Self Supervised Action Recognition On
評価指標
Top-1 Accuracy
評価結果
このベンチマークにおける各モデルのパフォーマンス結果
モデル名 | Top-1 Accuracy | Paper Title | Repository |
|---|---|---|---|
| MMV | 55.5 | Self-Supervised MultiModal Versatile Networks | |
| BraVe:V-FA (TSM-50x2) | 71.4 | Broaden Your Views for Self-Supervised Video Learning | |
| CVRL (R3D-50) | 70.4 | Spatiotemporal Contrastive Video Representation Learning | |
| CVRL (R3D-101) | 71.6 | Spatiotemporal Contrastive Video Representation Learning | |
| CVRL (R3D-152 2x) | 72.9 | Spatiotemporal Contrastive Video Representation Learning |
0 of 5 row(s) selected.