S3T-Former: A Purely Spike-Driven State-Space Topology Transformer for Skeleton Action Recognition
Open paper
Benchmark
Model
Rank
Results
skeleton-based-action-recognition-on-ntu-rgbd-60
S3T-Former (D=384, Ensemble)
–
Accuracy (CS): 87.35
Accuracy (CV): 94.05
Rank counts only results with a code link.