Multi-modal and multi-part with skeletons and texts for action recognition
Open paper
Benchmark
Model
Rank
Results
skeleton-based-action-recognition-on-ntu-rgbd-120
MMP-ST
–
Accuracy (Cross-Subject): 90.2
Accuracy (Cross-Setup): 91.2
skeleton-based-action-recognition-on-ntu-rgbd-60
MMP-ST
–
Accuracy (CS): 93.1
Accuracy (CV): 96.7
Rank counts only results with a code link.