Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.11861/10467
Title: View-adaptive graph neural network for action recognition
Authors: Shahid, Ali Raza 
Dr. NAWAZ Mehmood 
Fan, Xinqi 
Yan, Hong 
Issue Date: 2022
Source: IEEE Transactions on Cognitive and Developmental Systems, 2022, vol. 15(2), pp. 969-978.
Journal: IEEE Transactions on Cognitive and Developmental Systems 
Abstract: Skeleton-based recognition of human actions has received attention in recent years because of the popularity of 3-D acquisition sensors. Existing studies use 3-D skeleton data from video clips collected from several views. The body view shifts from the camera perspective when humans perform certain actions, resulting in unstable and noisy skeletal data. In this article, we developed a view-adaptive (VA) mechanism that identifies the viewpoints across the sequence and transforms the skeleton view through a data-driven learning process to counteract the influence of variations. Most existing methods use fixed human-defined prior criterion to reposition skeletons. We utilized an unsupervised reposition approach and jointly designed a VA neural network based on the graph neural network (GNN). Our VA-GNN model can transform the skeletons of distinct views into a considerably more consistent virtual perspective over preprocessing approach. The VA module learns the best observed view because it determines the most suitable view and transforms the skeletons from the action sequence for end-to-end recognition along with suited graph topology with adaptive GNN. Thus, our strategy reduces the influence of view variance, allowing networks to focus on learning action-specific properties and resulting in improved performance. The accuracy achieved by the experiments on the four benchmark data sets.
Type: Peer Reviewed Journal Article
URI: http://hdl.handle.net/20.500.11861/10467
ISSN: 2379-8920
2379-8939
DOI: 10.1109/TCDS.2022.3204905
Appears in Collections:Applied Data Science - Publication

Show full item record

SCOPUSTM   
Citations

7
checked on Dec 15, 2024

Page view(s)

21
Last Week
0
Last month
checked on Dec 20, 2024

Google ScholarTM

Impact Indices

Altmetric

PlumX

Metrics


Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.