Pose Estimation On Coco Test Dev

Metrics

AP50

AP75

APL

APM

Results

Performance results of various models on this benchmark

Model Name	AP	AP50	AP75	APL	APM	AR	Paper Title	Repository
Flow-based (ResNet-152)	73.7	91.9	81.1	80	70.3	79	Simple Baselines for Human Pose Estimation and Tracking	-
Mask-RCNN	63.1	87.3	68.7	71.4	-	-	Mask R-CNN	-
PPE (ResNeXt-101)	75.7	90.3	76.3	79.5	80.7	-	Deep Multi-Task Networks For Occluded Pedestrian Pose Estimation	-
OmniPose (WASPv2)	76.4	92.6	83.7	82.6	72.6	81.2	OmniPose: A Multi-Scale Framework for Multi-Person Pose Estimation	-
Faster R-CNN (ImageNet+300M)	64.4	85.7	70.7	69.8	61.8	-	Revisiting Unreasonable Effectiveness of Data in Deep Learning Era	-
Lite-HRNet-30	69.7	90.7	77.5	75.0	66.9	75.4	Lite-HRNet: A Lightweight High-Resolution Network	-
MIPNet	75.7	92.4	83.3	81.2	71.4	80.5	Multi-Instance Pose Networks: Rethinking Top-Down Pose Estimation	-
TFPose (ND=6 ResNet-50)	72.2	90.9	80.1	78.8	69.1	-	TFPose: Direct Human Pose Estimation with Transformers	-
PoseFix	74.7	91.2	81.9	81.2	71.1	79.9	PoseFix: Model-agnostic General Human Pose Refinement Network	-
MSPN	76.1	93.4	83.8	81.5	72.3	81.6	Rethinking on Multi-Stage Networks for Human Pose Estimation	-
TransPose-H-A6	75	92.2	82.3	81.1	71.3	-	TransPose: Keypoint Localization via Transformer	-
HRNet-W48+UDP	76.5	92.7	84	73.0	82.4	81.6	The Devil is in the Details: Delving into Unbiased Data Processing for Human Pose Estimation	-
HRNet-W48+DARK	77.4	92.6	84.6	83.7	73.6	82.3	Distribution-Aware Coordinate Representation for Human Pose Estimation	-
CMU-Pose	61.8	84.9	67.5	68.2	57.1	66.5	Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields	-
ViTPose (ViTAE-G, ensemble)	81.1	95.0	88.2	86.0	77.8	85.6	ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation	-
ViTPose (ViTAE-G)	80.9	94.8	88.1	85.9	77.5	85.4	ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation	-
KAPAO-L	70.3	91.2	77.8	76.8	66.3	77.7	Rethinking Keypoint Representations: Modeling Keypoints and Poses as Objects for Multi-Person Human Pose Estimation	-
RMPE++	72.3	89.2	79.1	78.6	68.0	-	RMPE: Regional Multi-person Pose Estimation	-
CPN	72.1	91.4	80.0	77.2	-	78.5	Cascaded Pyramid Network for Multi-Person Pose Estimation	-
yolopose	-	90.3	-	-	-	-	YOLO-Pose: Enhancing YOLO for Multi Person Pose Estimation Using Object Keypoint Similarity Loss	-

0 of 46 row(s) selected.