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 141150 of 191 papers

TitleStatusHype
Combining detection and tracking for human pose estimation in videos0
AnimePose: Multi-person 3D pose estimation and animation0
RGB-D Odometry and SLAM0
15 Keypoints Is All You Need0
6-PACK: Category-level 6D Pose Tracker with Anchor-Based KeypointsCode0
Multi-view consensus CNN for 3D facial landmark placementCode0
Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor0
FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks0
Movement science needs different pose tracking algorithms0
Efficient Circle-Based Camera Pose Tracking Free of PnP0
Show:102550
← PrevPage 15 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