Joint pose estimation and action recognition in image graphs
Human analysis in images and video is a hard problem due to the large variation in human pose, clothing, camera view-points, lighting and other factors. While the explicit modeling of this variability is difficult, the huge amount of available person images motivates for the implicit, data-driven ap...
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 | 28 |
|---|---|
| container_issue | |
| container_start_page | 25 |
| container_title | |
| container_volume | |
| creator | Raja, K. Laptev, I. Perez, P. Oisel, L. |
| description | Human analysis in images and video is a hard problem due to the large variation in human pose, clothing, camera view-points, lighting and other factors. While the explicit modeling of this variability is difficult, the huge amount of available person images motivates for the implicit, data-driven approach to human analysis. In this work we aim to explore this approach using the large amount of images spanning a subspace of human appearance. We model this subspace by connecting images into a graph and propagating information through such a graph using a discriminatively-trained graphical model. We particularly address the problems of human pose estimation and action recognition and demonstrate how image graphs help solving these problems jointly. We report results on still images with human actions from the KTH dataset. |
| doi_str_mv | 10.1109/ICIP.2011.6116197 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>ieee_6IE</sourceid><recordid>TN_cdi_ieee_primary_6116197</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>6116197</ieee_id><sourcerecordid>6116197</sourcerecordid><originalsourceid>FETCH-LOGICAL-i218t-9357cbab06c9960833f4f1d74390b04155f259f210c500d05004a241859039373</originalsourceid><addsrcrecordid>eNo1UNtKxDAUjDewu-4HiC_9gdZzcpImAV-keKks6IM-L2ma1ojblqYv_r1lXWGYGRgYhmHsGiFHBHNbldVbzgExLxALNOqEbYzSKKRSSEB0yhJOGjMthTljq_9AqHOWoOQ8E1rDJVvF-AWwFBEm7O5lCP2cjkP0qY9z2Ns5DH1q-ya17mAn74auDwcfFuxt59NusuNnvGIXrf2OfnPUNft4fHgvn7Pt61NV3m-zwFHPmSGpXG1rKJwxBWiiVrTYKEEGahAoZculaTmCkwANLCQsF6ilATKkaM1u_nqD9343TsuG6Wd3fIF-AX__Sf8</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Joint pose estimation and action recognition in image graphs</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Raja, K. ; Laptev, I. ; Perez, P. ; Oisel, L.</creator><creatorcontrib>Raja, K. ; Laptev, I. ; Perez, P. ; Oisel, L.</creatorcontrib><description>Human analysis in images and video is a hard problem due to the large variation in human pose, clothing, camera view-points, lighting and other factors. While the explicit modeling of this variability is difficult, the huge amount of available person images motivates for the implicit, data-driven approach to human analysis. In this work we aim to explore this approach using the large amount of images spanning a subspace of human appearance. We model this subspace by connecting images into a graph and propagating information through such a graph using a discriminatively-trained graphical model. We particularly address the problems of human pose estimation and action recognition and demonstrate how image graphs help solving these problems jointly. We report results on still images with human actions from the KTH dataset.</description><identifier>ISSN: 1522-4880</identifier><identifier>ISBN: 1457713047</identifier><identifier>ISBN: 9781457713040</identifier><identifier>EISSN: 2381-8549</identifier><identifier>EISBN: 9781457713033</identifier><identifier>EISBN: 1457713020</identifier><identifier>EISBN: 1457713039</identifier><identifier>EISBN: 9781457713026</identifier><identifier>DOI: 10.1109/ICIP.2011.6116197</identifier><language>eng</language><publisher>IEEE</publisher><subject>Action Recognition in still images ; Conferences ; Estimation ; Graph optimization ; Graphical models ; Humans ; Image recognition ; Joints ; Pose estimation ; Training</subject><ispartof>2011 18th IEEE International Conference on Image Processing, 2011, p.25-28</ispartof><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/6116197$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,780,784,789,790,2058,27925,54920</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/6116197$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Raja, K.</creatorcontrib><creatorcontrib>Laptev, I.</creatorcontrib><creatorcontrib>Perez, P.</creatorcontrib><creatorcontrib>Oisel, L.</creatorcontrib><title>Joint pose estimation and action recognition in image graphs</title><title>2011 18th IEEE International Conference on Image Processing</title><addtitle>ICIP</addtitle><description>Human analysis in images and video is a hard problem due to the large variation in human pose, clothing, camera view-points, lighting and other factors. While the explicit modeling of this variability is difficult, the huge amount of available person images motivates for the implicit, data-driven approach to human analysis. In this work we aim to explore this approach using the large amount of images spanning a subspace of human appearance. We model this subspace by connecting images into a graph and propagating information through such a graph using a discriminatively-trained graphical model. We particularly address the problems of human pose estimation and action recognition and demonstrate how image graphs help solving these problems jointly. We report results on still images with human actions from the KTH dataset.</description><subject>Action Recognition in still images</subject><subject>Conferences</subject><subject>Estimation</subject><subject>Graph optimization</subject><subject>Graphical models</subject><subject>Humans</subject><subject>Image recognition</subject><subject>Joints</subject><subject>Pose estimation</subject><subject>Training</subject><issn>1522-4880</issn><issn>2381-8549</issn><isbn>1457713047</isbn><isbn>9781457713040</isbn><isbn>9781457713033</isbn><isbn>1457713020</isbn><isbn>1457713039</isbn><isbn>9781457713026</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2011</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo1UNtKxDAUjDewu-4HiC_9gdZzcpImAV-keKks6IM-L2ma1ojblqYv_r1lXWGYGRgYhmHsGiFHBHNbldVbzgExLxALNOqEbYzSKKRSSEB0yhJOGjMthTljq_9AqHOWoOQ8E1rDJVvF-AWwFBEm7O5lCP2cjkP0qY9z2Ns5DH1q-ya17mAn74auDwcfFuxt59NusuNnvGIXrf2OfnPUNft4fHgvn7Pt61NV3m-zwFHPmSGpXG1rKJwxBWiiVrTYKEEGahAoZculaTmCkwANLCQsF6ilATKkaM1u_nqD9343TsuG6Wd3fIF-AX__Sf8</recordid><startdate>20110101</startdate><enddate>20110101</enddate><creator>Raja, K.</creator><creator>Laptev, I.</creator><creator>Perez, P.</creator><creator>Oisel, L.</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>20110101</creationdate><title>Joint pose estimation and action recognition in image graphs</title><author>Raja, K. ; Laptev, I. ; Perez, P. ; Oisel, L.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i218t-9357cbab06c9960833f4f1d74390b04155f259f210c500d05004a241859039373</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2011</creationdate><topic>Action Recognition in still images</topic><topic>Conferences</topic><topic>Estimation</topic><topic>Graph optimization</topic><topic>Graphical models</topic><topic>Humans</topic><topic>Image recognition</topic><topic>Joints</topic><topic>Pose estimation</topic><topic>Training</topic><toplevel>online_resources</toplevel><creatorcontrib>Raja, K.</creatorcontrib><creatorcontrib>Laptev, I.</creatorcontrib><creatorcontrib>Perez, P.</creatorcontrib><creatorcontrib>Oisel, L.</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>Raja, K.</au><au>Laptev, I.</au><au>Perez, P.</au><au>Oisel, L.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Joint pose estimation and action recognition in image graphs</atitle><btitle>2011 18th IEEE International Conference on Image Processing</btitle><stitle>ICIP</stitle><date>2011-01-01</date><risdate>2011</risdate><spage>25</spage><epage>28</epage><pages>25-28</pages><issn>1522-4880</issn><eissn>2381-8549</eissn><isbn>1457713047</isbn><isbn>9781457713040</isbn><eisbn>9781457713033</eisbn><eisbn>1457713020</eisbn><eisbn>1457713039</eisbn><eisbn>9781457713026</eisbn><abstract>Human analysis in images and video is a hard problem due to the large variation in human pose, clothing, camera view-points, lighting and other factors. While the explicit modeling of this variability is difficult, the huge amount of available person images motivates for the implicit, data-driven approach to human analysis. In this work we aim to explore this approach using the large amount of images spanning a subspace of human appearance. We model this subspace by connecting images into a graph and propagating information through such a graph using a discriminatively-trained graphical model. We particularly address the problems of human pose estimation and action recognition and demonstrate how image graphs help solving these problems jointly. We report results on still images with human actions from the KTH dataset.</abstract><pub>IEEE</pub><doi>10.1109/ICIP.2011.6116197</doi><tpages>4</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1522-4880 |
| ispartof | 2011 18th IEEE International Conference on Image Processing, 2011, p.25-28 |
| issn | 1522-4880 2381-8549 |
| language | eng |
| recordid | cdi_ieee_primary_6116197 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Action Recognition in still images Conferences Estimation Graph optimization Graphical models Humans Image recognition Joints Pose estimation Training |
| title | Joint pose estimation and action recognition in image graphs |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-02T18%3A26%3A10IST&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=Joint%20pose%20estimation%20and%20action%20recognition%20in%20image%20graphs&rft.btitle=2011%2018th%20IEEE%20International%20Conference%20on%20Image%20Processing&rft.au=Raja,%20K.&rft.date=2011-01-01&rft.spage=25&rft.epage=28&rft.pages=25-28&rft.issn=1522-4880&rft.eissn=2381-8549&rft.isbn=1457713047&rft.isbn_list=9781457713040&rft_id=info:doi/10.1109/ICIP.2011.6116197&rft_dat=%3Cieee_6IE%3E6116197%3C/ieee_6IE%3E%3Curl%3E%3C/url%3E&rft.eisbn=9781457713033&rft.eisbn_list=1457713020&rft.eisbn_list=1457713039&rft.eisbn_list=9781457713026&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=6116197&rfr_iscdi=true |