Publication:
DA-VLAD: Discriminative action vector of locally aggregated descriptors for action recognition

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Inteligencia Artificial Aplicada (GIAA)es
dc.contributor.authorMurtaza, Fiza
dc.contributor.authorYousaf, Muhammad Haroon
dc.contributor.authorVelastin Carroza, Sergio Alejandro
dc.contributor.funderEuropean Commissionen
dc.contributor.funderMinisterio de Economía y Competitividad (España)es
dc.date.accessioned2019-10-01T11:14:40Z
dc.date.available2019-10-01T11:14:40Z
dc.date.issued2018-09-06
dc.descriptionThis paper has been presented at : 25th IEEE International Conference on Image Processing (ICIP 2018)en
dc.description.abstractIn this paper, we propose a novel encoding method for the representation of human action videos, that we call Discriminative Action Vector of Locally Aggregated Descriptors (DA-VLAD). DA-VLAD is motivated by the fact that there are many unnecessary and overlapping frames that cause non-discriminative codewords during the training process. DA-VLAD deals with this issue by extracting class-specific clusters and learning the discriminative power of these codewords in the form of informative weights. We use these discriminative action weights with standard VLAD encoding as a contribution of each codeword. DA-VLAD reduces the inter-class similarity efficiently by diminishing the effect of common codewords among multiple action classes during the encoding process. We present the effectiveness of DA-VLAD on two challenging action recognition datasets: UCF101 and HMDB51, improving the state-of-the-art with accuracies of 95.1% and 80.1% respectively.en
dc.description.sponsorshipWe gratefully acknowledge the support of NVIDIA Corporation with the donation of the Titan X Pascal GPU used for this research. We also acknowledge the support from the Directorate of Advance Studies, Research and Technological development (ASR) & TD, University of Engineering and Technology Taxila, Pakistan. Sergio A Velastin acknowledges funding by 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 Economia y Competitividad (COFUND2013-51509) and Banco Santander.en
dc.format.extent5
dc.identifier.bibliographicCitationMurtaza, F., Yousaf, M.H. y Velastin, S.A. (2018). DA-VLAD: Discriminative Action Vector Of Locally Aggregated Descriptors for Action Recognition. In 2018 25th IEEE International Conference on Image Processing (ICIP).en
dc.identifier.doihttps://doi.org/10.1109/ICIP.2018.8451255
dc.identifier.isbn978-1-4799-7061-2
dc.identifier.publicationtitle2018 25th IEEE International Conference on Image Processing (ICIP)en
dc.identifier.urihttps://hdl.handle.net/10016/28937
dc.identifier.uxxiCC/0000029127
dc.language.isoengen
dc.publisherIEEEen
dc.relation.eventdate7-10 October 2018en
dc.relation.eventplaceAthens, Greeceen
dc.relation.eventtitle2018 IEEE International Conference on Image Processing (ICIP)en
dc.relation.projectIDinfo:eu-repo/grantAgreement/EC/PCOFUND-GA-2012-600371en
dc.relation.projectIDGobierno de España. COFUND2013-51509es
dc.rights© 2018 IEEE.en
dc.rights.accessRightsopen accessen
dc.subject.ecienciaInformáticaes
dc.subject.otherHuman action recognitionen
dc.subject.otherVLADen
dc.subject.otherFeature encodingen
dc.subject.otherCodewordsen
dc.subject.otherImproved Dense Trajectories (Idt)en
dc.titleDA-VLAD: Discriminative action vector of locally aggregated descriptors for action recognitionen
dc.typeconference paper*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
da_vlad_ICIP_2018_ps.pdf
Size:
1.53 MB
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