Benchmarks
Motion Understandinghigher is better
Something-Something v2
Action recognition over ~220k short clips of everyday object interactions; rewards genuine temporal/motion understanding over appearance. Reported as top-1 accuracy from an attentive probe on frozen features.
Benchmark source- Domain
- Motion Understanding
- Metric
- %
- Orientation
- Higher is better
- Results
- 1
Ranking
| # | Model | Score | Source | Status |
|---|---|---|---|---|
| 1 | V-JEPA 2 Meta AI | 77.3% | Meta — V-JEPA 2 (arXiv:2506.09985)paper | unverified |