3s-AimCLR

Reported on 4 benchmarks across 2 tasks · 1 paper · 4 SOTA

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
xset (%)· 2021-12-07
68.8
best: 71.7 (CMCS)
SOTA
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition arXiv:2112.03590
Activity RecognitiononNTU RGB+D 120
xsub (%)· 2021-12-07
68.2
best: 68.5 (CMCS)
SOTA
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition arXiv:2112.03590

Time Series2 results

Action RecognitiononNTU RGB+D 120
xset (%)· 2021-12-07
68.8
best: 71.7 (CMCS)
SOTA
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition arXiv:2112.03590
Action RecognitiononNTU RGB+D 120
xsub (%)· 2021-12-07
68.2
best: 68.5 (CMCS)
SOTA
Contrastive Learning from Extremely Augmented Skeleton Sequences for Self-supervised Action Recognition arXiv:2112.03590