List your company

Human Pose Estimation on PoseTrack 2017 (val)

93.3HeadTAR-ViTPose*
65.63672.8188087.182Jun 7, 2021Mar 22, 2022Jan 5, 2023Oct 21, 2023Aug 5, 2024May 21, 2025Mar 6, 2026

Evaluation results

MethodLinks
TAR-ViTPose*Backbone=ViT-H, Bounding Box Source=Ground-truth2026.0393.394.490.68786.59088.9—90.3
TAR-ViTPose*Backbone=ViT-B, Bounding Box Source=Ground-truth2026.0392.392.688.283.385.987.482.2—87.7
Poseidon*Backbone=ViT-H, Bounding Box Source=Ground-truth2026.0391.993.188.685.788.289.684.4—88.9
GNN-based pose dynamics learningBackbone=HRNet, Detector=Faster R-CNN, Filtering=None (pure pose estimation)2021.0690.990.78679.283.882.77884.9—
GLSMambaBackbone=ViT-H, Bounding Box Source=Ground-truth or unspecified2026.0390.792.189.285.38788.482.4—88
TDMI-ST2023.0390.690.787.281.585.284.578.785.9—
TDMIBackbone=HRNet-W48, Bounding Box Source=Ground-truth or unspecified2026.0390.69187.281.585.284.578.7—85.9
TAR-ViTPoseBackbone=ViT-H, Bounding Box Source=Predicted (Faster R-CNN)2026.0390.591.988.483.884.987.380.2—86.8
DCPose + HANetBase method=DCPose2022.1190908578.883.182.177.184.2—
TDMI2023.039091.187.181.485.284.578.585.7—
DSTABackbone=HRNet-W48, Approach=regression-based2024.0389.890.886.279.385.282.275.984.6—
DSTABackbone=HRNet-W48, Bounding Box Source=Predicted (Faster R-CNN)2026.0389.890.886.279.385.282.275.9—84.6
FAMI-Pose2022.0389.690.186.38084.683.47784.8—
FAMI-Pose2023.0389.690.186.38084.683.47784.8—
FAMIPoseBackbone=HRNet-W48, Approach=heatmap-based2024.0389.690.186.38084.683.47784.8—
FAMI-PoseBackbone=HRNet-W48, Bounding Box Source=Predicted (Faster R-CNN)2026.0389.690.186.38084.683.477—84.8
CombDetFiltering=None (pure pose estimation)2021.0689.489.785.579.582.480.876.483.8—
DetTrack2023.0389.489.785.579.582.480.876.483.8—
DetTrackBackbone=HRNet-W48, Approach=heatmap-based2024.0389.489.785.579.582.480.876.483.8—
DetTrackBackbone=HRNet-W48, Bounding Box Source=Ground-truth or unspecified2026.0389.489.785.579.582.480.876.4—83.8
DSTABackbone=ViT-H, Approach=regression-based2024.0389.390.687.382.684.585.177.885.6—
DSTABackbone=ViT-H, Bounding Box Source=Predicted (Faster R-CNN)2026.0389.390.687.382.684.585.177.8—85.6
CM-PoseBackbone=ViT, Bounding Box Source=Ground-truth or unspecified2026.0389.2928985.688.687.281.1—87.5
DiffPoseBackbone=ViT, Bounding Box Source=Ground-truth or unspecified2026.038991.287.483.585.587.280.2—86.4
Dynamic-GNN2022.0388.488.48274.579.178.373.181.1—
Dynamic-GNN2023.0388.488.48274.579.178.373.181.1—
Dyn.-GNNBackbone=HRNet-W48, Approach=heatmap-based2024.0388.488.48274.579.178.373.181.1—
Dyn.-GNNBackbone=HRNet-W48, Bounding Box Source=Ground-truth or unspecified2026.0388.488.48274.579.178.373.1—81.1
DSTABackbone=ResNet-152, Approach=regression-based2024.0388.388.183.37682.581.17081.8—
PAVE-Net†Backbone=Swin-L, Bounding Box Source=Predicted (Faster R-CNN), End-to-end=true2026.0388.289.181.774.881.678.571.8—81.3
DCPose2022.038888.784.178.48381.474.282.8—
DCPose2022.118888.784.178.48381.474.282.8—
DCPose2023.038888.784.178.48381.474.282.8—
DCPoseBackbone=HRNet-W48, Approach=heatmap-based2024.038888.784.178.48381.474.282.8—
DCPoseBackbone=HRNet-W48, Bounding Box Source=Predicted (Faster R-CNN)2026.038888.784.178.48381.474.2—82.8
TAR-ViTPoseBackbone=ViT-B, Bounding Box Source=Predicted (Faster R-CNN)2026.038889.28580.382.984.277.3—84
TAR-ViTPose*Backbone=ViT-S, Bounding Box Source=Ground-truth2026.038888.984.278.482.681.576.9—83.2
TAR-ViTPoseBackbone=ViT-S, Bounding Box Source=Predicted (Faster R-CNN)2026.0387.18883.277.880.48174.2—81.9
CorrTrack2023.0386.18783.476.477.379.273.380.8—
MDPN2022.0385.288.583.977.5797771.480.7—
MDPN2023.0385.288.583.977.5797771.480.7—
MDPNBackbone=ResNet-152, Approach=heatmap-based2024.0385.288.583.977.5797771.480.7—
STEmbedding2022.0383.881.677.17077.474.570.877—
STEmbedding2023.0383.881.677.17077.474.570.877—
STEmbed.Backbone=ResNet-152, Approach=heatmap-based2024.0383.881.677.17077.474.570.877—
STEmbedBackbone=ResNet-152, Bounding Box Source=Ground-truth or unspecified2026.0383.881.677.17077.474.570.8—77
HRNet2022.0382.183.680.473.375.575.368.577.3—
HRNet2022.1182.183.680.473.375.575.368.577.3—
HRNet2023.0382.183.680.473.375.575.368.577.3—
HRNetBackbone=HRNet-W48, Approach=heatmap-based2024.0382.183.680.473.375.575.368.577.3—
HRNetBackbone=HRNet-W48, Bounding Box Source=Predicted (Faster R-CNN)2026.0382.183.680.473.375.575.368.5—77.3
Simplebackbone=ResNet-1522022.0381.783.48072.475.374.867.176.7—
SimpleBackbone=ResNet-1522023.0381.783.48072.475.374.867.176.7—
SimBase.Backbone=ResNet-152, Approach=heatmap-based2024.0381.783.48072.475.374.867.176.7—
SimBase.Backbone=ResNet-152, Bounding Box Source=Predicted (Faster R-CNN)2026.0381.783.48072.475.374.867.1—76.7
PoseWarperFiltering=None (pure pose estimation)2021.0681.488.383.97882.480.573.681.2—
PoseWarper2022.0381.488.383.97882.480.573.681.2—
PoseWarper2022.1181.488.383.97882.480.573.681.2—
PoseWarper2023.0381.488.383.97882.480.573.681.2—
PoseWarp.Backbone=HRNet-W48, Approach=heatmap-based2024.0381.488.383.97882.480.573.681.2—
PoseWarp.Backbone=HRNet-W48, Bounding Box Source=Predicted (Faster R-CNN)2026.0381.488.383.97882.480.573.6—81.2
FastPose2022.038080.369.559.171.467.559.470.3—
FastPose2023.038080.369.559.171.467.559.470.3—
FastPoseBackbone=ResNet-101, Approach=heatmap-based2024.038080.368.559.171.467.559.470.3—
Simplebackbone=ResNet-502022.0379.180.575.56670.87061.772.4—
SimpleBackbone=ResNet-502023.0379.180.575.56670.87061.772.4—
JointFlow2022.0369.3——————69.3—
PoseTracker2022.0367.570.26251.760.758.749.860.6—
PoseTracker2023.0367.570.26251.760.758.749.860.6—
PoseTrackBackbone=ResNet-101, Approach=heatmap-based2024.0367.570.26251.760.758.749.860.6—
PoseTrackBackbone=ResNet-101, Bounding Box Source=Predicted (Faster R-CNN)2026.0367.570.26251.760.758.749.8—60.6
PoseFlow2022.0366.773.368.361.167.56761.366.5—
PoseFlow2023.0366.773.368.361.167.56761.366.5—
PoseFlowBackbone=ResNet-101, Approach=heatmap-based2024.0366.773.368.361.167.56761.366.5—
PoseFlowBackbone=ResNet-152, Bounding Box Source=Predicted (Faster R-CNN)2026.0366.773.368.361.167.56761.3—66.5
DCPoseBackbone=HRNet-W48, #Params=65.2M, FPS(↑)=128, GPU=A6000, Batch size=16, Auxiliary frames=22026.03————————82.8
DSTABackbone=ResNet-50, Method Category=video-based, Input Resolution=256 x 1922024.03————————79.7
DSTABackbone=HRNet-W48, Method Category=video-based, Input Resolution=384 x 2882024.03————————84.6
DSTABackbone=ViT-H, Method Category=video-based, Input Resolution=256 x 1922024.03————————85.6
DSTABackbone=HRNet-W48, #Params=63.7M, FPS(↑)=156, GPU=A6000, Batch size=16, Auxiliary frames=22026.03————————83.4
DSTABackbone=ViT-H, #Params=422.2M, FPS(↑)=25, GPU=A6000, Batch size=16, Auxiliary frames=22026.03————————84.3
JointFlow2023.03———————69.3—
PoseurBackbone=ResNet-50, Method Category=image-based, Input Resolution=256 x 1922024.03————————74.4
PoseurBackbone=HRNet-W48, Method Category=image-based, Input Resolution=384 x 2882024.03————————79.3
PoseurBackbone=ViT-H, Method Category=image-based, Input Resolution=256 x 1922024.03————————81
PoseWarperBackbone=HRNet-W48, #Params=71.1M, FPS(↑)=52, GPU=A6000, Batch size=16, Auxiliary frames=22026.03————————81
RLEBackbone=ResNet-50, Method Category=image-based, Input Resolution=256 x 1922024.03————————70.7
RLEBackbone=HRNet-W48, Method Category=image-based, Input Resolution=384 x 2882024.03————————75.7
RLEBackbone=ViT-H, Method Category=image-based, Input Resolution=256 x 1922024.03————————79
TAR-ViTPoseBackbone=ViT-S, #Params=35.6M, FPS(↑)=413, GPU=A6000, Batch size=16, Auxiliary frames=22026.03————————81.5
TAR-ViTPoseBackbone=ViT-B, #Params=101.1M, FPS(↑)=186, GPU=A6000, Batch size=16, Auxiliary frames=22026.03————————83.4
TAR-ViTPoseBackbone=ViT-H, #Params=672.5M, FPS(↑)=28, GPU=A6000, Batch size=16, Auxiliary frames=22026.03————————86.3
TML++2022.03———————71.5—
TML++2023.03———————71.5—