SOTAVerified

Multi-Person Pose Estimation and Tracking

Joint multi-person pose estimation and tracking following the PoseTrack benchmark. https://posetrack.net/

( Image credit: PoseTrack )

Papers

Recently AddedMost HypedMost ActiveNeeds VerificationMost Verified

Showing 1–11 of 11 papers

TitleStatusHype
AlphaPose: Whole-Body Regional Multi-Person Pose Estimation and Tracking in Real-TimeCode5
Texture-Based Input Feature Selection for Action Recognition—0
JRDB-Pose: A Large-scale Dataset for Multi-Person Pose Estimation and Tracking—0
Learning Dynamics via Graph Neural Networks for Human Pose Estimation and Tracking—0
Temporal Keypoint Matching and Refinement Network for Pose Estimation and Tracking—0
Self-supervised Keypoint Correspondences for Multi-Person Pose Estimation and Tracking in Videos—0
FastPose: Towards Real-time Pose Estimation and Tracking via Scale-normalized Multi-task Networks—0
Multi-person Articulated Tracking with Spatial and Temporal Embeddings—0
Multi-Domain Pose Network for Multi-Person Pose Estimation and Tracking—0
Learning to Refine Human Pose Estimation—0
PoseTrack: Joint Multi-Person Pose Estimation and TrackingCode0
Show:102550

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RefineMOTA58.4—Unverified