TSE-GCN uses symmetry-aware graph reactivation and per-frame deformable temporal convolution to reach 90.0 and 91.1 percent on NTU RGB+D 120 with 4.4 million parameters.
Multi-scale spatial temporal graph convolutional net- work 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
2024 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Topological Symmetry Enhanced Graph Convolution for Skeleton-Based Action Recognition
TSE-GCN uses symmetry-aware graph reactivation and per-frame deformable temporal convolution to reach 90.0 and 91.1 percent on NTU RGB+D 120 with 4.4 million parameters.