Recognizing human actions: a local SVM approach
Local space-time features capture local events in video and can be adapted to the size, the frequency and the velocity of moving patterns. In this paper, we demonstrate how such features can be used for recognizing complex motion patterns. We construct video representations in terms of local space-t...
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 | 36 Vol.3 |
|---|---|
| container_issue | |
| container_start_page | 32 |
| container_title | |
| container_volume | 3 |
| creator | Schuldt, C. Laptev, I. Caputo, B. |
| description | Local space-time features capture local events in video and can be adapted to the size, the frequency and the velocity of moving patterns. In this paper, we demonstrate how such features can be used for recognizing complex motion patterns. We construct video representations in terms of local space-time features and integrate such representations with SVM classification schemes for recognition. For the purpose of evaluation we introduce a new video database containing 2391 sequences of six human actions performed by 25 people in four different scenarios. The presented results of action recognition justify the proposed method and demonstrate its advantage compared to other relative approaches for action recognition. |
| doi_str_mv | 10.1109/ICPR.2004.1334462 |
| format | Conference Proceeding |
| fullrecord | <record><control><sourceid>swepub_6IE</sourceid><recordid>TN_cdi_ieee_primary_1334462</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1334462</ieee_id><sourcerecordid>oai_DiVA_org_kth_44315</sourcerecordid><originalsourceid>FETCH-LOGICAL-c326t-8fada0e55c1898d78448ac47a19bfdee1819cf6171c8ad330b4cdafa699364093</originalsourceid><addsrcrecordid>eNo90MtOg0AYhuGJh0RavQDjhgsQOv-cmHHX1FOTGk3VbsnPMMAoBQI0Rq9ekzauvs2Tb_EScgk0BqBmtly8rGNGqYiBcyEUOyIB0xyiRCTymExoooxkwDQ7IQFQCZFQEs7IZBg-KGWUSx2Q2drZtmz8j2_KsNptsQnRjr5thpsQw7q1WIevm6cQu65v0Vbn5LTAenAXh52S9_u7t8VjtHp-WC7mq8hypsZIF5gjdVJa0EbniRZCoxUJgsmK3DnQYGyhIAGrMeecZsLmWKAyhitBDZ-S6_3v8OW6XZZ2vd9i_5226NNbv5mnbV-mn2OVCsFB_vGrPffOuX986MJ_AZfFVAI</addsrcrecordid><sourcetype>Open Access Repository</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Recognizing human actions: a local SVM approach</title><source>IEEE Electronic Library (IEL) Conference Proceedings</source><creator>Schuldt, C. ; Laptev, I. ; Caputo, B.</creator><creatorcontrib>Schuldt, C. ; Laptev, I. ; Caputo, B.</creatorcontrib><description>Local space-time features capture local events in video and can be adapted to the size, the frequency and the velocity of moving patterns. In this paper, we demonstrate how such features can be used for recognizing complex motion patterns. We construct video representations in terms of local space-time features and integrate such representations with SVM classification schemes for recognition. For the purpose of evaluation we introduce a new video database containing 2391 sequences of six human actions performed by 25 people in four different scenarios. The presented results of action recognition justify the proposed method and demonstrate its advantage compared to other relative approaches for action recognition.</description><identifier>ISSN: 1051-4651</identifier><identifier>ISBN: 0769521282</identifier><identifier>ISBN: 9780769521282</identifier><identifier>EISSN: 2831-7475</identifier><identifier>DOI: 10.1109/ICPR.2004.1334462</identifier><language>eng</language><publisher>IEEE</publisher><subject>Cameras ; Computer vision ; Frequency ; Humans ; Image recognition ; Pattern recognition ; Performance evaluation ; Spatial databases ; Support vector machine classification ; Support vector machines</subject><ispartof>Pattern Recognition: Proceedings, 17th International Conference, Cambridge, UK, 2004., 2004, Vol.3, p.32-36 Vol.3</ispartof><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c326t-8fada0e55c1898d78448ac47a19bfdee1819cf6171c8ad330b4cdafa699364093</citedby></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1334462$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>230,309,310,776,780,785,786,881,2052,4036,4037,27902,54895</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1334462$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttps://urn.kb.se/resolve?urn=urn:nbn:se:kth:diva-44315$$DView record from Swedish Publication Index$$Hfree_for_read</backlink></links><search><creatorcontrib>Schuldt, C.</creatorcontrib><creatorcontrib>Laptev, I.</creatorcontrib><creatorcontrib>Caputo, B.</creatorcontrib><title>Recognizing human actions: a local SVM approach</title><title>Pattern Recognition: Proceedings, 17th International Conference, Cambridge, UK, 2004.</title><addtitle>ICPR</addtitle><description>Local space-time features capture local events in video and can be adapted to the size, the frequency and the velocity of moving patterns. In this paper, we demonstrate how such features can be used for recognizing complex motion patterns. We construct video representations in terms of local space-time features and integrate such representations with SVM classification schemes for recognition. For the purpose of evaluation we introduce a new video database containing 2391 sequences of six human actions performed by 25 people in four different scenarios. The presented results of action recognition justify the proposed method and demonstrate its advantage compared to other relative approaches for action recognition.</description><subject>Cameras</subject><subject>Computer vision</subject><subject>Frequency</subject><subject>Humans</subject><subject>Image recognition</subject><subject>Pattern recognition</subject><subject>Performance evaluation</subject><subject>Spatial databases</subject><subject>Support vector machine classification</subject><subject>Support vector machines</subject><issn>1051-4651</issn><issn>2831-7475</issn><isbn>0769521282</isbn><isbn>9780769521282</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2004</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><sourceid>RIE</sourceid><recordid>eNo90MtOg0AYhuGJh0RavQDjhgsQOv-cmHHX1FOTGk3VbsnPMMAoBQI0Rq9ekzauvs2Tb_EScgk0BqBmtly8rGNGqYiBcyEUOyIB0xyiRCTymExoooxkwDQ7IQFQCZFQEs7IZBg-KGWUSx2Q2drZtmz8j2_KsNptsQnRjr5thpsQw7q1WIevm6cQu65v0Vbn5LTAenAXh52S9_u7t8VjtHp-WC7mq8hypsZIF5gjdVJa0EbniRZCoxUJgsmK3DnQYGyhIAGrMeecZsLmWKAyhitBDZ-S6_3v8OW6XZZ2vd9i_5226NNbv5mnbV-mn2OVCsFB_vGrPffOuX986MJ_AZfFVAI</recordid><startdate>2004</startdate><enddate>2004</enddate><creator>Schuldt, C.</creator><creator>Laptev, I.</creator><creator>Caputo, B.</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope><scope>ADTPV</scope><scope>BNKNJ</scope><scope>D8V</scope></search><sort><creationdate>2004</creationdate><title>Recognizing human actions: a local SVM approach</title><author>Schuldt, C. ; Laptev, I. ; Caputo, B.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c326t-8fada0e55c1898d78448ac47a19bfdee1819cf6171c8ad330b4cdafa699364093</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2004</creationdate><topic>Cameras</topic><topic>Computer vision</topic><topic>Frequency</topic><topic>Humans</topic><topic>Image recognition</topic><topic>Pattern recognition</topic><topic>Performance evaluation</topic><topic>Spatial databases</topic><topic>Support vector machine classification</topic><topic>Support vector machines</topic><toplevel>online_resources</toplevel><creatorcontrib>Schuldt, C.</creatorcontrib><creatorcontrib>Laptev, I.</creatorcontrib><creatorcontrib>Caputo, B.</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><collection>SwePub</collection><collection>SwePub Conference</collection><collection>SWEPUB Kungliga Tekniska Högskolan</collection></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Schuldt, C.</au><au>Laptev, I.</au><au>Caputo, B.</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Recognizing human actions: a local SVM approach</atitle><btitle>Pattern Recognition: Proceedings, 17th International Conference, Cambridge, UK, 2004.</btitle><stitle>ICPR</stitle><date>2004</date><risdate>2004</risdate><volume>3</volume><spage>32</spage><epage>36 Vol.3</epage><pages>32-36 Vol.3</pages><issn>1051-4651</issn><eissn>2831-7475</eissn><isbn>0769521282</isbn><isbn>9780769521282</isbn><abstract>Local space-time features capture local events in video and can be adapted to the size, the frequency and the velocity of moving patterns. In this paper, we demonstrate how such features can be used for recognizing complex motion patterns. We construct video representations in terms of local space-time features and integrate such representations with SVM classification schemes for recognition. For the purpose of evaluation we introduce a new video database containing 2391 sequences of six human actions performed by 25 people in four different scenarios. The presented results of action recognition justify the proposed method and demonstrate its advantage compared to other relative approaches for action recognition.</abstract><pub>IEEE</pub><doi>10.1109/ICPR.2004.1334462</doi></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1051-4651 |
| ispartof | Pattern Recognition: Proceedings, 17th International Conference, Cambridge, UK, 2004., 2004, Vol.3, p.32-36 Vol.3 |
| issn | 1051-4651 2831-7475 |
| language | eng |
| recordid | cdi_ieee_primary_1334462 |
| source | IEEE Electronic Library (IEL) Conference Proceedings |
| subjects | Cameras Computer vision Frequency Humans Image recognition Pattern recognition Performance evaluation Spatial databases Support vector machine classification Support vector machines |
| title | Recognizing human actions: a local SVM approach |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-05T03%3A37%3A36IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-swepub_6IE&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Recognizing%20human%20actions:%20a%20local%20SVM%20approach&rft.btitle=Pattern%20Recognition:%20Proceedings,%2017th%20International%20Conference,%20Cambridge,%20UK,%202004.&rft.au=Schuldt,%20C.&rft.date=2004&rft.volume=3&rft.spage=32&rft.epage=36%20Vol.3&rft.pages=32-36%20Vol.3&rft.issn=1051-4651&rft.eissn=2831-7475&rft.isbn=0769521282&rft.isbn_list=9780769521282&rft_id=info:doi/10.1109/ICPR.2004.1334462&rft_dat=%3Cswepub_6IE%3Eoai_DiVA_org_kth_44315%3C/swepub_6IE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=1334462&rfr_iscdi=true |