Making the Invisible Visible: Action Recognition Through Walls and Occlusions
Open paper
Benchmark
Model
Rank
Results
skeleton-based-action-recognition-on-ntu-rgbd-60
RF-Action
–
Accuracy (CS): 86.8
Accuracy (CV): 91.6
skeleton-based-action-recognition-on-pku-mmd
RF-Action
–
mAP@0.50 (CV): 94.4
mAP@0.50 (CS): 92.9
Rank counts only results with a code link.