SOTAVerified

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

Showing 101–118 of 118 papers

TitleStatusHype
HigherHRNet: Scale-Aware Representation Learning for Bottom-Up Human Pose EstimationCode0
EventGAN: Leveraging Large Scale Image Datasets for Event CamerasCode0
Boosting Semi-Supervised 2D Human Pose Estimation by Revisiting Data Augmentation and Consistency TrainingCode0
Semi-supervised Human Pose Estimation in Art-historical ImagesCode0
PoseFix: Model-agnostic General Human Pose Refinement NetworkCode0
Efficient, Self-Supervised Human Pose Estimation with Inductive Prior TuningCode0
Pose2Seg: Detection Free Human Instance SegmentationCode0
PifPaf: Composite Fields for Human Pose EstimationCode0
Domain-Adaptive 2D Human Pose Estimation via Dual Teachers in Extremely Low-Light ConditionsCode0
Data-Free Backbone Fine-Tuning for Pruned Neural NetworksCode0
Near-Optimal Representation Learning for Hierarchical Reinforcement LearningCode0
LSTM Pose MachinesCode0
An Animation-based Augmentation Approach for Action Recognition from Discontinuous VideoCode0
AutoPose: Searching Multi-Scale Branch Aggregation for Pose EstimationCode0
Leolani: a reference machine with a theory of mind for social communicationCode0
Associative Embedding: End-to-End Learning for Joint Detection and GroupingCode0
导师评价网数据已在Github备份,可直接检索导师个人信息!Code0
Learning from Synthetic HumansCode0
Show:102550
← PrevPage 5 of 5Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RTMW-xWB70.2—Unverified
2PCNetWB66.4—Unverified
3ZoomNAS (V1.0 data)WB65.4—Unverified
4RTMPoseWB65.3—Unverified
5TCFormerWB64.2—Unverified
6ZoomNet (V1.0 data)WB63—Unverified
7Sapiens-0.3BWB62—Unverified
8ViTPose+-HWB61.2—Unverified
9Zauss et al.WB60.4—Unverified
10RTMW-mWB58—Unverified
#ModelMetricClaimedVerifiedStatus
1UniPoseAP0.76—Unverified
2RTMPose-lAP (gt bbox)0.75—Unverified
3ED-Pose (R50)AP0.72—Unverified
4ViTPose-hAP0.47—Unverified
5ViTPose-lAP0.46—Unverified
6HRNet-w48AP0.42—Unverified
7ViTpose-bAP0.41—Unverified
8HRNet-w32AP0.4—Unverified
9ViTPose-sAP0.38—Unverified
10RTMPose-sAP0.31—Unverified
#ModelMetricClaimedVerifiedStatus
1DeciWatchPCK98.8—Unverified
2PoseidonPCK97.3—Unverified
3SimplePosePCK94.4—Unverified
4DKD (ResNet50)PCK94—Unverified
5LSTM PMPCK93.6—Unverified
#ModelMetricClaimedVerifiedStatus
1SEFDTest AP44.1—Unverified
2ResNet-50Test AP30.4—Unverified
3Pose2SegTest AP23.8—Unverified
#ModelMetricClaimedVerifiedStatus
1mitsimpo10-20% Mask PSNR12—Unverified
#ModelMetricClaimedVerifiedStatus
1DA-LLPoseAP5—Unverified
#ModelMetricClaimedVerifiedStatus
1DA-LLPoseAP18.6—Unverified
#ModelMetricClaimedVerifiedStatus
1DA-LLPoseAP35.6—Unverified
#ModelMetricClaimedVerifiedStatus
1DA-LLPoseAP39.1—Unverified
#ModelMetricClaimedVerifiedStatus
1DA-LLPoseAP36.2—Unverified