MSA-GCN: Exploiting Multi-Scale Temporal Dynamics With Adaptive Graph Convolution for Skeleton-Based Action Recognition

Graph convolutional networks (GCNs) have been widely used and have achieved remarkable results in skeleton-based action recognition. We note that existing GCN-based approaches rely on local context information of the skeleton joints to construct adaptive graphs for feature aggregation, limiting thei...

Olles dieđut

Bibliográfalaš dieđut

Váldodahkkit:	Kowovi Comivi Alowonou, Ji-Hyeong Han
Materiálatiipa:	Artigo
Giella:	Inglês
Almmustuhtton:	IEEE 2024-01-01
Ráidu:	IEEE Access
Fáttát:	Skeleton-based action recognition GCN dynamic graph topology multi-scale temporal processing
Liŋkkat:	https://ieeexplore.ieee.org/document/10807218/
Fáddágilkorat:	Lasit fáddágilkoriid Eai fáddágilkorat, Lasit vuosttaš fáddágilkora!