Comparison of various combinations of self-supervised tasks on NW-UCLA dataset with 5% of labeled skeleton sequences.
| Method | NW-UCLA |
|---|---|
| Rand-S | 52.5 |
| Prediction | 52.8 |
| Jigsaw | 54.5 |
| Contrastive | 53.2 |
| Prediction & Contrastive | 54.8 |
| Jigsaw & Prediction | 55.3 |
| Contrastive & Jigsaw | 55.9 |
| Prediction & Jigsaw & Contrastive | 56.5 |
| Method | NW-UCLA |
|---|---|
| Rand-S | 52.5 |
| Prediction | 52.8 |
| Jigsaw | 54.5 |
| Contrastive | 53.2 |
| Prediction & Contrastive | 54.8 |
| Jigsaw & Prediction | 55.3 |
| Contrastive & Jigsaw | 55.9 |
| Prediction & Jigsaw & Contrastive |
Sharing content requires targeting cookies to be enabled. Please update your cookie preferences to use this feature.