Repository logo
 
Publication

Human action recognition in videos with articulated pose information by deep networks

2019-11Journal article Restricted access
Simple item page
dc.contributor.authorFarrajota, Miguel
dc.contributor.authorRodrigues, João
dc.contributor.authordu Buf, J. M. H.
dc.date.accessioned2020-07-24T10:51:09Z
dc.date.available2020-07-24T10:51:09Z
dc.date.issued2019-11
dc.description.abstractAction recognition is of great importance in understanding human motion from video. It is an important topic in computer vision due to its many applications such as video surveillance, human-machine interaction and video retrieval. One key problem is to automatically recognize low-level actions and high-level activities of interest. This paper proposes a way to cope with low-level actions by combining information of human body joints to aid action recognition. This is achieved by using high-level features computed by a convolutional neural network which was pre-trained on Imagenet, with articulated body joints as low-level features. These features are then used to feed a Long Short-Term Memory network to learn the temporal dependencies of an action. For pose prediction, we focus on articulated relations between body joints. We employ a series of residual auto-encoders to produce multiple predictions which are then combined to provide a likelihood map of body joints. In the network topology, features are processed across all scales which capture the various spatial relationships associated with the body. Repeated bottom-up and top-down processing with intermediate supervision of each auto-encoder network is applied. We demonstrate state-of-the-art results on the popular FLIC, LSP and UCF Sports datasets.
dc.description.sponsorshipFCT Project LARSyS [UID/EEA/50009/2013]
dc.description.sponsorshipFCT Ph.D. GrantPortuguese Foundation for Science and Technology [SFRH/BD/79812/2011]
dc.description.versioninfo:eu-repo/semantics/publishedVersion
dc.identifier.doi10.1007/s10044-018-0727-y
dc.identifier.issn1433-7541
dc.identifier.urihttp://hdl.handle.net/10400.1/14203
dc.language.isoeng
dc.peerreviewedyes
dc.publisherSpringer
dc.relationNEURAL CORRELATES OF MOTION AND STEREO VISION IN HUMAN POSE AND GAIT DETECTION
dc.subjectHuman action
dc.subjectHuman pose
dc.subjectConvNet
dc.subjectNeural networks
dc.subjectAuto-encoders
dc.subjectLSTM
dc.titleHuman action recognition in videos with articulated pose information by deep networks
dc.typejournal article
dspace.entity.typePublication
oaire.awardTitleNEURAL CORRELATES OF MOTION AND STEREO VISION IN HUMAN POSE AND GAIT DETECTION
oaire.awardURIinfo:eu-repo/grantAgreement/FCT/5876/UID%2FEEA%2F50009%2F2013/PT
oaire.awardURIinfo:eu-repo/grantAgreement/FCT//SFRH%2FBD%2F79812%2F2011/PT
oaire.citation.endPage1318
oaire.citation.issue4
oaire.citation.startPage1307
oaire.citation.titlePattern Analysis and Applications
oaire.citation.volume22
oaire.fundingStream5876
person.familyNameFarrajota
person.familyNameRodrigues
person.familyNamedu Buf
person.givenNameMiguel
person.givenNameJoao
person.givenNameHans
person.identifier.ciencia-id8A19-98F7-9914
person.identifier.orcid0000-0001-7970-4649
person.identifier.orcid0000-0002-3562-6025
person.identifier.orcid0000-0002-4345-1237
person.identifier.ridM-5125-2013
person.identifier.scopus-author-id55807461600
person.identifier.scopus-author-id6604075916
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.identifierhttp://doi.org/10.13039/501100001871
project.funder.nameFundação para a Ciência e a Tecnologia
project.funder.nameFundação para a Ciência e a Tecnologia
rcaap.rightsrestrictedAccess
rcaap.typearticle
relation.isAuthorOfPublicationca40db25-2109-4390-ad94-c5f28803c7e8
relation.isAuthorOfPublication683ba85b-459c-4789-a4ff-a4e2a904b295
relation.isAuthorOfPublicationcfad5636-2c77-4db0-a3a0-d7eb97ce6bee
relation.isAuthorOfPublication.latestForDiscovery683ba85b-459c-4789-a4ff-a4e2a904b295
relation.isProjectOfPublication19a727e2-d775-407f-ab10-7d5f19577e08
relation.isProjectOfPublicationd150d21b-0a3e-4403-92cb-65f221ecb683
relation.isProjectOfPublication.latestForDiscovery19a727e2-d775-407f-ab10-7d5f19577e08

Files

Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
Farrajota2019_Article_HumanActionRecognitionInVideos.pdf
Size:
2.65 MB
Format:
Adobe Portable Document Format
Download

Collections

FCT2-Artigos (em revistas ou actas indexadas)