Video Clip Ordering (R3D)

Reported on 4 benchmarks across 2 tasks

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
64.9
best: 99.7 (FTP-UniFormerV2-L/14)
Activity RecognitiononHMDB51
Top-1 Accuracy
29.5
best: 79.7 (MVD (ViT-B))

Time Series2 results

Action RecognitiononUCF101
3-fold Accuracy
64.9
best: 99.7 (FTP-UniFormerV2-L/14)
Action RecognitiononHMDB51
Top-1 Accuracy
29.5
best: 79.7 (MVD (ViT-B))