SeViLA (4 frames)
Reported on 1 benchmark across 1 task · 1 paper · 1 SOTA
Note: results are matched by exact model name. Different papers may use the same name for different model variants.
Reasoning1 result
- 1:1 Accuracy· 2023-05-11SOTA73.8best: 74.4 (ViLA (3B, 4 frames))