Fine-grained action recognition on FineGym290
46.54AccuracyRepresentation Learning via Global Temporal Alignment and Cycle-Consistency
Evaluation Results
| Method | Links | |
|---|---|---|
| Representation Learning via Global Temporal Alignment and Cycle-ConsistencyTraining=only bn2021.05 | 46.54 | |
| Representation Learning via Global Temporal Alignment and Cycle-ConsistencyTraining=scratch2021.05 | 43.49 | |
| TCCTraining=only bn2021.05 | 43.4 | |
| SaLTraining=only bn2021.05 | 41.58 | |
| TCCTraining=scratch2021.05 | 40.57 | |
| TCNTraining=only bn2021.05 | 39.93 | |
| SaLTraining=scratch2021.05 | 37.98 | |
| TCNTraining=scratch2021.05 | 37.4 | |
| SpeedNetTraining=only bn2021.05 | 35.92 | |
| D3TW*Training=only bn2021.05 | 34.04 | |
| D3TW*Training=scratch2021.05 | 32.15 | |
| SpeedNetTraining=scratch2021.05 | 29.87 |