Publication:
3D-Hog Embedding Frameworks for Single and Multi-Viewpoints Action Recognition Based on Human Silhouettes

Simple item page
dc.affiliation.dptoUC3M. Departamento de Informáticaes
dc.affiliation.grupoinvUC3M. Grupo de Investigación: Inteligencia Artificial Aplicada (GIAA)es
dc.contributor.authorAngelini, Federico
dc.contributor.authorFu, Zeyu
dc.contributor.authorVelastin Carroza, Sergio Alejandro
dc.contributor.authorChambers, Jonathon A.
dc.contributor.authorNaqvi, Syed Mohsen
dc.date.accessioned2019-10-01T10:26:58Z
dc.date.available2019-10-01T10:26:58Z
dc.date.issued2018-09-13
dc.descriptionThis paper has been presented at : 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)en
dc.description.abstractGiven the high demand for automated systems for human action recognition, great efforts have been undertaken in recent decades to progress the field. In this paper, we present frameworks for single and multi-viewpoints action recognition based on Space-Time Volume (STV) of human silhouettes and 3D-Histogram of Oriented Gradient (3D-HOG) embedding. We exploit fast-computational approaches involving Principal Component Analysis (PCA) over the local feature spaces for compactly describing actions as combinations of local gestures and L 2 -Regularized Logistic Regression (L 2 -RLR) for learning the action model from local features. Outperforming results on Weizmann and i3DPost datasets confirm efficacy of the proposed approaches as compared to the baseline method and other works, in terms of accuracy and robustness to appearance changes.en
dc.format.extent5
dc.identifier.bibliographicCitationAngelini, F., Fu, Z., Velastin, S.A, Chambers, J.A. y Naqvi, S.M. (2018). 3D-Hog Embedding Frameworks for Single and Multi-Viewpoints Action Recognition Based on Human Silhouettes. In 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP).en
dc.identifier.doihttps://doi.org/10.1109/ICASSP.2018.8461472
dc.identifier.isbn978-1-5386-4658-8
dc.identifier.publicationtitle2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)en
dc.identifier.urihttps://hdl.handle.net/10016/28936
dc.identifier.uxxiCC/0000029987
dc.language.isoengen
dc.publisherIEEEen
dc.relation.eventdate15-20 September 2018en
dc.relation.eventplaceCalgary, AB, Canadaen
dc.relation.eventtitle2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)en
dc.rights© 2018 IEEEen
dc.rights.accessRightsopen accessen
dc.subject.ecienciaInformáticaes
dc.subject.otherSingle-viewpointen
dc.subject.otherMulti-viewpointsen
dc.subject.otherHuman action recognitionen
dc.subject.other3d histogram of oriented gradienten
dc.subject.otherSilhouettesen
dc.title3D-Hog Embedding Frameworks for Single and Multi-Viewpoints Action Recognition Based on Human Silhouettesen
dc.typeconference paper*
dc.type.hasVersionAM*
dspace.entity.typePublication
Files
Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
3Dhog_ICASSP_2018_ps.pdf
Size:
382.59 KB
Format:
Adobe Portable Document Format
Download
Collections
DI - GIAA - Comunicaciones en Congresos y otros eventos
DI - GIAA - Capítulos de Monografías