Publication: Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks
dc.affiliation.dpto | UC3M. Departamento de Informática | es |
dc.affiliation.grupoinv | UC3M. Grupo de Investigación: Inteligencia Artificial Aplicada (GIAA) | es |
dc.contributor.author | Hieu Pham, Huy | |
dc.contributor.author | Khoudour, Louahdi | |
dc.contributor.author | Crouzil, Alain | |
dc.contributor.author | Zegers, Pablo | |
dc.contributor.author | Velastin Carroza, Sergio Alejandro | |
dc.date.accessioned | 2019-09-30T10:22:43Z | |
dc.date.available | 2019-09-30T10:22:43Z | |
dc.date.issued | 2018-09-06 | |
dc.description | This paper has been presented at : 25th IEEE International Conference on Image Processing (ICIP) | en |
dc.description.abstract | We propose a novel skeleton-based representation for 3D action recognition in videos using Deep Convolutional Neural Networks (D-CNNs). Two key issues have been addressed: First, how to construct a robust representation that easily captures the spatial-temporal evolutions of motions from skeleton sequences. Second, how to design D-CNNs capable of learning discriminative features from the new representation in a effective manner. To address these tasks, a skeleton-based representation, namely, SPMF (Skeleton Pose-Motion Feature) is proposed. The SPMFs are built from two of the most important properties of a human action: postures and their motions. Therefore, they are able to effectively represent complex actions. For learning and recognition tasks, we design and optimize new D-CNNs based on the idea of Inception Residual networks to predict actions from SPMFs. Our method is evaluated on two challenging datasets including MSR Action3D and NTU-RGB+D. Experimental results indicated that the proposed method surpasses state-of-the-art methods whilst requiring less computation. | en |
dc.format.extent | 5 | |
dc.identifier.bibliographicCitation | Pham, H.H., Khoudour, L., Crouzil, A., Zegers, P. y Velastin, S.A. (2018). Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks. In IEEE International Conference on Image Processing. | en |
dc.identifier.doi | https://doi.org/10.1109/ICIP.2018.8451404 | |
dc.identifier.isbn | 978-1-4799-7061-2 | |
dc.identifier.publicationtitle | IEEE International Conference on Image Processing | en |
dc.identifier.uri | https://hdl.handle.net/10016/28921 | |
dc.identifier.uxxi | CC/0000029977 | |
dc.language.iso | eng | en |
dc.publisher | IEEE | en |
dc.relation.eventdate | 7-10 October 2018 | en |
dc.relation.eventplace | Athens, Greece | en |
dc.relation.eventtitle | 25th IEEE International Conference on Image Processing (ICIP) | en |
dc.rights | © 2018 IEEE. | en |
dc.rights.accessRights | open access | en |
dc.subject.eciencia | Informática | es |
dc.subject.other | Human action recognition | en |
dc.subject.other | SPMF | en |
dc.subject.other | CNNs | en |
dc.title | Skeletal Movement to Color Map: A Novel Representation for 3D Action Recognition with Inception Residual Networks | en |
dc.type | conference paper | * |
dc.type.hasVersion | AM | * |
dspace.entity.type | Publication |
Files
Original bundle
1 - 1 of 1
Loading...
- Name:
- skeletal_ICIP_2018_ps.pdf
- Size:
- 674.13 KB
- Format:
- Adobe Portable Document Format