SOTAVerified

Multi-Person Pose Estimation

Multi-person pose estimation is the task of estimating the pose of multiple people in one frame.

( Image credit: Human Pose Estimation with TensorFlow )

Papers

Showing 26–50 of 151 papers

TitleStatusHype
Greedy Offset-Guided Keypoint Grouping for Human Pose EstimationCode1
Graph and Temporal Convolutional Networks for 3D Multi-person Pose Estimation in Monocular VideosCode1
Mask R-CNNCode1
HRFormer: High-Resolution Transformer for Dense PredictionCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
Generative Partition Networks for Multi-Person Pose EstimationCode1
Differentiable Multi-Granularity Human Representation Learning for Instance-Aware Human Semantic ParsingCode1
LAMP: Leveraging Language Prompts for Multi-person Pose EstimationCode1
I^2R-Net: Intra- and Inter-Human Relation Network for Multi-Person Pose EstimationCode1
Human Pose Regression with Residual Log-likelihood EstimationCode1
DiffusionRegPose: Enhancing Multi-Person Pose Estimation using a Diffusion-Based End-to-End Regression ApproachCode1
DirectPose: Direct End-to-End Multi-Person Pose EstimationCode1
Bottom-Up Human Pose Estimation by Ranking Heatmap-Guided Adaptive Keypoint EstimatesCode1
InsPose: Instance-Aware Networks for Single-Stage Multi-Person Pose EstimationCode1
Dual networks based 3D Multi-Person Pose Estimation from Monocular VideoCode1
BoIR: Box-Supervised Instance Representation for Multi-Person Pose EstimationCode1
EfficientHRNet: Efficient Scaling for Lightweight High-Resolution Multi-Person Pose EstimationCode1
Graph-Based 3D Multi-Person Pose Estimation Using Multi-View ImagesCode1
Metric-Scale Truncation-Robust Heatmaps for 3D Human Pose EstimationCode1
Iterative Greedy Matching for 3D Human Pose Tracking from Multiple ViewsCode1
End-to-End Multi-Person Pose Estimation With TransformersCode1
EvoPose2D: Pushing the Boundaries of 2D Human Pose Estimation using Accelerated Neuroevolution with Weight TransferCode1
Explicit Box Detection Unifies End-to-End Multi-Person Pose EstimationCode1
AdaptivePose: Human Parts as Adaptive PointsCode1
Learning Delicate Local Representations for Multi-Person Pose EstimationCode1
Show:102550
← PrevPage 2 of 7Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RTMO-lmAP @0.5:0.9583.8—Unverified
2BUCTD-W48 (w/cond. input from PETR, and generative sampling)mAP @0.5:0.9578.5—Unverified
3I²R-Net (1st stage: HRFormer-B)mAP @0.5:0.9577.4—Unverified
4ED-Pose (Swin-L)mAP @0.5:0.9576.6—Unverified
5DETRPose-XmAP @0.5:0.9575.1—Unverified
6DETRPose-LmAP @0.5:0.9573.3—Unverified
7HRFormer-BmAP @0.5:0.9572.4—Unverified
8BAPose (W32)mAP @0.5:0.9572.2—Unverified
9DETRPose-MmAP @0.5:0.9572—Unverified
10TransPose-HmAP @0.5:0.9571.8—Unverified
#ModelMetricClaimedVerifiedStatus
1EvoPose2D-LTest AP76.8—Unverified
2PoseFixTest AP76.7—Unverified
3LitePose-STest AP56.7—Unverified
4RSNAP0.79—Unverified
5DarkPoseAP0.77—Unverified
6UniPoseAP0.77—Unverified
7CPN+AP0.73—Unverified
8BAPoseAP0.73—Unverified
9CenterGroupAP0.71—Unverified
10OpenPifPafAP0.71—Unverified
#ModelMetricClaimedVerifiedStatus
1SCIO (HRNet-48)AP79.2—Unverified
2HRNet-W48plusAP78.7—Unverified
3HRNet-W32AP76.2—Unverified
4ResNet50AP73.7—Unverified
5HigherHRNet (ScaleNet_P4)AP71.6—Unverified
6HigherHRNet (HR-Net-48)AP70.5—Unverified
7SMPR (HR-Net-32)AP70.2—Unverified
8PersonLabAP68.7—Unverified
9Identity Mapping HourglassAP68.1—Unverified
10SPMAP66.9—Unverified
#ModelMetricClaimedVerifiedStatus
1AlphaPoseAP82.1—Unverified
2Generative Partition NetworksAP80.4—Unverified
3SPMAP78.5—Unverified
4RefineAP78—Unverified
5Associative EmbeddingAP77.5—Unverified
6Part Affinity FieldsAP75.6—Unverified
7Articulated TrackingAP74.3—Unverified
8Local Joint-to-Person AssociationAP62.2—Unverified
9DeeperCutAP59.4—Unverified
#ModelMetricClaimedVerifiedStatus
1MIPNet (gt-bb)AP5089.7—Unverified
2I²R-Net (1st stage:TransPose-H)AP5085—Unverified
3TransPose-HAP5082.7—Unverified
4HRFormer-BAP5081.4—Unverified
5SPMAP5067.5—Unverified
6CrowdPoseAP5040.8—Unverified
7SimplePoseAP5037.4—Unverified
8Mask R-CNNAP5033.2—Unverified
#ModelMetricClaimedVerifiedStatus
1HRNet-W48plusAP79.1—Unverified
2HRNet-W32AP77.8—Unverified
3ResNet50AP75.3—Unverified
4InsPoseAP63.1—Unverified
#ModelMetricClaimedVerifiedStatus
1PoseidonMean mAP87.8—Unverified
2DCPoseMean mAP79—Unverified
3PoseWarperMean mAP78—Unverified
4RefineMean mAP73.8—Unverified
#ModelMetricClaimedVerifiedStatus
1DCPoseMean mAP79.2—Unverified
2PoseWarperMean mAP77.94—Unverified
3PoseTrackMean mAP59.4—Unverified
#ModelMetricClaimedVerifiedStatus
1DeeperCutAOP88.1—Unverified
2DeepCutAOP86.5—Unverified
3Generative Partition NetworksAP84.8—Unverified
#ModelMetricClaimedVerifiedStatus
1CMU-PoseAP0.62—Unverified
#ModelMetricClaimedVerifiedStatus
1PoseTrackMean mAP38.2—Unverified
#ModelMetricClaimedVerifiedStatus
1PoseidonMean mAP88.3—Unverified