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 41–50 of 191 papers

TitleStatusHype
Visual Representation Learning with Stochastic Frame Prediction—0
SignMusketeers: An Efficient Multi-Stream Approach for Sign Language Translation at Scale—0
HO-Cap: A Capture System and Dataset for 3D Reconstruction and Pose Tracking of Hand-Object InteractionCode1
Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking—0
IMU-Aided Event-based Stereo Visual OdometryCode2
MS-MANO: Enabling Hand Pose Tracking with Biomechanical Constraints—0
You Only Scan Once: A Dynamic Scene Reconstruction Pipeline for 6-DoF Robotic Grasping of Novel Objects—0
Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark—0
High-Fidelity SLAM Using Gaussian Splatting with Rendering-Guided Densification and Regularized OptimizationCode1
Input-Output Extension of Underactuated Nonlinear Systems—0
Show:102550
← PrevPage 5 of 20Next →

Benchmark Results

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