Logo do repositório
 
Publicação

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

2019-11Artigo científico Acesso restrito
Ver registo simples
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.awardNumberUID/EEA/50009/2013
oaire.awardNumberSFRH/BD/79812/2011
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

Ficheiros

Principais
A mostrar 1 - 1 de 1
Miniatura indisponível
Nome:
Farrajota2019_Article_HumanActionRecognitionInVideos.pdf
Tamanho:
2.65 MB
Formato:
Adobe Portable Document Format
Ver/Abrir

Coleções

FCT2-Artigos (em revistas ou actas indexadas)