Sign in
Back
Unsupervised Human Action Categorization Using a Riemannian Averaged Fixed-Point Learning of Multivariate GGMM
Conference proceeding   Peer reviewed

Unsupervised Human Action Categorization Using a Riemannian Averaged Fixed-Point Learning of Multivariate GGMM

Fatma Najar, Sami Bourouis, Atef Zaguia, Nizar Bouguila and Safya Belghith
IMAGE ANALYSIS AND RECOGNITION (ICIAR 2018), Vol.10882, pp.408-415
Lecture Notes in Computer Science
01/01/2018
DOI: https://doi.org/10.1007/978-3-319-93000-8_46

Abstract

Computer Science Computer Science, Theory & Methods Imaging Science & Photographic Technology Science & Technology Technology
We present a novel learning algorithm for Human action recognition and categorization. Our purpose here is to develop a Riemannian Averaged Fixed-Point estimation algorithm (RA-FP) for learning the multivariate generalized Gaussian mixture model's parameters (MGGMM). Experiments in a large datasets of human action images have shown the merits of our approach.

Metrics

1 Record Views

Details