MVD (ViT-B)

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

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

Robots2 results

Activity RecognitiononHMDB51
Top-1 Accuracy· 2022-12-08
79.7
SOTA
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning arXiv:2212.04500
Activity RecognitiononUCF101
3-fold Accuracy· 2022-12-08
97.5
best: 99.7 (FTP-UniFormerV2-L/14)
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning arXiv:2212.04500

Time Series2 results

Action RecognitiononHMDB51
Top-1 Accuracy· 2022-12-08
79.7
SOTA
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning arXiv:2212.04500
Action RecognitiononUCF101
3-fold Accuracy· 2022-12-08
97.5
best: 99.7 (FTP-UniFormerV2-L/14)
Masked Video Distillation: Rethinking Masked Feature Modeling for Self-supervised Video Representation Learning arXiv:2212.04500