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 151160 of 191 papers

TitleStatusHype
Efficient Circle-Based Camera Pose Tracking Free of PnP0
Movement science needs different pose tracking algorithms0
Large-scale, real-time visual-inertial localization revisited0
Pose estimator and tracker using temporal flow maps for limbs0
PoseRBPF: A Rao-Blackwellized Particle Filter for 6D Object Pose TrackingCode0
Low-latency Visual SLAM with Appearance-Enhanced Local Map Building0
LightTrack: A Generic Framework for Online Top-Down Human Pose TrackingCode0
Visibility Constrained Generative Model for Depth-based 3D Facial Pose Tracking0
Multigrid Predictive Filter Flow for Unsupervised Learning on VideosCode0
Multi-person Articulated Tracking with Spatial and Temporal Embeddings0
Show:102550
← PrevPage 16 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