Zero Shot Video Question Answer On Video Mme 1
Métriques
Accuracy (%)
Résultats
Résultats de performance de divers modèles sur ce benchmark
Tableau comparatif
| Nom du modèle | Accuracy (%) |
|---|---|
| gpt-4o-visual-perception-performance-of | 68.9 |
| videollama-2-advancing-spatial-temporal | 63.1 |
| bimba-selective-scan-compression-for-long | 64.67 |
| video-rag-visually-aligned-retrieval | 77.4 |
| vila-on-pre-training-for-visual-language | 64.1 |
| gemini-1-5-unlocking-multimodal-understanding | 81.3 |
| longvu-spatiotemporal-adaptive-compression | 60.6 |
| 2408-01800 | 63.7 |
| gemini-1-5-unlocking-multimodal-understanding | 75.0 |
| gpt-4o-visual-perception-performance-of | 77.2 |