Log-Euclidean bag of words for human action recognition

Faraki, Masoud, Palhang, Maziar and Sanderson, Conrad (2015) Log-Euclidean bag of words for human action recognition. IET Computer Vision, 9 3: 331-339. doi:10.1049/iet-cvi.2014.0018

Author Faraki, Masoud
Palhang, Maziar
Sanderson, Conrad
Title Log-Euclidean bag of words for human action recognition
Journal name IET Computer Vision   Check publisher's open access policy
ISSN 1751-9632
Publication date 2015-05-18
Sub-type Article (original research)
DOI 10.1049/iet-cvi.2014.0018
Open Access Status Not Open Access
Volume 9
Issue 3
Start page 331
End page 339
Total pages 9
Place of publication Stevenage, Herts, United Kingdom
Publisher The Institution of Engineering and Technology
Language eng
Abstract Representing videos by densely extracted local space-time features has recently become a popular approach for analysing actions. In this study, the authors tackle the problem of categorising human actions by devising bag of words (BoWs) models based on covariance matrices of spatiotemporal features, with the features formed from histograms of optical flow. Since covariance matrices form a special type of Riemannian manifold, the space of symmetric positive definite (SPD) matrices, non-Euclidean geometry should be taken into account while discriminating between covariance matrices. To this end, the authors propose to embed SPD manifolds to Euclidean spaces via a diffeomorphism and extend the BoW approach to its Riemannian version. The proposed BoW approach takes into account the manifold geometry of SPD matrices during the generation of the codebook and histograms. Experiments on challenging human action datasets show that the proposed method obtains notable improvements in discrimination accuracy, in comparison with several state-of-the-art methods.
Q-Index Code C1
Q-Index Status Provisional Code
Institutional Status Non-UQ

Document type: Journal Article
Sub-type: Article (original research)
Collection: School of Information Technology and Electrical Engineering Publications
Version Filter Type
Citation counts: TR Web of Science Citation Count  Cited 1 times in Thomson Reuters Web of Science Article | Citations
Scopus Citation Count Cited 1 times in Scopus Article | Citations
Google Scholar Search Google Scholar
Created: Tue, 21 Jun 2016, 16:00:03 EST by Conrad Sanderson on behalf of School of Information Technol and Elec Engineering