ML Research Wiki / Benchmarks / 2D Human Pose Estimation / Human-Art

Human-Art

2D Human Pose Estimation Benchmark

Performance Over Time

📊 Showing 10 results | 📏 Metric: AP

Top Performing Models

Rank	Model	Paper	AP	Date	Code
1	UniPose 📚	X-Pose: Detecting Any Keypoints	0.76	2023-10-12	📦 idea-research/x-pose 📦 IDEA-Research/UniPose
2	RTMPose-l	RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose	0.75	2023-03-13	📦 open-mmlab/mmpose
3	ED-Pose (R50)	Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation	0.72	2023-02-03	📦 idea-research/ed-pose 📦 michel-liu/grouppose 📦 michel-liu/grouppose-paddle
4	ViTPose-h	ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation	0.47	2022-04-26	📦 huggingface/transformers 📦 vitae-transformer/vitpose 📦 vitae-transformer/qformer
5	ViTPose-l	ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation	0.46	2022-04-26	📦 huggingface/transformers 📦 vitae-transformer/vitpose 📦 vitae-transformer/qformer
6	HRNet-w48	Deep High-Resolution Representation Learning for Human Pose Estimation	0.42	2019-02-25	📦 open-mmlab/mmdetection 📦 PaddlePaddle/PaddleDetection 📦 open-mmlab/mmpose
7	ViTpose-b	ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation	0.41	2022-04-26	📦 huggingface/transformers 📦 vitae-transformer/vitpose 📦 vitae-transformer/qformer
8	HRNet-w32	Deep High-Resolution Representation Learning for Human Pose Estimation	0.40	2019-02-25	📦 open-mmlab/mmdetection 📦 PaddlePaddle/PaddleDetection 📦 open-mmlab/mmpose
9	ViTPose-s	ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation	0.38	2022-04-26	📦 huggingface/transformers 📦 vitae-transformer/vitpose 📦 vitae-transformer/qformer
10	RTMPose-s	RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose	0.31	2023-03-13	📦 open-mmlab/mmpose

All Papers (10)

X-Pose: Detecting Any Keypoints

2023

UniPose

idea-research/x-pose IDEA-Research/UniPose

RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose

2023

RTMPose-l

open-mmlab/mmpose

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

2023

ED-Pose (R50)

idea-research/ed-pose michel-liu/grouppose michel-liu/grouppose-paddle

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

2022

ViTPose-h

huggingface/transformers vitae-transformer/vitpose

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

2022

ViTPose-l

huggingface/transformers vitae-transformer/vitpose

Deep High-Resolution Representation Learning for Human Pose Estimation

2019

HRNet-w48

open-mmlab/mmdetection PaddlePaddle/PaddleDetection

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

2022

ViTpose-b

huggingface/transformers vitae-transformer/vitpose

Deep High-Resolution Representation Learning for Human Pose Estimation

2019

HRNet-w32

open-mmlab/mmdetection PaddlePaddle/PaddleDetection

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

2022

ViTPose-s

huggingface/transformers vitae-transformer/vitpose

RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose

2023

RTMPose-s

open-mmlab/mmpose

Human-Art

Performance Over Time

Edit Benchmark Results

Edit Result

Top Performing Models

All Papers (10)

X-Pose: Detecting Any Keypoints

RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose

Explicit Box Detection Unifies End-to-End Multi-Person Pose Estimation

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

Deep High-Resolution Representation Learning for Human Pose Estimation

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

Deep High-Resolution Representation Learning for Human Pose Estimation

ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation

RTMPose: Real-Time Multi-Person Pose Estimation based on MMPose

Model	Paper	AP	Date
UniPose	X-Pose: Detecting Any Keypoints	0.76	2023-10-12
RTMPose-l	RTMPose: Real-Time Multi-Person Pose Estimation b…	0.75	2023-03-13
ED-Pose (R50)	Explicit Box Detection Unifies End-to-End Multi-P…	0.72	2023-02-03
ViTPose-h	ViTPose: Simple Vision Transformer Baselines for …	0.47	2022-04-26
ViTPose-l	ViTPose: Simple Vision Transformer Baselines for …	0.46	2022-04-26
HRNet-w48	Deep High-Resolution Representation Learning for …	0.42	2019-02-25
ViTpose-b	ViTPose: Simple Vision Transformer Baselines for …	0.41	2022-04-26
HRNet-w32	Deep High-Resolution Representation Learning for …	0.40	2019-02-25
ViTPose-s	ViTPose: Simple Vision Transformer Baselines for …	0.38	2022-04-26
RTMPose-s	RTMPose: Real-Time Multi-Person Pose Estimation b…	0.31	2023-03-13