A 2D Convolutional Neural Network Approach for Human Action Recognition

Nowadays, deep neural networks are widely used for human action recognition (HAR) due to their ability to operate directly on the raw video inputs by extracting both the spatial and temporal information. Although the 3D convolutional neural networks as deep models have achieved superior performance,...

Full description

Saved in:
Bibliographic Details
Main Authors: Toudjeu, Ignace Tchangou, Tapamo, Jules-Raymond
Format: Conference Proceeding
Language:English
Subjects:
Computational modeling
Convolution
convolutional neural network
Deep learning
Feature extraction
History
human action recognition
Kernel
motion history image
Two dimensional displays
Online Access:Request full text
Tags: Add Tag
No Tags, Be the first to tag this record!
cited_by
cites
container_end_page 5
container_issue
container_start_page 1
container_title
container_volume
creator Toudjeu, Ignace Tchangou
Tapamo, Jules-Raymond
description Nowadays, deep neural networks are widely used for human action recognition (HAR) due to their ability to operate directly on the raw video inputs by extracting both the spatial and temporal information. Although the 3D convolutional neural networks as deep models have achieved superior performance, they remain computational expensive. In this paper we propose a 2D-CNN approach that learns robust feature representation from temporal information embedded into the motion history images of action videos. The proposed approach is simple and reduces the computational complexity imposed by the 3D-CNN approaches. The KTH database is used to validate our approach and the achieved results are compared favorably against the handcrafted state-of-the-art methods.
doi_str_mv 10.1109/AFRICON46755.2019.9133840
format conference_proceeding
fullrecord <record><control><sourceid>ieee_CHZPO</sourceid><recordid>TN_cdi_ieee_primary_9133840</recordid><sourceformat>XML</sourceformat><sourcesystem>PC</sourcesystem><ieee_id>9133840</ieee_id><sourcerecordid>9133840</sourcerecordid><originalsourceid>FETCH-LOGICAL-i203t-a51cb82074e1d5be99354bf30aeeba8118bc7dac5363a2be49043c70d3afc6bc3</originalsourceid><addsrcrecordid>eNotj81KAzEURqMgWGufwE18gKn35iadZDmM9gdKC0XXJUkzOtpOhsxU8e1LtavzLQ4fHMYeEcaIYJ6K6WZRrldykis1FoBmbJBIS7hid5gLjSS0kddsIFBRBkB0y0Zd9wkACFoRqQGbFVw88zI233F_7OvY2D1fhWP6Q_8T0xcv2jZF6z94FROfHw-24YU_q3wTfHxv6vO-ZzeV3XdhdOGQvU1fXst5tlzPFmWxzGoB1GdWoXdaQC4D7pQLxpCSriKwITirEbXz-c56RROywgVpQJLPYUe28hPnacge_n_rEMK2TfXBpt_tpZtO3IhN9g</addsrcrecordid><sourcetype>Publisher</sourcetype><iscdi>true</iscdi><recordtype>conference_proceeding</recordtype></control><display><type>conference_proceeding</type><title>A 2D Convolutional Neural Network Approach for Human Action Recognition</title><source>IEEE Xplore All Conference Series</source><creator>Toudjeu, Ignace Tchangou ; Tapamo, Jules-Raymond</creator><creatorcontrib>Toudjeu, Ignace Tchangou ; Tapamo, Jules-Raymond</creatorcontrib><description>Nowadays, deep neural networks are widely used for human action recognition (HAR) due to their ability to operate directly on the raw video inputs by extracting both the spatial and temporal information. Although the 3D convolutional neural networks as deep models have achieved superior performance, they remain computational expensive. In this paper we propose a 2D-CNN approach that learns robust feature representation from temporal information embedded into the motion history images of action videos. The proposed approach is simple and reduces the computational complexity imposed by the 3D-CNN approaches. The KTH database is used to validate our approach and the achieved results are compared favorably against the handcrafted state-of-the-art methods.</description><identifier>EISSN: 2153-0033</identifier><identifier>EISBN: 1728132894</identifier><identifier>EISBN: 9781728132891</identifier><identifier>DOI: 10.1109/AFRICON46755.2019.9133840</identifier><language>eng</language><publisher>IEEE</publisher><subject>Computational modeling ; Convolution ; convolutional neural network ; Deep learning ; Feature extraction ; History ; human action recognition ; Kernel ; motion history image ; Two dimensional displays</subject><ispartof>2019 IEEE AFRICON, 2019, p.1-5</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/9133840$$EHTML$$P50$$Gieee$$H</linktohtml><link.rule.ids>309,310,776,780,785,786,23909,23910,25118,27902,54530,54907</link.rule.ids><linktorsrc>$$Uhttps://ieeexplore.ieee.org/document/9133840$$EView_record_in_IEEE$$FView_record_in_$$GIEEE</linktorsrc></links><search><creatorcontrib>Toudjeu, Ignace Tchangou</creatorcontrib><creatorcontrib>Tapamo, Jules-Raymond</creatorcontrib><title>A 2D Convolutional Neural Network Approach for Human Action Recognition</title><title>2019 IEEE AFRICON</title><addtitle>AFRICON</addtitle><description>Nowadays, deep neural networks are widely used for human action recognition (HAR) due to their ability to operate directly on the raw video inputs by extracting both the spatial and temporal information. Although the 3D convolutional neural networks as deep models have achieved superior performance, they remain computational expensive. In this paper we propose a 2D-CNN approach that learns robust feature representation from temporal information embedded into the motion history images of action videos. The proposed approach is simple and reduces the computational complexity imposed by the 3D-CNN approaches. The KTH database is used to validate our approach and the achieved results are compared favorably against the handcrafted state-of-the-art methods.</description><subject>Computational modeling</subject><subject>Convolution</subject><subject>convolutional neural network</subject><subject>Deep learning</subject><subject>Feature extraction</subject><subject>History</subject><subject>human action recognition</subject><subject>Kernel</subject><subject>motion history image</subject><subject>Two dimensional displays</subject><issn>2153-0033</issn><isbn>1728132894</isbn><isbn>9781728132891</isbn><fulltext>true</fulltext><rsrctype>conference_proceeding</rsrctype><creationdate>2019</creationdate><recordtype>conference_proceeding</recordtype><sourceid>6IE</sourceid><recordid>eNotj81KAzEURqMgWGufwE18gKn35iadZDmM9gdKC0XXJUkzOtpOhsxU8e1LtavzLQ4fHMYeEcaIYJ6K6WZRrldykis1FoBmbJBIS7hid5gLjSS0kddsIFBRBkB0y0Zd9wkACFoRqQGbFVw88zI233F_7OvY2D1fhWP6Q_8T0xcv2jZF6z94FROfHw-24YU_q3wTfHxv6vO-ZzeV3XdhdOGQvU1fXst5tlzPFmWxzGoB1GdWoXdaQC4D7pQLxpCSriKwITirEbXz-c56RROywgVpQJLPYUe28hPnacge_n_rEMK2TfXBpt_tpZtO3IhN9g</recordid><startdate>201909</startdate><enddate>201909</enddate><creator>Toudjeu, Ignace Tchangou</creator><creator>Tapamo, Jules-Raymond</creator><general>IEEE</general><scope>6IE</scope><scope>6IH</scope><scope>CBEJK</scope><scope>RIE</scope><scope>RIO</scope></search><sort><creationdate>201909</creationdate><title>A 2D Convolutional Neural Network Approach for Human Action Recognition</title><author>Toudjeu, Ignace Tchangou ; Tapamo, Jules-Raymond</author></sort><facets><frbrtype>5</frbrtype><frbrgroupid>cdi_FETCH-LOGICAL-i203t-a51cb82074e1d5be99354bf30aeeba8118bc7dac5363a2be49043c70d3afc6bc3</frbrgroupid><rsrctype>conference_proceedings</rsrctype><prefilter>conference_proceedings</prefilter><language>eng</language><creationdate>2019</creationdate><topic>Computational modeling</topic><topic>Convolution</topic><topic>convolutional neural network</topic><topic>Deep learning</topic><topic>Feature extraction</topic><topic>History</topic><topic>human action recognition</topic><topic>Kernel</topic><topic>motion history image</topic><topic>Two dimensional displays</topic><toplevel>online_resources</toplevel><creatorcontrib>Toudjeu, Ignace Tchangou</creatorcontrib><creatorcontrib>Tapamo, Jules-Raymond</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/IET 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>Toudjeu, Ignace Tchangou</au><au>Tapamo, Jules-Raymond</au><format>book</format><genre>proceeding</genre><ristype>CONF</ristype><atitle>A 2D Convolutional Neural Network Approach for Human Action Recognition</atitle><btitle>2019 IEEE AFRICON</btitle><stitle>AFRICON</stitle><date>2019-09</date><risdate>2019</risdate><spage>1</spage><epage>5</epage><pages>1-5</pages><eissn>2153-0033</eissn><eisbn>1728132894</eisbn><eisbn>9781728132891</eisbn><abstract>Nowadays, deep neural networks are widely used for human action recognition (HAR) due to their ability to operate directly on the raw video inputs by extracting both the spatial and temporal information. Although the 3D convolutional neural networks as deep models have achieved superior performance, they remain computational expensive. In this paper we propose a 2D-CNN approach that learns robust feature representation from temporal information embedded into the motion history images of action videos. The proposed approach is simple and reduces the computational complexity imposed by the 3D-CNN approaches. The KTH database is used to validate our approach and the achieved results are compared favorably against the handcrafted state-of-the-art methods.</abstract><pub>IEEE</pub><doi>10.1109/AFRICON46755.2019.9133840</doi><tpages>5</tpages></addata></record>
fulltext fulltext_linktorsrc
identifier EISSN: 2153-0033
ispartof 2019 IEEE AFRICON, 2019, p.1-5
issn 2153-0033
language eng
recordid cdi_ieee_primary_9133840
source IEEE Xplore All Conference Series
subjects Computational modeling
Convolution
convolutional neural network
Deep learning
Feature extraction
History
human action recognition
Kernel
motion history image
Two dimensional displays
title A 2D Convolutional Neural Network Approach for Human Action Recognition
url http://sfxeu10.hosted.exlibrisgroup.com/loughborough?ctx_ver=Z39.88-2004&ctx_enc=info:ofi/enc:UTF-8&ctx_tim=2025-02-02T07%3A47%3A41IST&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=A%202D%20Convolutional%20Neural%20Network%20Approach%20for%20Human%20Action%20Recognition&rft.btitle=2019%20IEEE%20AFRICON&rft.au=Toudjeu,%20Ignace%20Tchangou&rft.date=2019-09&rft.spage=1&rft.epage=5&rft.pages=1-5&rft.eissn=2153-0033&rft_id=info:doi/10.1109/AFRICON46755.2019.9133840&rft.eisbn=1728132894&rft.eisbn_list=9781728132891&rft_dat=%3Cieee_CHZPO%3E9133840%3C/ieee_CHZPO%3E%3Cgrp_id%3Ecdi_FETCH-LOGICAL-i203t-a51cb82074e1d5be99354bf30aeeba8118bc7dac5363a2be49043c70d3afc6bc3%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=9133840&rfr_iscdi=true