RT Conference Proceedings
T1 3D-Hog Embedding Frameworks for Single and Multi-Viewpoints Action Recognition Based on Human Silhouettes
A1 Angelini, Federico
A1 Fu, Zeyu
A1 Velastin Carroza, Sergio Alejandro
A1 Chambers, Jonathon A.
A1 Naqvi, Syed Mohsen
AB 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.
PB IEEE
SN 978-1-5386-4658-8
YR 2018
FD 2018-09-13
LK https://hdl.handle.net/10016/28936
UL https://hdl.handle.net/10016/28936
LA eng
NO This paper has been presented at : 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
DS e-Archivo
RD 20 may. 2024