SOTA Pedestrian Detection benchmarks and papers with code

Benchmarks

Dataset Name	SOTA Method	Metric
CityPersons (val)	InterNet	AP (Reasonable)17.9	85	4d ago
CrowdHuman (val)	Hulk	MR^-236.5	61	3d ago
CrowdHuman	InternImage-H	mAP97.2	38	3d ago
Caltech (test)	RPN+BF	MR9.6	36	3d ago
KAIST (test)	AR-CNN	MR (Near)0	22	3d ago
MultiviewX	TrackTacular	MODA96.5	21	3d ago
Wildtrack		MODA94.1	21	3d ago
CityPersons 1.0 (val)		Miss Rate (Reasonable)9.4	21	3d ago
LLVIP (test)	AUNet	mAP@5097.2	20	3d ago
Caltech	NMS-Ped	MR5.92	17	3d ago
CrowdHuman (test)	Faster R-CNN (ours)	MR40.7	16	3d ago
CityPersons highly occluded (HO)	PedesFormer	Miss Rate36.9	16	3d ago
KAIST multispectral pedestrian dataset (All-dataset)		Detection Rate (Near)28.74	14	3d ago
Waymo Open Dataset (val)	RSN	AP L1 3D80.2	12	4d ago
KITTI Hard (val)	MS-CNN	AP64.08	12	4d ago
KITTI Easy (val)	HyperLearner + Segmentation	AP79.43	12	4d ago
KITTI Moderate (val)	HyperLearner + Edge	AP72.51	12	4d ago
KITTI (test)		AP (Easy)73.14	12	4d ago
Caltech Reasonable	PedHunter	Miss Rate2.3	11	3d ago
CityPersons original image size (1024x2048 pixels) (test)	CornerNet	AP (Reasonable)21	11	4d ago
CVC-14 (Night)	MBNet	MR^-213.5	11	3d ago
CVC-14 (Day)	AR-CNN	MR^-224.7	11	3d ago
Caltech standard (test)		Detection Rate (Reasonable)11.52	11	3d ago
City Persons 6 (test)	F2DNet	MR-2 (Reasonable)8.7	10	3d ago
KAIST reasonable subset (test)	MBNet	MR^-2 (IoU=0.5, All)8.13	10	3d ago

Showing 25 of 68 rows