Cross-Model Cross-Stream Learning for Self-Supervised Human Action Recognition
Open paper
Benchmark
Model
Rank
Results
self-supervised-human-action-recognition-on-ntu-rgbd-120
CMCS
#1
xsub (%): 68.5
xset (%): 71.7
Encoder: ST-GCN
Classifier: FC
Rank counts only results with a code link.