HFGCN groups skeleton joints by body part and core distance, then uses hypergraph attention and convolution to reach top-1 accuracy of 93.1% on NTU RGB+D X-Sub.
Hypergraph neural network for skeleton-based action recognition
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
HFGCN:Hypergraph Fusion Graph Convolutional Networks for Skeleton-Based Action Recognition
HFGCN groups skeleton joints by body part and core distance, then uses hypergraph attention and convolution to reach top-1 accuracy of 93.1% on NTU RGB+D X-Sub.