E2E-GNet: An End-to-End Skeleton-based Geometric Deep Neural Network for Human Motion Recognition
Open paper
Benchmark
Model
Rank
Results
skeleton-based-action-recognition-on-ntu-rgbd-120
E2E-GNet
#3
Accuracy (Cross-Subject): 95.2
Accuracy (Cross-Setup): 93.3
skeleton-based-action-recognition-on-ntu-rgbd-60
E2E-GNet
#3
Accuracy (CS): 97.1
Accuracy (CV): 98.6
Rank counts only results with a code link.