VA-AR: Learning Velocity-Aware Action Representations with Mixture of Window Attention
Open paper
Benchmark
Model
Rank
Results
video-classification-on-finegym-gym99
VA-AR
#4
Top-1 Accuracy: 92.8
skeleton-based-action-recognition-on-ntu-rgbd-60
VA-AR
#26
Accuracy (CS): 93.1
Rank counts only results with a code link.