Paper Info
Title
Video-Based Human Action Recognition Using Kernel Relevance Analysis
Abstract
This paper presents a video-based Human Action Recognition using kernel relevance analysis. Our approach, termed HARK, comprises the conventional pipeline employed in action recognition, with a two-fold post-processing stage: (i) A descriptor relevance ranking based on the centered kernel alignment (CKA) algorithm to match trajectory-aligned descriptors with the output labels (action categories), and (ii) a feature embedding based on the same algorithm to project the video samples into the CKA space, where the class separability is preserved, and the number of dimensions is reduced. For concrete testing, the UCF50 human action dataset is employed to assess the HARK under a leave-one-group-out cross-validation scheme. Attained results show that the proposed approach correctly classifies the 90.97% of human actions samples using an average input data dimension of 105 in the classification stage, which outperforms state-of-the-art results concerning the trade-off between accuracy and dimensionality of the final video representation. Also, the relevance analysis allows to increase the video data interpretability, by ranking trajectory-aligned descriptors according to their importance to support action recognition.
Year
DOI
Venue
2018
10.1007/978-3-030-03801-4_11
ADVANCES IN VISUAL COMPUTING, ISVC 2018
Keywords
Field
DocType
Human action recognition, Relevance analysis, Feature embedding, Kernel methods
Kernel (linear algebra),Relevance analysis,Interpretability,Embedding,Pattern recognition,Ranking,Computer science,Action recognition,Curse of dimensionality,Artificial intelligence,Kernel method
Conference
Volume
ISSN
Citations 
11241
0302-9743
0
PageRank 
References 
Authors
0.34
10
3
Name
Order
Citations
PageRank
Jorge Fernández-Ramírez100.34
Andrés Marino Álvarez-Meza29316.89
Álvaro Orozco-Gutiérrez352.46