Statistical analysis of dynamic actions
Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actions, need a minimal number of parameters, and necessitate as short as possible learning stage. In this paper, we suggest s...
Gespeichert in:
| Veröffentlicht in: | IEEE transactions on pattern analysis and machine intelligence 2006-09, Vol.28 (9), p.1530-1535 |
|---|---|
| Hauptverfasser: | , |
| Format: | Artikel |
| Sprache: | eng |
| Schlagworte: | |
| Online-Zugang: | Volltext bestellen |
| Tags: |
Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
|
| container_end_page | 1535 |
|---|---|
| container_issue | 9 |
| container_start_page | 1530 |
| container_title | IEEE transactions on pattern analysis and machine intelligence |
| container_volume | 28 |
| creator | Zelnik-Manor, L. Irani, M. |
| description | Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actions, need a minimal number of parameters, and necessitate as short as possible learning stage. In this paper, we suggest such an approach. We regard dynamic activities as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple statistical distance measure between video sequences which captures the similarities in their behavioral content. This measure is nonparametric and can thus handle a wide range of complex dynamic actions. Having a behavior-based distance measure between sequences, we use it for a variety of tasks, including: video indexing, temporal segmentation, and action-based video clustering. These tasks are performed without prior knowledge of the types of actions, their models, or their temporal extents |
| doi_str_mv | 10.1109/TPAMI.2006.194 |
| format | Article |
| fullrecord | <record><control><sourceid>proquest_RIE</sourceid><recordid>TN_cdi_proquest_journals_865710220</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>1661555</ieee_id><sourcerecordid>68784752</sourcerecordid><originalsourceid>FETCH-LOGICAL-c442t-8181174278df13d270922600d3cf7dbb9e9ca455c813582065ca2e20be8c3c3f3</originalsourceid><addsrcrecordid>eNp90c1LwzAYx_EgipvTqxdBhqCeOp8nad6OY_gymCg4zyVLU8jo2tm0h_33Zm4w8eApl09-kG8IuUQYIYJ-mL-PX6cjCiBGqNMj0kfNdMI408ekDyhoohRVPXIWwhIAUw7slPRQaKol031y_9Ga1ofWW1MOTWXKTfBhWBfDfFOZlbdDY1tfV-GcnBSmDO5ifw7I59PjfPKSzN6ep5PxLLFpSttEoUKUKZUqL5DlVIKmVADkzBYyXyy009aknFuFjCsKgltDHYWFU5ZZVrABud_trpv6q3OhzVY-WFeWpnJ1FzKlRXwhgojy7l8plFSp5DTCmz9wWXdNfGpcE1wiUAoRjXbINnUIjSuydeNXptlkCNm2dPZTOtuWzmLpeOF6v9otVi4_8H3aCG73wIQYt2hMZX04OBW_Q8utu9o575z7NSOQc86-AcNoi9Y</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>865710220</pqid></control><display><type>article</type><title>Statistical analysis of dynamic actions</title><source>IEEE Electronic Library (IEL)</source><creator>Zelnik-Manor, L. ; Irani, M.</creator><creatorcontrib>Zelnik-Manor, L. ; Irani, M.</creatorcontrib><description>Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actions, need a minimal number of parameters, and necessitate as short as possible learning stage. In this paper, we suggest such an approach. We regard dynamic activities as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple statistical distance measure between video sequences which captures the similarities in their behavioral content. This measure is nonparametric and can thus handle a wide range of complex dynamic actions. Having a behavior-based distance measure between sequences, we use it for a variety of tasks, including: video indexing, temporal segmentation, and action-based video clustering. These tasks are performed without prior knowledge of the types of actions, their models, or their temporal extents</description><identifier>ISSN: 0162-8828</identifier><identifier>EISSN: 1939-3539</identifier><identifier>EISSN: 2160-9292</identifier><identifier>DOI: 10.1109/TPAMI.2006.194</identifier><identifier>PMID: 16929739</identifier><identifier>CODEN: ITPIDJ</identifier><language>eng</language><publisher>Los Alamitos, CA: IEEE</publisher><subject>Action recognition ; Algorithms ; Applied sciences ; Artificial Intelligence ; Computer science; control theory; systems ; Dynamic range ; Dynamic tests ; Dynamical systems ; Dynamics ; Exact sciences and technology ; Face recognition ; Handles ; Humans ; Image Enhancement - methods ; Image Interpretation, Computer-Assisted - methods ; Image recognition ; Image segmentation ; Indexing ; Information analysis ; Information Storage and Retrieval - methods ; Kinetics ; Learning ; Motion pictures ; Movement - physiology ; Parametric statistics ; Pattern Recognition, Automated - methods ; Pattern recognition. Digital image processing. Computational geometry ; Statistical analysis ; Tasks ; Temporal logic ; temporal segmentation ; video indexing ; Video Recording - methods ; Video sequences ; Walking - physiology</subject><ispartof>IEEE transactions on pattern analysis and machine intelligence, 2006-09, Vol.28 (9), p.1530-1535</ispartof><rights>2006 INIST-CNRS</rights><rights>Copyright The Institute of Electrical and Electronics Engineers, Inc. (IEEE) 2006</rights><lds50>peer_reviewed</lds50><oa>free_for_read</oa><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c442t-8181174278df13d270922600d3cf7dbb9e9ca455c813582065ca2e20be8c3c3f3</citedby><cites>FETCH-LOGICAL-c442t-8181174278df13d270922600d3cf7dbb9e9ca455c813582065ca2e20be8c3c3f3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/1661555$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>314,776,780,792,27901,27902,54733</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/1661555$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc><backlink>$$Uhttp://pascal-francis.inist.fr/vibad/index.php?action=getRecordDetail&idt=18001979$$DView record in Pascal Francis$$Hfree_for_read</backlink><backlink>$$Uhttps://www.ncbi.nlm.nih.gov/pubmed/16929739$$D View this record in MEDLINE/PubMed$$Hfree_for_read</backlink></links><search><creatorcontrib>Zelnik-Manor, L.</creatorcontrib><creatorcontrib>Irani, M.</creatorcontrib><title>Statistical analysis of dynamic actions</title><title>IEEE transactions on pattern analysis and machine intelligence</title><addtitle>TPAMI</addtitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><description>Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actions, need a minimal number of parameters, and necessitate as short as possible learning stage. In this paper, we suggest such an approach. We regard dynamic activities as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple statistical distance measure between video sequences which captures the similarities in their behavioral content. This measure is nonparametric and can thus handle a wide range of complex dynamic actions. Having a behavior-based distance measure between sequences, we use it for a variety of tasks, including: video indexing, temporal segmentation, and action-based video clustering. These tasks are performed without prior knowledge of the types of actions, their models, or their temporal extents</description><subject>Action recognition</subject><subject>Algorithms</subject><subject>Applied sciences</subject><subject>Artificial Intelligence</subject><subject>Computer science; control theory; systems</subject><subject>Dynamic range</subject><subject>Dynamic tests</subject><subject>Dynamical systems</subject><subject>Dynamics</subject><subject>Exact sciences and technology</subject><subject>Face recognition</subject><subject>Handles</subject><subject>Humans</subject><subject>Image Enhancement - methods</subject><subject>Image Interpretation, Computer-Assisted - methods</subject><subject>Image recognition</subject><subject>Image segmentation</subject><subject>Indexing</subject><subject>Information analysis</subject><subject>Information Storage and Retrieval - methods</subject><subject>Kinetics</subject><subject>Learning</subject><subject>Motion pictures</subject><subject>Movement - physiology</subject><subject>Parametric statistics</subject><subject>Pattern Recognition, Automated - methods</subject><subject>Pattern recognition. Digital image processing. Computational geometry</subject><subject>Statistical analysis</subject><subject>Tasks</subject><subject>Temporal logic</subject><subject>temporal segmentation</subject><subject>video indexing</subject><subject>Video Recording - methods</subject><subject>Video sequences</subject><subject>Walking - physiology</subject><issn>0162-8828</issn><issn>1939-3539</issn><issn>2160-9292</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2006</creationdate><recordtype>article</recordtype><sourceid>RIE</sourceid><sourceid>EIF</sourceid><recordid>eNp90c1LwzAYx_EgipvTqxdBhqCeOp8nad6OY_gymCg4zyVLU8jo2tm0h_33Zm4w8eApl09-kG8IuUQYIYJ-mL-PX6cjCiBGqNMj0kfNdMI408ekDyhoohRVPXIWwhIAUw7slPRQaKol031y_9Ga1ofWW1MOTWXKTfBhWBfDfFOZlbdDY1tfV-GcnBSmDO5ifw7I59PjfPKSzN6ep5PxLLFpSttEoUKUKZUqL5DlVIKmVADkzBYyXyy009aknFuFjCsKgltDHYWFU5ZZVrABud_trpv6q3OhzVY-WFeWpnJ1FzKlRXwhgojy7l8plFSp5DTCmz9wWXdNfGpcE1wiUAoRjXbINnUIjSuydeNXptlkCNm2dPZTOtuWzmLpeOF6v9otVi4_8H3aCG73wIQYt2hMZX04OBW_Q8utu9o575z7NSOQc86-AcNoi9Y</recordid><startdate>20060901</startdate><enddate>20060901</enddate><creator>Zelnik-Manor, L.</creator><creator>Irani, M.</creator><general>IEEE</general><general>IEEE Computer Society</general><general>The Institute of Electrical and Electronics Engineers, Inc. (IEEE)</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>IQODW</scope><scope>CGR</scope><scope>CUY</scope><scope>CVF</scope><scope>ECM</scope><scope>EIF</scope><scope>NPM</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SC</scope><scope>7SP</scope><scope>8FD</scope><scope>JQ2</scope><scope>L7M</scope><scope>L~C</scope><scope>L~D</scope><scope>7X8</scope><scope>F28</scope><scope>FR3</scope></search><sort><creationdate>20060901</creationdate><title>Statistical analysis of dynamic actions</title><author>Zelnik-Manor, L. ; Irani, M.</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c442t-8181174278df13d270922600d3cf7dbb9e9ca455c813582065ca2e20be8c3c3f3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2006</creationdate><topic>Action recognition</topic><topic>Algorithms</topic><topic>Applied sciences</topic><topic>Artificial Intelligence</topic><topic>Computer science; control theory; systems</topic><topic>Dynamic range</topic><topic>Dynamic tests</topic><topic>Dynamical systems</topic><topic>Dynamics</topic><topic>Exact sciences and technology</topic><topic>Face recognition</topic><topic>Handles</topic><topic>Humans</topic><topic>Image Enhancement - methods</topic><topic>Image Interpretation, Computer-Assisted - methods</topic><topic>Image recognition</topic><topic>Image segmentation</topic><topic>Indexing</topic><topic>Information analysis</topic><topic>Information Storage and Retrieval - methods</topic><topic>Kinetics</topic><topic>Learning</topic><topic>Motion pictures</topic><topic>Movement - physiology</topic><topic>Parametric statistics</topic><topic>Pattern Recognition, Automated - methods</topic><topic>Pattern recognition. Digital image processing. Computational geometry</topic><topic>Statistical analysis</topic><topic>Tasks</topic><topic>Temporal logic</topic><topic>temporal segmentation</topic><topic>video indexing</topic><topic>Video Recording - methods</topic><topic>Video sequences</topic><topic>Walking - physiology</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Zelnik-Manor, L.</creatorcontrib><creatorcontrib>Irani, M.</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998-Present</collection><collection>IEEE Electronic Library (IEL)</collection><collection>Pascal-Francis</collection><collection>Medline</collection><collection>MEDLINE</collection><collection>MEDLINE (Ovid)</collection><collection>MEDLINE</collection><collection>MEDLINE</collection><collection>PubMed</collection><collection>CrossRef</collection><collection>Computer and Information Systems Abstracts</collection><collection>Electronics & Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ProQuest Computer Science Collection</collection><collection>Advanced Technologies Database with Aerospace</collection><collection>Computer and Information Systems Abstracts Academic</collection><collection>Computer and Information Systems Abstracts Professional</collection><collection>MEDLINE - Academic</collection><collection>ANTE: Abstracts in New Technology & Engineering</collection><collection>Engineering Research Database</collection><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext_linktorsrc</fulltext></delivery><addata><au>Zelnik-Manor, L.</au><au>Irani, M.</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>Statistical analysis of dynamic actions</atitle><jtitle>IEEE transactions on pattern analysis and machine intelligence</jtitle><stitle>TPAMI</stitle><addtitle>IEEE Trans Pattern Anal Mach Intell</addtitle><date>2006-09-01</date><risdate>2006</risdate><volume>28</volume><issue>9</issue><spage>1530</spage><epage>1535</epage><pages>1530-1535</pages><issn>0162-8828</issn><eissn>1939-3539</eissn><eissn>2160-9292</eissn><coden>ITPIDJ</coden><abstract>Real-world action recognition applications require the development of systems which are fast, can handle a large variety of actions without a priori knowledge of the type of actions, need a minimal number of parameters, and necessitate as short as possible learning stage. In this paper, we suggest such an approach. We regard dynamic activities as long-term temporal objects, which are characterized by spatio-temporal features at multiple temporal scales. Based on this, we design a simple statistical distance measure between video sequences which captures the similarities in their behavioral content. This measure is nonparametric and can thus handle a wide range of complex dynamic actions. Having a behavior-based distance measure between sequences, we use it for a variety of tasks, including: video indexing, temporal segmentation, and action-based video clustering. These tasks are performed without prior knowledge of the types of actions, their models, or their temporal extents</abstract><cop>Los Alamitos, CA</cop><pub>IEEE</pub><pmid>16929739</pmid><doi>10.1109/TPAMI.2006.194</doi><tpages>6</tpages><oa>free_for_read</oa></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 0162-8828 |
| ispartof | IEEE transactions on pattern analysis and machine intelligence, 2006-09, Vol.28 (9), p.1530-1535 |
| issn | 0162-8828 1939-3539 2160-9292 |
| language | eng |
| recordid | cdi_proquest_journals_865710220 |
| source | IEEE Electronic Library (IEL) |
| subjects | Action recognition Algorithms Applied sciences Artificial Intelligence Computer science control theory systems Dynamic range Dynamic tests Dynamical systems Dynamics Exact sciences and technology Face recognition Handles Humans Image Enhancement - methods Image Interpretation, Computer-Assisted - methods Image recognition Image segmentation Indexing Information analysis Information Storage and Retrieval - methods Kinetics Learning Motion pictures Movement - physiology Parametric statistics Pattern Recognition, Automated - methods Pattern recognition. Digital image processing. Computational geometry Statistical analysis Tasks Temporal logic temporal segmentation video indexing Video Recording - methods Video sequences Walking - physiology |
| title | Statistical analysis of dynamic actions |
| url | https://sfx.bib-bvb.de/sfx_tum?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-14T10%3A06%3A32IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_RIE&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=Statistical%20analysis%20of%20dynamic%20actions&rft.jtitle=IEEE%20transactions%20on%20pattern%20analysis%20and%20machine%20intelligence&rft.au=Zelnik-Manor,%20L.&rft.date=2006-09-01&rft.volume=28&rft.issue=9&rft.spage=1530&rft.epage=1535&rft.pages=1530-1535&rft.issn=0162-8828&rft.eissn=1939-3539&rft.coden=ITPIDJ&rft_id=info:doi/10.1109/TPAMI.2006.194&rft_dat=%3Cproquest_RIE%3E68784752%3C/proquest_RIE%3E%3Curl%3E%3C/url%3E&disable_directlink=true&sfx.directlink=off&sfx.report_link=0&rft_id=info:oai/&rft_pqid=865710220&rft_id=info:pmid/16929739&rft_ieee_id=1661555&rfr_iscdi=true |