p-Laplacian Regularized Sparse Coding for Human Activity Recognition

Human activity analysis in videos has increasingly attracted attention in computer vision research with the massive number of videos now accessible online. Although many recognition algorithms have been reported recently, activity representation is challenging. Recently, manifold regularized sparse...

Full description

Saved in:
Bibliographic Details
Published in:IEEE transactions on industrial electronics (1982) 2016-08, Vol.63 (8), p.5120-5129
Main Authors: Liu, Weifeng, Zha, Zheng-Jun, Wang, Yanjiang, Lu, Ke, Tao, Dacheng
Format: Article
Language:English
Subjects:
Algorithms
Coding
Dictionaries
Encoding
Feature extraction
Human activity recognition
Human motion
Image coding
Laplace equations
manifold
Manifolds
Moving object recognition
p-Laplacian
Preserves
Representations
sparse coding
Videos
Citations: Items that this one cites
Items that cite this one
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by cdi_FETCH-LOGICAL-c296t-5ab086a71c7184c3f2f2c8d988702376e36ee6a079984e5f738367aee489c80c3
cites cdi_FETCH-LOGICAL-c296t-5ab086a71c7184c3f2f2c8d988702376e36ee6a079984e5f738367aee489c80c3
container_end_page 5129
container_issue 8
container_start_page 5120
container_title IEEE transactions on industrial electronics (1982)
container_volume 63
creator Liu, Weifeng
Zha, Zheng-Jun
Wang, Yanjiang
Lu, Ke
Tao, Dacheng
description Human activity analysis in videos has increasingly attracted attention in computer vision research with the massive number of videos now accessible online. Although many recognition algorithms have been reported recently, activity representation is challenging. Recently, manifold regularized sparse coding has obtained promising performance in action recognition, because it simultaneously learns the sparse representation and preserves the manifold structure. In this paper, we propose a generalized version of Laplacian regularized sparse coding for human activity recognition called p-Laplacian regularized sparse coding (pLSC). The proposed method exploits p-Laplacian regularization to preserve the local geometry. The p-Laplacian is a nonlinear generalization of standard graph Laplacian and has tighter isoperimetric inequality. As a result, pLSC provides superior theoretical evidence than standard Laplacian regularized sparse coding with a proper p. We also provide a fast iterative shrinkage-thresholding algorithm for the optimization of pLSC. Finally, we input the sparse codes learned by the pLSC algorithm into support vector machines and conduct extensive experiments on the unstructured social activity attribute dataset and human motion database (HMDB51) for human activity recognition. The experimental results demonstrate that the proposed pLSC algorithm outperforms the manifold regularized sparse coding algorithms including the standard Laplacian regularized sparse coding algorithm with a proper p.
doi_str_mv 10.1109/TIE.2016.2552147
format article
fullrecord <record><control><sourceid>proquest_cross</sourceid><recordid>TN_cdi_crossref_primary_10_1109_TIE_2016_2552147</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>7448894</ieee_id><sourcerecordid>1825567095</sourcerecordid><originalsourceid>FETCH-LOGICAL-c296t-5ab086a71c7184c3f2f2c8d988702376e36ee6a079984e5f738367aee489c80c3</originalsourceid><addsrcrecordid>eNo9kE1Lw0AURQdRsFb3gpss3aS-mcznstTWFgqC1vUwTl_KSJrEmUSov96UFld3c-6Fewi5pzChFMzTZjWfMKBywoRglKsLMqJCqNwYri_JCJjSOQCX1-QmpS8AygUVI_Lc5mvXVs4HV2dvuOsrF8MvbrP31sWE2azZhnqXlU3Mlv1-YKa-Cz-hOwywb3Z16EJT35Kr0lUJ7845Jh-L-Wa2zNevL6vZdJ17ZmSXC_cJWjpFvaKa-6JkJfN6a7RWwAolsZCI0oEyRnMUpSp0IZVD5Np4Db4Yk8fTbhub7x5TZ_cheawqV2PTJ0v1cF4qMGJA4YT62KQUsbRtDHsXD5aCPQqzgzB7FGbPwobKw6kSEPEfV5xrbXjxBzwiZcM</addsrcrecordid><sourcetype>Aggregation Database</sourcetype><iscdi>true</iscdi><recordtype>article</recordtype><pqid>1825567095</pqid></control><display><type>article</type><title>p-Laplacian Regularized Sparse Coding for Human Activity Recognition</title><source>IEEE Electronic Library (IEL) Journals</source><creator>Liu, Weifeng ; Zha, Zheng-Jun ; Wang, Yanjiang ; Lu, Ke ; Tao, Dacheng</creator><creatorcontrib>Liu, Weifeng ; Zha, Zheng-Jun ; Wang, Yanjiang ; Lu, Ke ; Tao, Dacheng</creatorcontrib><description>Human activity analysis in videos has increasingly attracted attention in computer vision research with the massive number of videos now accessible online. Although many recognition algorithms have been reported recently, activity representation is challenging. Recently, manifold regularized sparse coding has obtained promising performance in action recognition, because it simultaneously learns the sparse representation and preserves the manifold structure. In this paper, we propose a generalized version of Laplacian regularized sparse coding for human activity recognition called p-Laplacian regularized sparse coding (pLSC). The proposed method exploits p-Laplacian regularization to preserve the local geometry. The p-Laplacian is a nonlinear generalization of standard graph Laplacian and has tighter isoperimetric inequality. As a result, pLSC provides superior theoretical evidence than standard Laplacian regularized sparse coding with a proper p. We also provide a fast iterative shrinkage-thresholding algorithm for the optimization of pLSC. Finally, we input the sparse codes learned by the pLSC algorithm into support vector machines and conduct extensive experiments on the unstructured social activity attribute dataset and human motion database (HMDB51) for human activity recognition. The experimental results demonstrate that the proposed pLSC algorithm outperforms the manifold regularized sparse coding algorithms including the standard Laplacian regularized sparse coding algorithm with a proper p.</description><identifier>ISSN: 0278-0046</identifier><identifier>EISSN: 1557-9948</identifier><identifier>DOI: 10.1109/TIE.2016.2552147</identifier><identifier>CODEN: ITIED6</identifier><language>eng</language><publisher>IEEE</publisher><subject>Algorithms ; Coding ; Dictionaries ; Encoding ; Feature extraction ; Human activity recognition ; Human motion ; Image coding ; Laplace equations ; manifold ; Manifolds ; Moving object recognition ; p-Laplacian ; Preserves ; Representations ; sparse coding ; Videos</subject><ispartof>IEEE transactions on industrial electronics (1982), 2016-08, Vol.63 (8), p.5120-5129</ispartof><lds50>peer_reviewed</lds50><woscitedreferencessubscribed>false</woscitedreferencessubscribed><citedby>FETCH-LOGICAL-c296t-5ab086a71c7184c3f2f2c8d988702376e36ee6a079984e5f738367aee489c80c3</citedby><cites>FETCH-LOGICAL-c296t-5ab086a71c7184c3f2f2c8d988702376e36ee6a079984e5f738367aee489c80c3</cites></display><links><openurl>$$Topenurl_article</openurl><openurlfulltext>$$Topenurlfull_article</openurlfulltext><thumbnail>$$Tsyndetics_thumb_exl</thumbnail><linktohtml>$$Uhttps://ieeexplore.ieee.org/document/7448894$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>315,786,790,27957,27958,55147</link.rule.ids></links><search><creatorcontrib>Liu, Weifeng</creatorcontrib><creatorcontrib>Zha, Zheng-Jun</creatorcontrib><creatorcontrib>Wang, Yanjiang</creatorcontrib><creatorcontrib>Lu, Ke</creatorcontrib><creatorcontrib>Tao, Dacheng</creatorcontrib><title>p-Laplacian Regularized Sparse Coding for Human Activity Recognition</title><title>IEEE transactions on industrial electronics (1982)</title><addtitle>TIE</addtitle><description>Human activity analysis in videos has increasingly attracted attention in computer vision research with the massive number of videos now accessible online. Although many recognition algorithms have been reported recently, activity representation is challenging. Recently, manifold regularized sparse coding has obtained promising performance in action recognition, because it simultaneously learns the sparse representation and preserves the manifold structure. In this paper, we propose a generalized version of Laplacian regularized sparse coding for human activity recognition called p-Laplacian regularized sparse coding (pLSC). The proposed method exploits p-Laplacian regularization to preserve the local geometry. The p-Laplacian is a nonlinear generalization of standard graph Laplacian and has tighter isoperimetric inequality. As a result, pLSC provides superior theoretical evidence than standard Laplacian regularized sparse coding with a proper p. We also provide a fast iterative shrinkage-thresholding algorithm for the optimization of pLSC. Finally, we input the sparse codes learned by the pLSC algorithm into support vector machines and conduct extensive experiments on the unstructured social activity attribute dataset and human motion database (HMDB51) for human activity recognition. The experimental results demonstrate that the proposed pLSC algorithm outperforms the manifold regularized sparse coding algorithms including the standard Laplacian regularized sparse coding algorithm with a proper p.</description><subject>Algorithms</subject><subject>Coding</subject><subject>Dictionaries</subject><subject>Encoding</subject><subject>Feature extraction</subject><subject>Human activity recognition</subject><subject>Human motion</subject><subject>Image coding</subject><subject>Laplace equations</subject><subject>manifold</subject><subject>Manifolds</subject><subject>Moving object recognition</subject><subject>p-Laplacian</subject><subject>Preserves</subject><subject>Representations</subject><subject>sparse coding</subject><subject>Videos</subject><issn>0278-0046</issn><issn>1557-9948</issn><fulltext>true</fulltext><rsrctype>article</rsrctype><creationdate>2016</creationdate><recordtype>article</recordtype><recordid>eNo9kE1Lw0AURQdRsFb3gpss3aS-mcznstTWFgqC1vUwTl_KSJrEmUSov96UFld3c-6Fewi5pzChFMzTZjWfMKBywoRglKsLMqJCqNwYri_JCJjSOQCX1-QmpS8AygUVI_Lc5mvXVs4HV2dvuOsrF8MvbrP31sWE2azZhnqXlU3Mlv1-YKa-Cz-hOwywb3Z16EJT35Kr0lUJ7845Jh-L-Wa2zNevL6vZdJ17ZmSXC_cJWjpFvaKa-6JkJfN6a7RWwAolsZCI0oEyRnMUpSp0IZVD5Np4Db4Yk8fTbhub7x5TZ_cheawqV2PTJ0v1cF4qMGJA4YT62KQUsbRtDHsXD5aCPQqzgzB7FGbPwobKw6kSEPEfV5xrbXjxBzwiZcM</recordid><startdate>20160801</startdate><enddate>20160801</enddate><creator>Liu, Weifeng</creator><creator>Zha, Zheng-Jun</creator><creator>Wang, Yanjiang</creator><creator>Lu, Ke</creator><creator>Tao, Dacheng</creator><general>IEEE</general><scope>97E</scope><scope>RIA</scope><scope>RIE</scope><scope>AAYXX</scope><scope>CITATION</scope><scope>7SP</scope><scope>8FD</scope><scope>F28</scope><scope>FR3</scope><scope>L7M</scope></search><sort><creationdate>20160801</creationdate><title>p-Laplacian Regularized Sparse Coding for Human Activity Recognition</title><author>Liu, Weifeng ; Zha, Zheng-Jun ; Wang, Yanjiang ; Lu, Ke ; Tao, Dacheng</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-c296t-5ab086a71c7184c3f2f2c8d988702376e36ee6a079984e5f738367aee489c80c3</frbrgroupid><rsrctype>articles</rsrctype><prefilter>articles</prefilter><language>eng</language><creationdate>2016</creationdate><topic>Algorithms</topic><topic>Coding</topic><topic>Dictionaries</topic><topic>Encoding</topic><topic>Feature extraction</topic><topic>Human activity recognition</topic><topic>Human motion</topic><topic>Image coding</topic><topic>Laplace equations</topic><topic>manifold</topic><topic>Manifolds</topic><topic>Moving object recognition</topic><topic>p-Laplacian</topic><topic>Preserves</topic><topic>Representations</topic><topic>sparse coding</topic><topic>Videos</topic><toplevel>peer_reviewed</toplevel><toplevel>online_resources</toplevel><creatorcontrib>Liu, Weifeng</creatorcontrib><creatorcontrib>Zha, Zheng-Jun</creatorcontrib><creatorcontrib>Wang, Yanjiang</creatorcontrib><creatorcontrib>Lu, Ke</creatorcontrib><creatorcontrib>Tao, Dacheng</creatorcontrib><collection>IEEE All-Society Periodicals Package (ASPP) 2005-present</collection><collection>IEEE All-Society Periodicals Package (ASPP) 1998–Present</collection><collection>IEL</collection><collection>CrossRef</collection><collection>Electronics &amp; Communications Abstracts</collection><collection>Technology Research Database</collection><collection>ANTE: Abstracts in New Technology &amp; Engineering</collection><collection>Engineering Research Database</collection><collection>Advanced Technologies Database with Aerospace</collection><jtitle>IEEE transactions on industrial electronics (1982)</jtitle></facets><delivery><delcategory>Remote Search Resource</delcategory><fulltext>fulltext</fulltext></delivery><addata><au>Liu, Weifeng</au><au>Zha, Zheng-Jun</au><au>Wang, Yanjiang</au><au>Lu, Ke</au><au>Tao, Dacheng</au><format>journal</format><genre>article</genre><ristype>JOUR</ristype><atitle>p-Laplacian Regularized Sparse Coding for Human Activity Recognition</atitle><jtitle>IEEE transactions on industrial electronics (1982)</jtitle><stitle>TIE</stitle><date>2016-08-01</date><risdate>2016</risdate><volume>63</volume><issue>8</issue><spage>5120</spage><epage>5129</epage><pages>5120-5129</pages><issn>0278-0046</issn><eissn>1557-9948</eissn><coden>ITIED6</coden><notes>ObjectType-Article-1</notes><notes>SourceType-Scholarly Journals-1</notes><notes>ObjectType-Feature-2</notes><notes>content type line 23</notes><abstract>Human activity analysis in videos has increasingly attracted attention in computer vision research with the massive number of videos now accessible online. Although many recognition algorithms have been reported recently, activity representation is challenging. Recently, manifold regularized sparse coding has obtained promising performance in action recognition, because it simultaneously learns the sparse representation and preserves the manifold structure. In this paper, we propose a generalized version of Laplacian regularized sparse coding for human activity recognition called p-Laplacian regularized sparse coding (pLSC). The proposed method exploits p-Laplacian regularization to preserve the local geometry. The p-Laplacian is a nonlinear generalization of standard graph Laplacian and has tighter isoperimetric inequality. As a result, pLSC provides superior theoretical evidence than standard Laplacian regularized sparse coding with a proper p. We also provide a fast iterative shrinkage-thresholding algorithm for the optimization of pLSC. Finally, we input the sparse codes learned by the pLSC algorithm into support vector machines and conduct extensive experiments on the unstructured social activity attribute dataset and human motion database (HMDB51) for human activity recognition. The experimental results demonstrate that the proposed pLSC algorithm outperforms the manifold regularized sparse coding algorithms including the standard Laplacian regularized sparse coding algorithm with a proper p.</abstract><pub>IEEE</pub><doi>10.1109/TIE.2016.2552147</doi><tpages>10</tpages></addata></record>
fulltext fulltext
identifier ISSN: 0278-0046
ispartof IEEE transactions on industrial electronics (1982), 2016-08, Vol.63 (8), p.5120-5129
issn 0278-0046
1557-9948
language eng
recordid cdi_crossref_primary_10_1109_TIE_2016_2552147
source IEEE Electronic Library (IEL) Journals
subjects Algorithms
Coding
Dictionaries
Encoding
Feature extraction
Human activity recognition
Human motion
Image coding
Laplace equations
manifold
Manifolds
Moving object recognition
p-Laplacian
Preserves
Representations
sparse coding
Videos
title p-Laplacian Regularized Sparse Coding for Human Activity Recognition
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2024-09-22T06%3A21%3A15IST&url_ver=Z39.88-2004&url_ctx_fmt=infofi/fmt:kev:mtx:ctx&rfr_id=info:sid/primo.exlibrisgroup.com:primo3-Article-proquest_cross&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.genre=article&rft.atitle=p-Laplacian%20Regularized%20Sparse%20Coding%20for%20Human%20Activity%20Recognition&rft.jtitle=IEEE%20transactions%20on%20industrial%20electronics%20(1982)&rft.au=Liu,%20Weifeng&rft.date=2016-08-01&rft.volume=63&rft.issue=8&rft.spage=5120&rft.epage=5129&rft.pages=5120-5129&rft.issn=0278-0046&rft.eissn=1557-9948&rft.coden=ITIED6&rft_id=info:doi/10.1109/TIE.2016.2552147&rft_dat=%3Cproquest_cross%3E1825567095%3C/proquest_cross%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-c296t-5ab086a71c7184c3f2f2c8d988702376e36ee6a079984e5f738367aee489c80c3%3C/grp_id%3E%3Coa%3E%3C/oa%3E%3Curl%3E%3C/url%3E&rft_id=info:oai/&rft_pqid=1825567095&rft_id=info:pmid/&rft_ieee_id=7448894&rfr_iscdi=true