Collision Counting on CLEVRER T3 (val)
77.84AccuracyV-JEPA 2
Evaluation Results
| Method | Links | |
|---|---|---|
| V-JEPA 2Modality=256×256 Video, Size=ViT-L, Pre-training Dataset=Real-World, Training Samples=22M (88×), Video Hours Eq.=≈1.73M (12, 357×), Evaluation Protocol=Linear Probing2026.05 | 77.84 | |
| TIMEModality=32×32 Tracks, Size=ViT-B, Pre-training Dataset=Synthetic, Training Samples=0.25M (1×), Video Hours Eq.=140 (1×), Evaluation Protocol=Linear Probing2026.05 | 61.35 | |
| RVMModality=224×224 Video, Size=ViT-B, Pre-training Dataset=Real-World, Training Samples=5.68M (23×), Video Hours Eq.=≈0.25M (1, 785×), Evaluation Protocol=Linear Probing2026.05 | 59.1 | |
| VideoMAEv2Modality=224×224 Video, Size=ViT-B, Pre-training Dataset=Real-World, Training Samples=5.36M (27×), Video Hours Eq.=≈7,500 (54×), Evaluation Protocol=Linear Probing2026.05 | 36.69 |