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 76–100 of 191 papers

TitleStatusHype
Single camera pose estimation using Bayesian filtering and Kinect motion priorsCode0
Multi-person Physics-based Pose Estimation for Combat Sports—0
Multi-person Pose Tracking using Sequential Monte Carlo with Probabilistic Neural Pose Predictor—0
Input-Output Extension of Underactuated Nonlinear Systems—0
No More Shortcuts: Realizing the Potential of Temporal Self-Supervision—0
OA-SLAM: Leveraging Objects for Camera Relocalization in Visual SLAM—0
Omni6DPose: A Benchmark and Model for Universal 6D Object Pose Estimation and Tracking—0
OmniPose6D: Towards Short-Term Object Pose Tracking in Dynamic Scenes from Monocular RGB—0
Peek into the Future Camera-based Occupant Sensing in Configurable Cabins for Autonomous Vehicles—0
Pose estimator and tracker using temporal flow maps for limbs—0
PoseFlow: A Deep Motion Representation for Understanding Human Behaviors in Videos—0
PoseTrackReID: Dataset Description—0
Real Acoustic Fields: An Audio-Visual Room Acoustics Dataset and Benchmark—0
Real-Time Constrained 6D Object-Pose Tracking of An In-Hand Suture Needle for Minimally Invasive Robotic Surgery—0
Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor—0
Physics-Based Object 6D-Pose Estimation during Non-Prehensile Manipulation—0
Relative Localization of Mobile Robots with Multiple Ultra-WideBand Ranging Measurements—0
RGB-D Odometry and SLAM—0
Robotic Manipulation by Imitating Generated Videos Without Physical Demonstrations—0
Robust 6DoF Pose Tracking Considering Contour and Interior Correspondence Uncertainty for AR Assembly Guidance—0
Robust pose tracking with a joint model of appearance and shape—0
ROSEFusion: Random Optimization for Online Dense Reconstruction under Fast Camera Motion—0
SeamPose: Repurposing Seams as Capacitive Sensors in a Shirt for Upper-Body Pose Tracking—0
Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos—0
ShaRPy: Shape Reconstruction and Hand Pose Estimation from RGB-D with Uncertainty—0
Show:102550
← PrevPage 4 of 8Next →
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