MCN (R2+1D; RGB)

Reported on 4 benchmarks across 2 tasks · 1 paper

Note: results are matched by exact model name. Different papers may use the same name for different model variants.

Robots2 results

Activity RecognitiononUCF101
3-fold Accuracy· 2021-08-19
84.8
best: 99.7 (FTP-UniFormerV2-L/14)
Self-Supervised Video Representation Learning with Meta-Contrastive Network arXiv:2108.08426
Activity RecognitiononHMDB51
Top-1 Accuracy· 2021-08-19
54.5
best: 79.7 (MVD (ViT-B))
Self-Supervised Video Representation Learning with Meta-Contrastive Network arXiv:2108.08426

Time Series2 results

Action RecognitiononUCF101
3-fold Accuracy· 2021-08-19
84.8
best: 99.7 (FTP-UniFormerV2-L/14)
Self-Supervised Video Representation Learning with Meta-Contrastive Network arXiv:2108.08426
Action RecognitiononHMDB51
Top-1 Accuracy· 2021-08-19
54.5
best: 79.7 (MVD (ViT-B))
Self-Supervised Video Representation Learning with Meta-Contrastive Network arXiv:2108.08426