Object Detection On Visual Genome

MAP

Results

Performance results of various models on this benchmark

		Paper Title
KnowZRel	44	KnowZRel: Common Sense Knowledge-based Zero-Shot Relationship Retrieval for Generalised Scene Graph Generation
YOLOv5x6	32.7	An Enhanced Object Detection Model for Scene Graph Generation
MSDN	7.43	Scene Graph Generation from Objects, Phrases and Region Captions
AP (%)	5.39	DenseCap: Fully Convolutional Localization Networks for Dense Captioning

0 of 4 row(s) selected.