Dense Captioning On Visual Genome

mAP

평가 결과

이 벤치마크에서 각 모델의 성능 결과

		Paper Title
ControlCap	18.2	ControlCap: Controllable Region-level Captioning
GRiT (ViT-B)	15.5	GRiT: A Generative Region-to-text Transformer for Object Understanding
CAG-Net	10.5	Context and Attribute Grounded Dense Captioning
FCLN	5.4	DenseCap: Fully Convolutional Localization Networks for Dense Captioning

0 of 4 row(s) selected.