Accueil Actualités Articles de recherche récents Tutoriels Ensembles de données Wiki SOTA Modèles LLM Classement GPU Événements

Français

Highlight Detection On Youtube Highlights

Métriques

mAP

Résultats

Résultats de performance de divers modèles sur ce benchmark

Nom du modèle	mAP	Paper Title	Repository
SG-DETR	76.7	Saliency-Guided DETR for Moment Retrieval and Highlight Detection
UMT	74.9	UMT: Unified Multi-modal Transformers for Joint Video Moment Retrieval and Highlight Detection
FlashVTG	75.4	FlashVTG: Feature Layering and Adaptive Score Handling Network for Video Temporal Grounding
CG-DETR	75.9	Correlation-Guided Query-Dependency Calibration for Video Temporal Grounding
UVCOM	77.4	Bridging the Gap: A Unified Video Comprehension Framework for Moment Retrieval and Highlight Detection
SG-DETR (w/ PT)	78.0	Saliency-Guided DETR for Moment Retrieval and Highlight Detection
LLMEPET	75.3	Prior Knowledge Integration via LLM Encoding and Pseudo Event Regulation for Video Moment Retrieval

0 of 7 row(s) selected.