Deep High-Resolution Representation Learning for Human Pose Estimation

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 CVPR 2019 PDF CVPR 2019 Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK USES EXTRA
TRAINING DATA
RESULT BENCHMARK
Keypoint Detection COCO HRNet-48 Validation AP 76.3 # 3
Test AP 75.5 # 5
Keypoint Detection COCO HRNet-32 Validation AP 75.8 # 4
Instance Segmentation COCO minival HTC (HRNetV2p-W48) mask AP 41.0 # 12
Pose Estimation COCO test-dev HRNet-W48 AP 77 # 2
AP50 92.7 # 2
AP75 84.5 # 2
APL 83.1 # 2
APM 73.4 # 4
AR 82 # 2
Keypoint Detection COCO test-dev HRNet APL 81.5 # 3
APM 71.9 # 4
AP50 92.5 # 3
AP75 83.3 # 4
AR 80.5 # 4
Keypoint Detection COCO test-dev HRNet* APL 83.1 # 1
APM 73.4 # 1
AP50 92.7 # 2
AP75 84.5 # 1
AR 82.0 # 1
Pose Estimation MPII Human Pose HRNet-W32 PCKh-0.5 92.3% # 6
Pose Tracking PoseTrack2017 HRNet-W48 COCO MOTA 57.9 # 3
MAP 74.9 # 2

Methods used in the Paper


METHOD TYPE
Heatmap
Output Functions