Self Supervised Action Recognition On Ucf101 1
評価指標
3-fold Accuracy
Pretrain
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
比較表
| モデル名 | 3-fold Accuracy | Pretrain |
|---|---|---|
| spatiotemporal-contrastive-video | 92.2 | K400 |
| self-supervised-video-representation-learning-7 | 82.8 | UCF101 |
| audio-visual-instance-discrimination-with | 91.5 | - |
| self-supervised-co-training-for-video | 87.9 | K400 |
| self-supervised-video-representation-learning-7 | 88.8 | UCF101 |
| spatiotemporal-contrastive-video | 93.4 | K600 |
| self-supervised-video-representation-learning-7 | 90.5 | UCF101 |
| spatiotemporal-contrastive-video | 93.9 | K600 |
| cooperative-learning-of-audio-and-video | 89.0 | - |
| broaden-your-views-for-self-supervised-video | 95.7 | - |
| self-supervised-video-representation-learning-7 | 84.3 | UCF101 |
| self-supervised-multimodal-versatile-networks | 91.5 | - |
| evolving-losses-for-unsupervised-video | 93.8 | - |
| self-supervised-learning-by-cross-modal-audio | 95.5 | - |