SOTAVerified

Multi-Person Pose Estimation

Multi-person pose estimation is the task of estimating the pose of multiple people in one frame.

( Image credit: Human Pose Estimation with TensorFlow )

Papers

Showing 110 of 151 papers

TitleStatusHype
SEPose: A Synthetic Event-based Human Pose Estimation Dataset for Pedestrian Monitoring0
DETRPose: Real-time end-to-end transformer model for multi-person pose estimationCode2
LGM-Pose: A Lightweight Global Modeling Network for Real-time Human Pose Estimation0
MultiFormer: A Multi-Person Pose Estimation System Based on CSI and Attention Mechanism0
Multi-person Physics-based Pose Estimation for Combat Sports0
RapidPoseTriangulation: Multi-view Multi-person Whole-body Human Pose Triangulation in a MillisecondCode0
SimpleDepthPose: Fast and Reliable Human Pose Estimation with RGBD-ImagesCode0
Poseidon: A ViT-based Architecture for Multi-Frame Pose Estimation with Adaptive Frame Weighting and Multi-Scale Feature FusionCode1
Waterfall Transformer for Multi-person Pose Estimation0
VoxelKeypointFusion: Generalizable Multi-View Multi-Person Pose EstimationCode0
Show:102550
← PrevPage 1 of 16Next →

Benchmark Results

#ModelMetricClaimedVerifiedStatus
1RTMO-lmAP @0.5:0.9583.8Unverified
2BUCTD-W48 (w/cond. input from PETR, and generative sampling)mAP @0.5:0.9578.5Unverified
3I²R-Net (1st stage: HRFormer-B)mAP @0.5:0.9577.4Unverified
4ED-Pose (Swin-L)mAP @0.5:0.9576.6Unverified
5DETRPose-XmAP @0.5:0.9575.1Unverified
6DETRPose-LmAP @0.5:0.9573.3Unverified
7HRFormer-BmAP @0.5:0.9572.4Unverified
8BAPose (W32)mAP @0.5:0.9572.2Unverified
9DETRPose-MmAP @0.5:0.9572Unverified
10TransPose-HmAP @0.5:0.9571.8Unverified