Please use this identifier to cite or link to this item: http://hdl.handle.net/20.500.11861/10467
DC FieldValueLanguage
dc.contributor.authorShahid, Ali Razaen_US
dc.contributor.authorDr. NAWAZ Mehmooden_US
dc.contributor.authorFan, Xinqien_US
dc.contributor.authorYan, Hongen_US
dc.date.accessioned2024-09-07T06:46:26Z-
dc.date.available2024-09-07T06:46:26Z-
dc.date.issued2022-
dc.identifier.citationIEEE Transactions on Cognitive and Developmental Systems, 2022, vol. 15(2), pp. 969-978.en_US
dc.identifier.issn2379-8920-
dc.identifier.issn2379-8939-
dc.identifier.urihttp://hdl.handle.net/20.500.11861/10467-
dc.description.abstractSkeleton-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.en_US
dc.language.isoenen_US
dc.relation.ispartofIEEE Transactions on Cognitive and Developmental Systemsen_US
dc.titleView-adaptive graph neural network for action recognitionen_US
dc.typePeer Reviewed Journal Articleen_US
dc.identifier.doi10.1109/TCDS.2022.3204905-
item.fulltextNo Fulltext-
crisitem.author.deptDepartment of Applied Data Science-
Appears in Collections:Applied Data Science - Publication
Show simple item record

SCOPUSTM   
Citations

7
checked on Nov 17, 2024

Page view(s)

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

Google ScholarTM

Impact Indices

Altmetric

PlumX

Metrics


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