Visual Question Answering On Gqa

Accuracy

Résultats

Résultats de performance de divers modèles sur ce benchmark

		Paper Title
PEVL+	77	PEVL: Position-enhanced Pre-training and Prompt Tuning for Vision-language Models
RelViT	65.54	RelViT: Concept-guided Vision Transformer for Visual Relational Reasoning

0 of 2 row(s) selected.