GenPrior: Unleashing Text-to-Motion Generative Priors for Zero-Shot Skeleton-based Action Recognition

Open paper
Benchmark Model Rank Results
zero-shot-skeletal-action-recognition-on-ntu-120GenPrior#1Accuracy (10 unseen classes): 90.44Accuracy (24 unseen classes): 81.39
zero-shot-skeletal-action-recognition-on-ntu-60GenPrior#1Accuracy (12 unseen classes): 73.43Accuracy (5 unseen classes): 87.98

Rank counts only results with a code link.