Video Classification on EgoPet
56AccuracyVIOLA
Evaluation results
| Method | Links | |
|---|---|---|
| VIOLABackbone=Qwen3-VL2026.01 | 56 | |
| VIOLABackbone=Qwen2-VL2026.01 | 52.9 | |
| VIOLABackbone=VideoLLaMA32026.01 | 50.7 | |
| VIOLABackbone=LLaVA-Video2026.01 | 45.3 | |
| VoteKBackbone=Qwen3-VL2026.01 | 40 | |
| VideoICLBackbone=Qwen3-VL2026.01 | 39.4 | |
| RandomBackbone=Qwen3-VL2026.01 | 39.1 | |
| +Pseudo AnnotationBackbone=LLaVA-Video2026.01 | 36.8 | |
| +Pseudo AnnotationBackbone=Qwen3-VL2026.01 | 33.3 | |
| Zero-shotBackbone=Qwen3-VL2026.01 | 32.6 | |
| +Pseudo AnnotationBackbone=Qwen2-VL2026.01 | 32.4 | |
| VoteKBackbone=LLaVA-Video2026.01 | 25.7 | |
| VoteKBackbone=Qwen2-VL2026.01 | 21.2 | |
| RandomBackbone=Qwen2-VL2026.01 | 19 | |
| RandomBackbone=LLaVA-Video2026.01 | 18.8 | |
| VideoICLBackbone=LLaVA-Video2026.01 | 16.3 | |
| VideoICLBackbone=Qwen2-VL2026.01 | 16.2 | |
| RandomBackbone=VideoLLaMA32026.01 | 16.1 | |
| VideoICLBackbone=VideoLLaMA32026.01 | 15.8 | |
| Zero-shotBackbone=LLaVA-Video2026.01 | 15.2 | |
| Zero-shotBackbone=Qwen2-VL2026.01 | 14.7 | |
| +Pseudo AnnotationBackbone=VideoLLaMA32026.01 | 14.1 | |
| VoteKBackbone=VideoLLaMA32026.01 | 12.9 | |
| Zero-shotBackbone=VideoLLaMA32026.01 | 10.7 |