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

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 101–110 of 191 papers

TitleStatusHype
Pose2Gait: Extracting Gait Features from Monocular Video of Individuals with DementiaCode0
M3Act: Learning from Synthetic Human Group Activities—0
GenPose: Generative Category-level Object Pose Estimation via Diffusion Models—0
A Gated Attention Transformer for Multi-Person Pose Tracking—0
Counter-Hypothetical Particle Filters for Single Object Pose Tracking—0
Design, Implementation and Evaluation of an External Pose-Tracking System for Underwater Cameras—0
Event-based Camera Tracker by t NeRF—0
Markerless 3D human pose tracking through multiple cameras and AI: Enabling high accuracy, robustness, and real-time performance—0
Human from Blur: Human Pose Tracking from Blurry Images—0
ShaRPy: Shape Reconstruction and Hand Pose Estimation from RGB-D with Uncertainty—0
Show:102550
← PrevPage 11 of 20Next →
All datasetsPoseTrack2017PoseTrack2018Multi-Person PoseTrack

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