SOTAVerified

Pose Tracking

Pose Tracking is the task of estimating multi-person human poses in videos and assigning unique instance IDs for each keypoint across frames. Accurate estimation of human keypoint-trajectories is useful for human action recognition, human interaction understanding, motion capture and animation.

Source: LightTrack: A Generic Framework for Online Top-Down Human Pose Tracking

Papers

Showing 125 of 191 papers

TitleStatusHype
BlazePose: On-device Real-time Body Pose trackingCode4
FoundationPose: Unified 6D Pose Estimation and Tracking of Novel ObjectsCode4
Humans in 4D: Reconstructing and Tracking Humans with TransformersCode3
Keypoint Promptable Re-IdentificationCode3
BundleSDF: Neural 6-DoF Tracking and 3D Reconstruction of Unknown ObjectsCode3
RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and TrackingCode2
ESVO2: Direct Visual-Inertial Odometry with Stereo Event CamerasCode2
IMU-Aided Event-based Stereo Visual OdometryCode2
Structure PLP-SLAM: Efficient Sparse Mapping and Localization using Point, Line and Plane for Monocular, RGB-D and Stereo CamerasCode2
You Only Demonstrate Once: Category-Level Manipulation from Single Visual DemonstrationCode2
Keypoint-Based Category-Level Object Pose Tracking from an RGB Sequence with Uncertainty EstimationCode2
AvatarPoser: Articulated Full-Body Pose Tracking from Sparse Motion SensingCode2
DynOPETs: A Versatile Benchmark for Dynamic Object Pose Estimation and Tracking in Moving Camera ScenariosCode1
Do Different Tracking Tasks Require Different Appearance Models?Code1
GS-EVT: Cross-Modal Event Camera Tracking based on Gaussian SplattingCode1
Embracing Dynamics: Dynamics-aware 4D Gaussian Splatting SLAMCode1
Deep High-Resolution Representation Learning for Human Pose EstimationCode1
GarmentTracking: Category-Level Garment Pose TrackingCode1
High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized OptimizationCode1
CAPTRA: CAtegory-level Pose Tracking for Rigid and Articulated Objects from Point CloudsCode1
Data-driven 6D Pose Tracking by Calibrating Image Residuals in Synthetic DomainsCode1
3D Neural Embedding Likelihood: Probabilistic Inverse Graphics for Robust 6D Pose EstimationCode1
3D-POP - An automated annotation approach to facilitate markerless 2D-3D tracking of freely moving birds with marker-based motion captureCode1
Deep Graph Pose: a semi-supervised deep graphical model for improved animal pose trackingCode1
BundleTrack: 6D Pose Tracking for Novel Objects without Instance or Category-Level 3D ModelsCode1
Show:102550
← PrevPage 1 of 8Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DetTrackMOTA64.09Unverified
2KeyTrackMOTA61.15Unverified
3LightTrackMOTA58.01Unverified
4HRNet-W48 COCOMOTA57.93Unverified
5MSRA (FlowTrack)MOTA57.81Unverified
6TML++ (MIPAL)MOTA54.46Unverified
7STAFMOTA53.81Unverified
8ProTrackerMOTA51.82Unverified
9PoseFlowMOTA50.98Unverified
10PoseTrackMOTA48.37Unverified
#ModelMetricClaimedVerifiedStatus
1DetTrackMOTA64.3Unverified
2UniTrackMOTA63.5Unverified
34DHumans + ViTDetMOTA61.9Unverified
4MSRAMOTA61.37Unverified
5TML++ (MIPAL)MOTA54.86Unverified
#ModelMetricClaimedVerifiedStatus
1PoseTrackMOTA28.2Unverified