Reference : Pose Encoding for Robust Skeleton-Based Action Recognition

	Document type :	Scientific congresses, symposiums and conference proceedings : Paper published in a book
	Discipline(s) :	Engineering, computing & technology : Computer science
	Focus Areas :	Security, Reliability and Trust
	To cite this reference:	http://hdl.handle.net/10993/35566

Title :	Pose Encoding for Robust Skeleton-Based Action Recognition
Language :	English
Author, co-author :	Demisse, Girum [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Papadopoulos, Konstantinos [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Aouada, Djamila [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
	Ottersten, Björn [University of Luxembourg > Interdisciplinary Centre for Security, Reliability and Trust (SNT) > >]
Publication date :	18-Jun-2018
Main document title :	CVPRW: Visual Understanding of Humans in Crowd Scene, Salt Lake City, Utah, June 18-22, 2018
Peer reviewed :	Yes
Event name :	CVPRW: Visual Understanding of Humans in Crowd Scene
Event date :	from 18-06-2018 to 22-06-2018
Abstract :	[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.
Research centres :	Interdisciplinary Centre for Security, Reliability and Trust (SnT) > SIGCOM
Permalink :	http://hdl.handle.net/10993/35566
FnR project :	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): File Commentary Version Size Access Open access paper.pdf Author preprint 600.47 kB View/Open

All documents in ORBi^lu are protected by a user license.

 

University of Luxembourg Library |  Feedback |  Legal notices Site Map