SVT

Reported on 7 benchmarks across 3 tasks · 1 paper

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

Robots3 results

Activity RecognitiononHMDB-51
Average accuracy of 3 splits· 2021-12-02
67.2
best: 88.7 (VideoMAE V2-g)
Self-supervised Video Transformer arXiv:2112.01514
Activity RecognitiononSomething-Something V2
Top-1 Accuracy· 2021-12-02
59.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Self-supervised Video Transformer arXiv:2112.01514
Activity RecognitiononUCF101
3-fold Accuracy· 2021-12-02
93.7
best: 99.7 (FTP-UniFormerV2-L/14)
Self-supervised Video Transformer arXiv:2112.01514

Action RecognitiononHMDB-51
Average accuracy of 3 splits· 2021-12-02
67.2
best: 88.7 (VideoMAE V2-g)
Self-supervised Video Transformer arXiv:2112.01514
Action RecognitiononSomething-Something V2
Top-1 Accuracy· 2021-12-02
59.2
best: 77.3 (MVD (Kinetics400 pretrain, ViT-H, 16 frame))
Self-supervised Video Transformer arXiv:2112.01514
Action RecognitiononUCF101
3-fold Accuracy· 2021-12-02
93.7
best: 99.7 (FTP-UniFormerV2-L/14)
Self-supervised Video Transformer arXiv:2112.01514