Video Question Answering on EgoSchema Total
60.1ScoreFlashVID
Evaluation Results
| Method | Links | |
|---|---|---|
| FlashVIDBackbone=Qwen2.5VL-7B, Frames / Pruning Configuration=F160 (5×) / 20%2026.05 | 60.1 | |
| EchoPruneBackbone=Qwen2.5VL-7B, Frames / Pruning Configuration=F160 (5×) / 20%2026.05 | 59.9 | |
| MI-PrunerBackbone=Qwen2.5VL-7B, Frames / Pruning Configuration=F160 (5×) / 20%2026.05 | 59.8 | |
| RandomBackbone=Qwen2.5VL-7B, Frames / Pruning Configuration=F160 (5×) / 20%2026.05 | 59 | |
| Qwen2.5VL-7BBackbone=Qwen2.5VL-7B, Frames / Pruning Configuration=F32 (1×) / 100%2026.05 | 58.1 | |
| FlashVIDBackbone=Qwen2.5VL-3B, Frames / Pruning Configuration=F160 (5×) / 20%2026.05 | 56.2 | |
| EchoPruneBackbone=Qwen2.5VL-3B, Frames / Pruning Configuration=F160 (5×) / 20%2026.05 | 55.7 | |
| MI-PrunerBackbone=Qwen2.5VL-3B, Frames / Pruning Configuration=F160 (5×) / 20%2026.05 | 55.6 | |
| RandomBackbone=Qwen2.5VL-3B, Frames / Pruning Configuration=F160 (5×) / 20%2026.05 | 55 | |
| Qwen2.5VL-3BBackbone=Qwen2.5VL-3B, Frames / Pruning Configuration=F32 (1×) / 100%2026.05 | 54.3 |