><isbn>1467312266</isbn><eisbn>1467312282</eisbn><eisbn>1467312274</eisbn><eisbn>9781467312271</eisbn><eisbn>9781467312288</eisbn><abstract>Most image understanding algorithms begin with the extraction of information thought to be relevant to the particular task. This is commonly known as feature extraction and has, up to this date, been a largely manual process, where a reasonable method is chosen through validation on the experimented dataset. In this work we propose a data driven, local histogram based feature extraction method that reduces the manual intervention during the feature computation process and improves on the performance of widely used gradient histogram based features (e.g., HOG). We demonstrate favorable object detection results against HOG on the Inria Pedestrian[7], Pascal 2007[10] data.</abstract><pub>IEEE</pub><doi>10.1109/CVPR.2012.6248069</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1063-6919 |
| ispartof | 2012 IEEE Conference on Computer Vision and Pattern Recognition, 2012, p.3314-3321 |
| issn | 1063-6919 |
| language | eng |
| recordid | cdi_ieee_primary_6248069 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Clustering algorithms Dictionaries Feature extraction Histograms Object detection Testing Training |
| title | A data driven method for feature transformation |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-18T10%3A46%3A22IST&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=A%20data%20driven%20method%20for%20feature%20transformation&rft.btitle=2012%20IEEE%20Conference%20on%20Computer%20Vision%20and%20Pattern%20Recognition&rft.au=Dikmen,%20M.&rft.date=2012-06&rft.spage=3314&rft.epage=3321&rft.pages=3314-3321&rft.issn=1063-6919&rft.isbn=9781467312264&rft.isbn_list=1467312266&rft_id=info:doi/10.1109/CVPR.2012.6248069&rft_dat=%3Cieee_6IE%3E6248069%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=1467312282&rft.eisbn_list=1467312274&rft.eisbn_list=9781467312271&rft.eisbn_list=9781467312288&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6248069&rfr_iscdi=true |