Video Action Classification on Jester
97.8Top-1 AccV-JEPA 2 ViT-g384
Evaluation Results
| Method | Links | |
|---|---|---|
| V-JEPA 2 ViT-g384Parameters=1B, Input format=32x4x3 frames2025.06 | 97.8 | |
| V-JEPA ViT-HParameters=600M, Evaluation Protocol=Attentive probe2025.06 | 97.7 | |
| V-JEPA 2 ViT-HParameters=600M, Input format=32x4x3 frames2025.06 | 97.7 | |
| V-JEPA 2 ViT-gParameters=1B, Input format=32x4x3 frames2025.06 | 97.7 | |
| V-JEPA 2 ViT-LParameters=300M, Input format=32x4x3 frames2025.06 | 97.6 | |
| InternVideo2_s2-1BParameters=1B, Evaluation Protocol=Attentive probe2025.06 | 97 | |
| DINOv2Parameters=1.1B, Evaluation Protocol=Attentive probe2025.06 | 93.4 | |
| SigLIP2Parameters=1.2B, Evaluation Protocol=Attentive probe2025.06 | 91 | |
| PEcoreGParameters=1.9B, Evaluation Protocol=Attentive probe2025.06 | 90 |