Multi-Person Pose Estimation on COCO test-dev

60개 결과 · ⬇ CSV · JSON

Rank	Model	AP	APL	APM	AP50	AP75	AR	AR50	Paper	Code	Year
1	SCIO (HRNet-48)	79.2	84.2	74.1	93.5	85.8	81.6	–	Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation		2022
2	HRNet-W48plus	78.7	–	–	–	–	–	–	AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation	open-mmlab/mmpose · HuangJunJie2017/UDP-Pose	2020
3	HRNet-W32	76.2	–	–	–	–	–	–	AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation	open-mmlab/mmpose · HuangJunJie2017/UDP-Pose	2020
4	ResNet50	73.7	–	–	–	–	–	–	AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation	open-mmlab/mmpose · HuangJunJie2017/UDP-Pose	2020
5	HigherHRNet (ScaleNet_P4)	71.6	77.2	67.5	90.3	78.2	76.0	92.3	ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition		2020
6	HigherHRNet (HR-Net-48)	70.5	75.8	66.6	89.3	77.2	–	–	HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose Estimation	PaddlePaddle/PaddleDetection · open-mmlab/mmpose · HRNet/Higher-HRNet-Human-Pose-Estimation · +16	2019
7	SMPR (HR-Net-32)	70.2	77.2	65.9	89.7	77.5	–	–	SMPR: Single-Stage Multi-Person Pose Regression	cmdi-dlut/SMPR	2020
8	PersonLab	68.7	75.5	64.1	89.0	75.4	–	–	PersonLab: Person Pose Estimation and Instance Segmentation with a Bottom-Up, Part-Based, Geometric Embedding Model	google-coral/project-posenet · SAtacker/PosenetTflite · jp-sm/jp-sm.github.io	2018
9	Identity Mapping Hourglass	68.1	70.5	66.8	–	–	72.1	88.2	Simple Pose: Rethinking and Improving a Bottom-up Approach for Multi-Person Pose Estimation	osmr/imgclsmob · hellojialee/Improved-Body-Parts · hellojialee/Multi-Person-Pose-using-Body-Parts · +5	2019
10	SPM	66.9	73.1	62.6	88.5	72.9	–	–	Single-Stage Multi-Person Pose Machines	murdockhou/Single-Stage-Multi-person-Pose-Machines	2019
11	Supervising Self-Attention	66.5	–	–	–	–	–	–	Attend to Who You Are: Supervising Self-Attention for Keypoint Detection and Instance-Aware Association	yangsenius/ssa	2021
12	Hourglass-104	65.6	68.8	63.3	–	–	–	–	Greedy Offset-Guided Keypoint Grouping for Human Pose Estimation	hellojialee/OffsetGuided	2021
13	G-RMI	64.9	70.0	62.3	85.5	71.3	–	–	Towards Accurate Multi-person Pose Estimation in the Wild		2017
14	CMU-Pose	61.8	68.2	57.1	84.9	67.5	–	–	Realtime Multi-Person 2D Pose Estimation using Part Affinity Fields	CMU-Perceptual-Computing-Lab/openpose · ZheC/Realtime_Multi-Person_Pose_Estimation · shihenw/convolutional-pose-machines-release · +58	2016
14	RMPE	61.8	67.6	58.6	83.7	69.8	–	–	RMPE: Regional Multi-person Pose Estimation	MVIG-SJTU/AlphaPose · osmr/imgclsmob · mindspore-ai/models · +11	2016
16	SCIO (HRNet-48)	79.2	84.2	74.1	93.5	85.8	81.6	–	Self-Constrained Inference Optimization on Structural Groups for Human Pose Estimation		2022
17	HRNet-W48plus	78.7	–	–	–	–	–	–	AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation	open-mmlab/mmpose · HuangJunJie2017/UDP-Pose	2020
18	HRNet-W32	76.2	–	–	–	–	–	–	AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation	open-mmlab/mmpose · HuangJunJie2017/UDP-Pose	2020
19	ResNet50	73.7	–	–	–	–	–	–	AID: Pushing the Performance Boundary of Human Pose Estimation with Information Dropping Augmentation	open-mmlab/mmpose · HuangJunJie2017/UDP-Pose	2020
20	HigherHRNet (ScaleNet_P4)	71.6	77.2	67.5	90.3	78.2	76.0	92.3	ScaleNAS: One-Shot Learning of Scale-Aware Representations for Visual Recognition		2020