Comparative evaluation of action recognition methods via Riemannian manifolds, Fisher vectors and GMMs: ideal and challenging conditions

Carvajal, Johanna, Wiliem, Arnold, McCool, Chris, Lovell, Brian and Sanderson, Conrad (2016). Comparative evaluation of action recognition methods via Riemannian manifolds, Fisher vectors and GMMs: ideal and challenging conditions. In Huiping Cao, Jinyan Li and Ruili Wang (Ed.), Trends and applications in knowledge discovery and data mining (pp. 88-100) Switzerland: Springer. doi:10.1007/978-3-319-42996-0_8

Attached Files (Some files may be inaccessible until you login with your UQ eSpace credentials)
Name Description MIMEType Size Downloads
carvajal_action_recognition_evaluation_2016.pdf carvajal_action_recognition_evaluation_2016.pdf application/pdf 1.87MB 0

Author Carvajal, Johanna
Wiliem, Arnold
McCool, Chris
Lovell, Brian
Sanderson, Conrad
Title of chapter Comparative evaluation of action recognition methods via Riemannian manifolds, Fisher vectors and GMMs: ideal and challenging conditions
Title of book Trends and applications in knowledge discovery and data mining
Place of Publication Switzerland
Publisher Springer
Publication Year 2016
Sub-type Research book chapter (original research)
DOI 10.1007/978-3-319-42996-0_8
Open Access Status Not Open Access
Year available 2016
Series Lecture notes in computer science, Lecture notes in artificial intelligence
ISBN 9783319429960
9783319429953
ISSN 1611-3349
0302-9743
Editor Huiping Cao
Jinyan Li
Ruili Wang
Volume number 9794
Chapter number 8
Start page 88
End page 100
Total pages 13
Total chapters 23
Collection year 2017
Language eng
Abstract/Summary We present a comparative evaluation of various techniques for action recognition while keeping as many variables as possible controlled. We employ two categories of Riemannian manifolds: symmetric positive definite matrices and linear subspaces. For both categories we use their corresponding nearest neighbour classifiers, kernels, and recent kernelised sparse representations. We compare against traditional action recognition techniques based on Gaussian mixture models and Fisher vectors (FVs). We evaluate these action recognition techniques under ideal conditions, as well as their sensitivity in more challenging conditions (variations in scale and translation). Despite recent advancements for handling manifolds, manifold based techniques obtain the lowest performance and their kernel representations are more unstable in the presence of challenging conditions. The FV approach obtains the highest accuracy under ideal conditions. Moreover, FV best deals with moderate scale and translation changes.
Keyword Riemannian manifolds
Fisher vectors (FVs)
Gaussian mixture models (GMMs)
Action recognition techniques
Action recognition
Q-Index Code B1
Q-Index Status Provisional Code
Institutional Status UQ
Additional Notes http://dx.doi.org/10.1007/978-3-319-42996-0_8 http://link.springer.com/chapter/10.1007/978-3-319-42996-0_8

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 26 Jul 2016, 01:17:40 EST by Conrad Sanderson on behalf of School of Information Technol and Elec Engineering