Reference : Pose Encoding for Robust Skeleton-Based Action Recognition |
Scientific congresses, symposiums and conference proceedings : Paper published in a book | |||
Engineering, computing & technology : Computer science | |||
Security, Reliability and Trust | |||
http://hdl.handle.net/10993/35566 | |||
Pose Encoding for Robust Skeleton-Based Action Recognition | |
English | |
Demisse, Girum ![]() | |
Papadopoulos, Konstantinos ![]() | |
Aouada, Djamila ![]() | |
Ottersten, Björn ![]() | |
18-Jun-2018 | |
CVPRW: Visual Understanding of Humans in Crowd Scene, Salt Lake City, Utah, June 18-22, 2018 | |
Yes | |
CVPRW: Visual Understanding of Humans in Crowd Scene | |
from 18-06-2018 to 22-06-2018 | |
[en] Some of the main challenges in skeleton-based action recognition systems are redundant and noisy pose transformations. Earlier works in skeleton-based action recognition explored different approaches for filtering linear noise transformations, but neglect to address potential nonlinear
transformations. In this paper, we present an unsupervised learning approach for estimating nonlinear noise transformations in pose estimates. Our approach starts by decoupling linear and nonlinear noise transformations. While the linear transformations are modelled explicitly the nonlinear transformations are learned from data. Subsequently, we use an autoencoder with L2-norm reconstruction error and show that it indeed does capture nonlinear noise transformations, and recover a denoised pose estimate which in turn improves performance significantly. We validate our approach on a publicly available dataset, NW-UCLA. | |
Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM | |
http://hdl.handle.net/10993/35566 | |
FnR ; FNR10415355 > Björn Ottersten > 3D-ACT > 3D Action Recognition Using Refinement and Invariance Strategies for Reliable Surveillance > 01/06/2016 > 31/05/2019 > 2015 |
File(s) associated to this reference | ||||||||||||||
Fulltext file(s):
| ||||||||||||||
All documents in ORBilu are protected by a user license.