2D Human Pose Estimation

What is Human Pose Estimation? Human pose estimation is the process of estimating the configuration of the body (pose) from a single, typically monocular, image. Background. Human pose estimation is one of the key problems in computer vision that has been studied for well over 15 years. The reason for its importance is the abundance of applications that can benefit from such a technology. For example, human pose estimation allows for higher-level reasoning in the context of human-computer interaction and activity recognition; it is also one of the basic building blocks for marker-less motion capture (MoCap) technology. MoCap technology is useful for applications ranging from character animation to clinical analysis of gait pathologies.

Papers

Recently Added Most Hyped Most Active Needs Verification Most Verified

Showing 101–118 of 118 papers

Title	Date	Tasks	Status
Human Pose Estimation using Motion Priors and Ensemble Models	Jan 26, 2019	2D Human Pose Estimation3D Human Pose Tracking	—Unverified
PoseFix: Model-agnostic General Human Pose Refinement Network	Dec 10, 2018	2D Human Pose EstimationKeypoint Detection	CodeCode Available
Near-Optimal Representation Learning for Hierarchical Reinforcement Learning	Oct 2, 2018	2D Human Pose Estimationcontinuous-control	CodeCode Available
Leolani: a reference machine with a theory of mind for social communication	Jun 5, 2018	10-shot image generation16k	CodeCode Available
Part-Aligned Bilinear Representations for Person Re-identification	Apr 19, 2018	2D Human Pose EstimationPerson Re-Identification	—Unverified
Pose2Seg: Detection Free Human Instance Segmentation	Mar 28, 2018	2D Human Pose EstimationHuman Instance Segmentation	CodeCode Available
LSTM Pose Machines	Dec 18, 2017	2D Human Pose EstimationPose Estimation	CodeCode Available
Alibaba at IJCNLP-2017 Task 1: Embedding Grammatical Features into LSTMs for Chinese Grammatical Error Diagnosis Task	Dec 1, 2017	2D Human Pose EstimationPosition	—Unverified
DeepSkeleton: Skeleton Map for 3D Human Pose Regression	Nov 29, 2017	2D Human Pose Estimation3D Human Pose Estimation	—Unverified
2D-3D Pose Consistency-based Conditional Random Fields for 3D Human Pose Estimation	Apr 13, 2017	2D Human Pose Estimation3D Human Pose Estimation	—Unverified
Learning from Synthetic Humans	Jan 5, 2017	2D Human Pose Estimation3D Human Pose Estimation	CodeCode Available
Associative Embedding: End-to-End Learning for Joint Detection and Grouping	Nov 16, 2016	2D Human Pose EstimationInstance Segmentation	CodeCode Available
3D Human Pose Estimation Using Convolutional Neural Networks with 2D Pose Information	Aug 10, 2016	2D Human Pose Estimation2D Pose Estimation	—Unverified
Preconditioned Stochastic Gradient Descent	Dec 14, 2015	2D Human Pose Estimation	CodeCode Available
Beyond Tree Structure Models: A New Occlusion Aware Graphical Model for Human Pose Estimation	Dec 1, 2015	2D Human Pose EstimationPose Estimation	—Unverified
Enhanced Mixtures of Part Model for Human Pose Estimation	Jan 22, 2015	2D Human Pose Estimation3D Pose Estimation	—Unverified
MoDeep: A Deep Learning Framework Using Motion Features for Human Pose Estimation	Sep 28, 2014	2D Human Pose EstimationPose Estimation	—Unverified
2D Human Pose Estimation: New Benchmark and State of the Art Analysis	Jun 1, 2014	2D Human Pose EstimationArt Analysis	CodeCode Available

Show:10 25 50

← PrevPage 3 of 3Next →

All datasets COCO-WholeBody Human-Art JHMDB (2D poses only)OCHuman Alibaba Cluster Trace ExLPose-LL-E ExLPose-LL-H ExLPose-LL-N ExLPose-OCN-A7M3 ExLPose-OCN-RICOH3

Benchmark Results

#	Model	Metric	Claimed	Verified	Status
1	RTMW-x	WB	70.2	—	Unverified
2	PCNet	WB	66.4	—	Unverified
3	ZoomNAS (V1.0 data)	WB	65.4	—	Unverified
4	RTMPose	WB	65.3	—	Unverified
5	TCFormer	WB	64.2	—	Unverified
6	ZoomNet (V1.0 data)	WB	63	—	Unverified
7	Sapiens-0.3B	WB	62	—	Unverified
8	ViTPose+-H	WB	61.2	—	Unverified
9	Zauss et al.	WB	60.4	—	Unverified
10	RTMW-m	WB	58	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	UniPose	AP	0.76	—	Unverified
2	RTMPose-l	AP (gt bbox)	0.75	—	Unverified
3	ED-Pose (R50)	AP	0.72	—	Unverified
4	ViTPose-h	AP	0.47	—	Unverified
5	ViTPose-l	AP	0.46	—	Unverified
6	HRNet-w48	AP	0.42	—	Unverified
7	ViTpose-b	AP	0.41	—	Unverified
8	HRNet-w32	AP	0.4	—	Unverified
9	ViTPose-s	AP	0.38	—	Unverified
10	RTMPose-s	AP	0.31	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DeciWatch	PCK	98.8	—	Unverified
2	Poseidon	PCK	97.3	—	Unverified
3	SimplePose	PCK	94.4	—	Unverified
4	DKD (ResNet50)	PCK	94	—	Unverified
5	LSTM PM	PCK	93.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	SEFD	Test AP	44.1	—	Unverified
2	ResNet-50	Test AP	30.4	—	Unverified
3	Pose2Seg	Test AP	23.8	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	mitsimpo	10-20% Mask PSNR	12	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DA-LLPose	AP	5	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DA-LLPose	AP	18.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DA-LLPose	AP	35.6	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DA-LLPose	AP	39.1	—	Unverified

#	Model	Metric	Claimed	Verified	Status
1	DA-LLPose	AP	36.2	—	Unverified