Action Recognition In Videos On Jester 1
Métriques
Val
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Val |
|---|---|
| denseimage-network-video-spatial-temporal | 95.31 |
| stm-spatiotemporal-and-motion-encoding-for | 96.7 |
| resource-efficient-3d-convolutional-neural | 86.91 |
| temporal-relational-reasoning-in-videos | 95.31 |
| gating-revisited-deep-multi-layer-rnns-that-1 | 92.7 |
| learning-video-representations-from | 96.7 |
| motion-feature-network-fixed-motion-filter | 96.68 |
| resource-efficient-3d-convolutional-neural | 90.77 |
| resource-efficient-3d-convolutional-neural | 86.43 |