Visual Grounding On Refcoco Val

Accuracy (%)

评测结果

各个模型在此基准测试上的表现结果

		Paper Title
Florence-2-large-ft	93.4	Florence-2: Advancing a Unified Representation for a Variety of Vision Tasks
mPLUG-2	90.33	mPLUG-2: A Modularized Multi-modal Foundation Model Across Text, Image and Video
X2-VLM (large)	87.6	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
XFM (base)	86.1	Toward Building General Foundation Models for Language, Vision, and Vision-Language Understanding Tasks
X2-VLM (base)	85.2	X$^2$-VLM: All-In-One Pre-trained Model For Vision-Language Tasks
X-VLM (base)	84.51	Multi-Grained Vision Language Pre-Training: Aligning Texts with Visual Concepts

0 of 6 row(s) selected.