R3D-18

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 RecognitiononUCF-101
Accuracy· 2022-07-05
81.95
SOTA
Federated Self-supervised Learning for Video Understanding arXiv:2207.01975
Activity RecognitiononUCF101
Accuracy· 2022-07-05
73.16
best: 87.8 (Structured Keypoint Pooling)
SOTA
Federated Self-supervised Learning for Video Understanding arXiv:2207.01975

Time Series2 results

Action RecognitiononUCF-101
Accuracy· 2022-07-05
81.95
SOTA
Federated Self-supervised Learning for Video Understanding arXiv:2207.01975
Action RecognitiononUCF101
Accuracy· 2022-07-05
73.16
best: 87.8 (Structured Keypoint Pooling)
SOTA
Federated Self-supervised Learning for Video Understanding arXiv:2207.01975