Publication:
Human Action Recognition using Multi-Kernel Learning for Temporal Residual Network

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Inteligencia Artificial Aplicada (GIAA)es
dc.contributor.authorNazir, Saima
dc.contributor.authorQian, Yu
dc.contributor.authorYousaf, Muhammad Haroon
dc.contributor.authorVelastin Carroza, Sergio Alejandro
dc.contributor.authorIzquierdo, Ebroul
dc.contributor.authorVazquez, Eduard
dc.contributor.funderEuropean Commissionen
dc.contributor.funderMinisterio de Economía y Competitividad (España)es
dc.contributor.funderMinisterio de Educación, Cultura y Deporte (España)es
dc.date.accessioned2019-09-27T08:59:10Z
dc.date.available2019-09-27T08:59:10Z
dc.date.issued2019-02
dc.descriptionThis paper has been presented at the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.en
dc.description.abstractDeep learning has led to a series of breakthrough in the human action recognition field. Given the powerful representational ability of residual networks (ResNet), performance in many computer vision tasks including human action recognition has improved. Motivated by the success of ResNet, we use the residual network and its variations to obtain feature representation. Bearing in mind the importance of appearance and motion information for action representation, our network utilizes both for feature extraction. Appearance and motion features are further fused for action classification using a multi-kernel support vector machine (SVM).We also investigate the fusion of dense trajectories with the proposed network to boost up the network performance. We evaluate our proposed methods on a benchmark dataset (HMDB-51) and results shows the multi-kernel learning shows the better performance than the fusion of classification score from deep network SoftMax layer. Our proposed method also shows good performance as compared to the recent state-of-the-art methods.en
dc.description.sponsorshipSergio A. Velastin has received funding from the Universidad Carlos III de Madrid, the European Unions Seventh Framework Programme for research, technological development and demonstration under grant agreement n◦ 600371, el Ministerio de Economía, Industria y Competitividad (COFUND2013-51509) el Ministerio de Educación, cultura y Deporte (CEI-15-17) and Banco Santander. Authors also acknowledge support from the Higher Education Commission, Pakistan.en
dc.format.extent7
dc.identifier.bibliographicCitationNazir, S., Qian, Y., Yousaf, M., Velastin, S., Izquierdo, E. y Vazquez, E. (2019). Human Action Recognition using Multi-Kernel Learning for Temporal Residual Network. In Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications, 5, pp. 420-426.en
dc.identifier.doihttps://doi.org/10.5220/0007371104200426
dc.identifier.isbn978-989-758-354-4
dc.identifier.publicationfirstpage420
dc.identifier.publicationlastpage426
dc.identifier.publicationtitleProceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applicationsen
dc.identifier.publicationvolume5
dc.identifier.urihttps://hdl.handle.net/10016/28911
dc.identifier.uxxiCC/0000029978
dc.language.isoengen
dc.publisherSciTePressen
dc.relation.eventdate25-27 February 2019en
dc.relation.eventplacePrague, Czech Republicen
dc.relation.eventtitle14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP 2019)en
dc.relation.projectIDGobierno de España. COFUND2013-51509es
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/H2020/600371en
dc.relation.projectIDGobierno de España. CEI-15-17es
dc.rights© 2019 14th International Conference on Computer Vision Theory and Applications by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.en
dc.rightsAtribución-NoComercial-SinDerivadas 3.0 España*
dc.rights.accessRightsopen accessen
dc.rights.urihttp://creativecommons.org/licenses/by-nc-nd/3.0/es/*
dc.subject.ecienciaInformáticaes
dc.subject.otherDeep learningen
dc.subject.otherResidual networken
dc.subject.otherSpatio-temporal networken
dc.subject.otherTemporal residual networken
dc.subject.otherHuman action recognitionen
dc.titleHuman Action Recognition using Multi-Kernel Learning for Temporal Residual Networken
dc.typeconference paper*
dc.type.hasVersionVoR*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
human_JCCV_2019.pdf
Size:
555.26 KB
Format:
Adobe Portable Document Format
Download
Collections
DI - GIAA - Comunicaciones en Congresos y otros eventos
DI - GIAA - Capítulos de Monografías
OpenAIRE: Open Access Infrastructure for Research in Europe