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 1–10 of 191 papers

TitleStatusHype
From Neck to Head: Bio-Impedance Sensing for Head Pose Estimation—0
Failure Forecasting Boosts Robustness of Sim2Real Rhythmic Insertion Policies—0
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations—0
RGBTrack: Fast, Robust Depth-Free 6D Pose Estimation and TrackingCode2
Fluoroscopic Shape and Pose Tracking of Catheters with Custom Radiopaque Markers—0
Mouse Lockbox Dataset: Behavior Recognition for Mice Solving Lockboxes—0
SpikeVideoFormer: An Efficient Spike-Driven Video Transformer with Hamming Attention and O(T) ComplexityCode1
Comparison of Visual Trackers for Biomechanical Analysis of Running—0
GSFF-SLAM: 3D Semantic Gaussian Splatting SLAM via Feature Field—0
Multi-person Physics-based Pose Estimation for Combat Sports—0
Show:102550
← PrevPage 1 of 20Next →
All datasetsPoseTrack2017PoseTrack2018Multi-Person PoseTrack

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1DetTrackMOTA64.3—Unverified
2UniTrackMOTA63.5—Unverified
34DHumans + ViTDetMOTA61.9—Unverified
4MSRAMOTA61.37—Unverified
5TML++ (MIPAL)MOTA54.86—Unverified