Deep High-Resolution Representation Learning for Human Pose Estimation

CVPR 2019 Ke SunBin XiaoDong LiuJingdong Wang

This is an official pytorch implementation of Deep High-Resolution Representation Learning for Human Pose Estimation. In this work, we are interested in the human pose estimation problem with a focus on learning reliable high-resolution representations... (read more)

PDF Abstract

Evaluation Results from the Paper


#2 best model for Pose Estimation on COCO (using extra training data)

     Get a GitHub badge
TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
COMPARE
Keypoint Detection COCO HRNet-48 Validation AP 76.3 # 2
Keypoint Detection COCO HRNet-48 Test AP 75.5 # 4
Pose Estimation COCO HRNet-48 Mean mAP 77.0 # 2
Multi-Person Pose Estimation COCO HRNet-48 AP 0.770 # 2
Keypoint Detection COCO HRNet-32 Validation AP 75.8 # 3
Instance Segmentation COCO minival HTC (HRNetV2p-W48) mask AP 41.0 # 2
Pose Estimation MPII Human Pose HRNet-32 PCKh-0.5 92.3% # 4
Pose Tracking PoseTrack2017 HRNet MOTA 57.93 # 3