Loading…
Remember and transfer what you have learned - recognizing composite activities based on activity spotting
Activity recognition approaches have shown to enable good performance for a wide variety of applications. Most approaches rely on machine learning techniques requiring significant amounts of training data for each application. Consequently they have to be retrained for each new application limiting...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Conference Proceeding |
| Language: | English |
| Subjects: | |
| Online Access: | Request full text |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| cited_by | |
|---|---|
| cites | |
| container_end_page | 8 |
| container_issue | |
| container_start_page | 1 |
| container_title | |
| container_volume | |
| creator | Blanke, U Schiele, B |
| description | Activity recognition approaches have shown to enable good performance for a wide variety of applications. Most approaches rely on machine learning techniques requiring significant amounts of training data for each application. Consequently they have to be retrained for each new application limiting the real-world applicability of today's activity recognition methods. This paper explores the possibility to transfer learned knowledge from one application to others thereby significantly reducing the required training data for new applications. To achieve this transferability the paper proposes a new layered activity recognition approach that lends itself to transfer knowledge across applications. Besides allowing to transfer knowledge across applications this layered approach also shows improved recognition performance both of composite activities as well as of activity events. |
| doi_str_mv | 10.1109/ISWC.2010.5665869 |
| format | conference_proceeding |
| fullrecord | <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_5665869</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>5665869</ieee_id><sourcerecordid>5665869</sourcerecordid><originalsourceid>FETCH-LOGICAL-i241t-85c11f7eb5b00d2174aa3521f542a3f085d2c53affe146404bd8de4b779868153</originalsourceid><addsrcrecordid>eNpFUNtKAzEQjTew1n6A-JIf2JrJZpLdRyleCgXBCz6W7O6kjXR3yyZW6tcbsOK8DOfCYc4wdgViCiDKm_nL-2wqRYKoNRa6PGIXoKRSpVCoj9lI5kZnBSo4-Re0OmUjQBSZKkCfs0kIHyINSmMUjph_ppbaigZuu4bHwXbBJfC1tpHv-0--tjviG7JDRw3P-EB1v-r8t-9WvO7bbR98JG7r6Hc-egq8siEZ--6P2_Ow7WNM_kt25uwm0OSwx-zt_u519pgtnh7ms9tF5qWCmO6vAZyhCishGglGWZujBIdK2tyJAhtZY26dI0jthKqaoiFVGVMWugDMx-z6N9cT0XI7-NYO--XhZfkPWYNc3A</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>Remember and transfer what you have learned - recognizing composite activities based on activity spotting</title><source>IEEE Xplore All Conference Series</source><creator>Blanke, U ; Schiele, B</creator><creatorcontrib>Blanke, U ; Schiele, B</creatorcontrib><description>Activity recognition approaches have shown to enable good performance for a wide variety of applications. Most approaches rely on machine learning techniques requiring significant amounts of training data for each application. Consequently they have to be retrained for each new application limiting the real-world applicability of today's activity recognition methods. This paper explores the possibility to transfer learned knowledge from one application to others thereby significantly reducing the required training data for new applications. To achieve this transferability the paper proposes a new layered activity recognition approach that lends itself to transfer knowledge across applications. Besides allowing to transfer knowledge across applications this layered approach also shows improved recognition performance both of composite activities as well as of activity events.</description><identifier>ISSN: 1550-4816</identifier><identifier>ISBN: 1424490464</identifier><identifier>ISBN: 9781424490462</identifier><identifier>EISSN: 2376-8541</identifier><identifier>EISBN: 1424490456</identifier><identifier>EISBN: 9781424490455</identifier><identifier>DOI: 10.1109/ISWC.2010.5665869</identifier><language>eng</language><publisher>IEEE</publisher><subject>Data models ; Hidden Markov models ; Joints ; Knowledge transfer ; Mirrors ; Training ; Training data</subject><ispartof>International Symposium on Wearable Computers (ISWC) 2010, 2010, p.1-8</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/5665869$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,778,782,787,788,2054,27912,54542,54907,54919</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/5665869$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Blanke, U</creatorcontrib><creatorcontrib>Schiele, B</creatorcontrib><title>Remember and transfer what you have learned - recognizing composite activities based on activity spotting</title><title>International Symposium on Wearable Computers (ISWC) 2010</title><addtitle>ISWC</addtitle><description>Activity recognition approaches have shown to enable good performance for a wide variety of applications. Most approaches rely on machine learning techniques requiring significant amounts of training data for each application. Consequently they have to be retrained for each new application limiting the real-world applicability of today's activity recognition methods. This paper explores the possibility to transfer learned knowledge from one application to others thereby significantly reducing the required training data for new applications. To achieve this transferability the paper proposes a new layered activity recognition approach that lends itself to transfer knowledge across applications. Besides allowing to transfer knowledge across applications this layered approach also shows improved recognition performance both of composite activities as well as of activity events.</description><subject>Data models</subject><subject>Hidden Markov models</subject><subject>Joints</subject><subject>Knowledge transfer</subject><subject>Mirrors</subject><subject>Training</subject><subject>Training data</subject><issn>1550-4816</issn><issn>2376-8541</issn><isbn>1424490464</isbn><isbn>9781424490462</isbn><isbn>1424490456</isbn><isbn>9781424490455</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2010</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNpFUNtKAzEQjTew1n6A-JIf2JrJZpLdRyleCgXBCz6W7O6kjXR3yyZW6tcbsOK8DOfCYc4wdgViCiDKm_nL-2wqRYKoNRa6PGIXoKRSpVCoj9lI5kZnBSo4-Re0OmUjQBSZKkCfs0kIHyINSmMUjph_ppbaigZuu4bHwXbBJfC1tpHv-0--tjviG7JDRw3P-EB1v-r8t-9WvO7bbR98JG7r6Hc-egq8siEZ--6P2_Ow7WNM_kt25uwm0OSwx-zt_u519pgtnh7ms9tF5qWCmO6vAZyhCishGglGWZujBIdK2tyJAhtZY26dI0jthKqaoiFVGVMWugDMx-z6N9cT0XI7-NYO--XhZfkPWYNc3A</recordid><startdate>201010</startdate><enddate>201010</enddate><creator>Blanke, U</creator><creator>Schiele, B</creator><general>IEEE</general><scope>6IE</scope><scope>6IL</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIL</scope></search><sort><creationdate>201010</creationdate><title>Remember and transfer what you have learned - recognizing composite activities based on activity spotting</title><author>Blanke, U ; Schiele, B</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i241t-85c11f7eb5b00d2174aa3521f542a3f085d2c53affe146404bd8de4b779868153</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2010</creationdate><topic>Data models</topic><topic>Hidden Markov models</topic><topic>Joints</topic><topic>Knowledge transfer</topic><topic>Mirrors</topic><topic>Training</topic><topic>Training data</topic><toplevel>online_resources</toplevel><creatorcontrib>Blanke, U</creatorcontrib><creatorcontrib>Schiele, 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/IET Electronic Library</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>Blanke, U</au><au>Schiele, B</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>Remember and transfer what you have learned - recognizing composite activities based on activity spotting</atitle><btitle>International Symposium on Wearable Computers (ISWC) 2010</btitle><stitle>ISWC</stitle><date>2010-10</date><risdate>2010</risdate><spage>1</spage><epage>8</epage><pages>1-8</pages><issn>1550-4816</issn><eissn>2376-8541</eissn><isbn>1424490464</isbn><isbn>9781424490462</isbn><eisbn>1424490456</eisbn><eisbn>9781424490455</eisbn><abstract>Activity recognition approaches have shown to enable good performance for a wide variety of applications. Most approaches rely on machine learning techniques requiring significant amounts of training data for each application. Consequently they have to be retrained for each new application limiting the real-world applicability of today's activity recognition methods. This paper explores the possibility to transfer learned knowledge from one application to others thereby significantly reducing the required training data for new applications. To achieve this transferability the paper proposes a new layered activity recognition approach that lends itself to transfer knowledge across applications. Besides allowing to transfer knowledge across applications this layered approach also shows improved recognition performance both of composite activities as well as of activity events.</abstract><pub>IEEE</pub><doi>10.1109/ISWC.2010.5665869</doi><tpages>8</tpages></addata></record> |
| fulltext | fulltext_linktorsrc |
| identifier | ISSN: 1550-4816 |
| ispartof | International Symposium on Wearable Computers (ISWC) 2010, 2010, p.1-8 |
| issn | 1550-4816 2376-8541 |
| language | eng |
| recordid | cdi_ieee_primary_5665869 |
| source | IEEE Xplore All Conference Series |
| subjects | Data models Hidden Markov models Joints Knowledge transfer Mirrors Training Training data |
| title | Remember and transfer what you have learned - recognizing composite activities based on activity spotting |
| url | http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-01-15T20%3A42%3A30IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-ieee_CHZPO&rft_val_fmt=info:ofi/fmt:kev:mtx:book&rft.genre=proceeding&rft.atitle=Remember%20and%20transfer%20what%20you%20have%20learned%20-%20recognizing%20composite%20activities%20based%20on%20activity%20spotting&rft.btitle=International%20Symposium%20on%20Wearable%20Computers%20(ISWC)%202010&rft.au=Blanke,%20U&rft.date=2010-10&rft.spage=1&rft.epage=8&rft.pages=1-8&rft.issn=1550-4816&rft.eissn=2376-8541&rft.isbn=1424490464&rft.isbn_list=9781424490462&rft_id=info:doi/10.1109/ISWC.2010.5665869&rft.eisbn=1424490456&rft.eisbn_list=9781424490455&rft_dat=%3Cieee_CHZPO%3E5665869%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i241t-85c11f7eb5b00d2174aa3521f542a3f085d2c53affe146404bd8de4b779868153%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_id=info:pmid/&rft_ieee_id=5665869&rfr_iscdi=true |