Body Pose Evolution Map

Reported on 4 benchmarks across 2 tasks

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots2 results

Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)
64.6
best: 96.7 (DSCNet (RGB + Pose))
Activity RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)
66.9
best: 95.6 (DSCNet (RGB + Pose))

Time Series2 results

Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Setup)
64.6
best: 96.7 (DSCNet (RGB + Pose))
Action RecognitiononNTU RGB+D 120
Accuracy (Cross-Subject)
66.9
best: 95.6 (DSCNet (RGB + Pose))