Self Supervised Action Recognition On 1
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 |
|---|---|---|---|
| CVRL (R3D-101) | 67.6 | Spatiotemporal Contrastive Video Representation Learning | |
| XKD (ViT-B/112/16) | 77.6 | XKD: Cross-modal Knowledge Distillation with Domain Alignment for Video Representation Learning | |
| CVRL (R3D-152 2x; K600 pretrain) | 71.6 | Spatiotemporal Contrastive Video Representation Learning | |
| CVRL (R3D-50) | 66.1 | Spatiotemporal Contrastive Video Representation Learning |
0 of 4 row(s) selected.