MaskCLR: Attention-Guided Contrastive Learning for Robust Action Representation Learning

Open paper
Benchmark Model Rank Results
skeleton-based-action-recognition-on-ntu-rgbd-120MaskCLR–Accuracy (Cross-Subject): 87.4Accuracy (Cross-Setup): 89.5
skeleton-based-action-recognition-on-ntu-rgbd-60MaskCLR–Accuracy (CS): 93.9Accuracy (CV): 97.3

Rank counts only results with a code link.