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

e-Archivo Repository

Show simple item record

dc.contributor.author Nazir, Saima
dc.contributor.author Qian, Yu
dc.contributor.author Yousaf, Muhammad
dc.contributor.author Velastin Carroza, Sergio Alejandro
dc.contributor.author Izquierdo, Ebroul
dc.contributor.author Vazquez, Eduard
dc.date.accessioned 2019-09-27T08:59:10Z
dc.date.available 2019-09-27T08:59:10Z
dc.date.issued 2019-02
dc.identifier.bibliographicCitation Nazir, 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.
dc.identifier.isbn 978-989-758-354-4
dc.identifier.uri http://hdl.handle.net/10016/28911
dc.description This paper has been presented at the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications.
dc.description.abstract Deep 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.
dc.description.sponsorship Sergio 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.
dc.format.extent 7
dc.language.iso eng
dc.publisher SciTePress
dc.rights © 2019 14th International Conference on Computer Vision Theory and Applications by SCITEPRESS – Science and Technology Publications, Lda. All rights reserved.
dc.rights Atribución-NoComercial-SinDerivadas 3.0 España
dc.rights.uri http://creativecommons.org/licenses/by-nc-nd/3.0/es/
dc.subject.other Deep learning
dc.subject.other Residual network
dc.subject.other Spatio-temporal network
dc.subject.other Temporal residual network
dc.subject.other Human action recognition
dc.title Human Action Recognition using Multi-Kernel Learning for Temporal Residual Network
dc.type bookPart
dc.type conferenceObject
dc.subject.eciencia Informática
dc.identifier.doi https://doi.org/10.5220/0007371104200426
dc.rights.accessRights openAccess
dc.relation.projectID Gobierno de España. COFUND2013-51509
dc.relation.projectID info:eu-repo/grantAgreement/EC/H2020/600371
dc.relation.projectID Gobierno de España. CEI-15-17
dc.type.version publishedVersion
dc.relation.eventdate 25-27 February 2019
dc.relation.eventplace Prague, Czech Republic
dc.relation.eventtitle 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications (VISAPP 2019)
dc.relation.eventtype proceeding
dc.identifier.publicationfirstpage 420
dc.identifier.publicationlastpage 426
dc.identifier.publicationtitle Proceedings of the 14th International Joint Conference on Computer Vision, Imaging and Computer Graphics Theory and Applications
dc.identifier.publicationvolume 5
dc.identifier.uxxi CC/0000029978
dc.contributor.funder European Commission
dc.contributor.funder Ministerio de Economía y Competitividad (España)
dc.contributor.funder Ministerio de Educación, Cultura y Deporte (España)
 Find Full text

Files in this item

*Click on file's image for preview. (Embargoed files's preview is not supported)


The following license files are associated with this item:

This item appears in the following Collection(s)

Show simple item record