Publication: 3D-Hog Embedding Frameworks for Single and Multi-Viewpoints Action Recognition Based on Human Silhouettes
dc.affiliation.dpto | UC3M. Departamento de Informática | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Inteligencia Artificial Aplicada (GIAA) | es |
dc.contributor.author | Angelini, Federico | |
dc.contributor.author | Fu, Zeyu | |
dc.contributor.author | Velastin Carroza, Sergio Alejandro | |
dc.contributor.author | Chambers, Jonathon A. | |
dc.contributor.author | Naqvi, Syed Mohsen | |
dc.date.accessioned | 2019-10-01T10:26:58Z | |
dc.date.available | 2019-10-01T10:26:58Z | |
dc.date.issued | 2018-09-13 | |
dc.description | This paper has been presented at : 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | en |
dc.description.abstract | Given 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.extent | 5 | |
dc.identifier.bibliographicCitation | Angelini, 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.doi | https://doi.org/10.1109/ICASSP.2018.8461472 | |
dc.identifier.isbn | 978-1-5386-4658-8 | |
dc.identifier.publicationtitle | 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | en |
dc.identifier.uri | https://hdl.handle.net/10016/28936 | |
dc.identifier.uxxi | CC/0000029987 | |
dc.language.iso | eng | en |
dc.publisher | IEEE | en |
dc.relation.eventdate | 15-20 September 2018 | en |
dc.relation.eventplace | Calgary, AB, Canada | en |
dc.relation.eventtitle | 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP) | en |
dc.rights | © 2018 IEEE | en |
dc.rights.accessRights | open access | en |
dc.subject.eciencia | Informática | es |
dc.subject.other | Single-viewpoint | en |
dc.subject.other | Multi-viewpoints | en |
dc.subject.other | Human action recognition | en |
dc.subject.other | 3d histogram of oriented gradient | en |
dc.subject.other | Silhouettes | en |
dc.title | 3D-Hog Embedding Frameworks for Single and Multi-Viewpoints Action Recognition Based on Human Silhouettes | en |
dc.type | conference paper | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1