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 171180 of 191 papers

TitleStatusHype
Efficient Pose Tracking from Natural Features in Standard Web Browsers0
Learning to Refine Human Pose Estimation0
Simple Baselines for Human Pose Estimation and TrackingCode1
Statistical Sensor Fusion of a 9-DoF MEMS IMU for Indoor Navigation0
Pose Flow: Efficient Online Pose TrackingCode0
Detect-and-Track: Efficient Pose Estimation in VideosCode0
PoseTrack: A Benchmark for Human Pose Estimation and TrackingCode0
A Generative Model for Depth-Based Robust 3D Facial Pose Tracking0
Camera Pose Filtering with Local Regression Geodesics on the Riemannian Manifold of Dual Quaternions0
Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor0
Show:102550
← PrevPage 18 of 20Next →

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