Angelini, FedericoFu, ZeyuVelastin Carroza, Sergio AlejandroChambers, Jonathon A.Naqvi, Syed Mohsen2019-10-012019-10-012018-09-13Angelini, 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).978-1-5386-4658-8https://hdl.handle.net/10016/28936This paper has been presented at : 2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)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.5eng© 2018 IEEESingle-viewpointMulti-viewpointsHuman action recognition3d histogram of oriented gradientSilhouettesconference paperInformáticahttps://doi.org/10.1109/ICASSP.2018.8461472open access2018 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)CC/0000029987