Rethinking on Multi-Stage Networks for Human Pose Estimation

Existing pose estimation approaches fall into two categories: single-stage and multi-stage methods. While multi-stage methods are seemingly more suited for the task, their performance in current practice is not as good as single-stage methods... (read more)

PDF Abstract

Results from the Paper


TASK DATASET MODEL METRIC NAME METRIC VALUE GLOBAL RANK RESULT BENCHMARK
Keypoint Detection COCO MSPN Test AP 76.1 # 4
Pose Estimation COCO minival MSPN AP 75.9 # 1
Keypoint Detection COCO test-challenge MSPN+* AR 82.2 # 1
ARM 77.5 # 1
AP 76.4 # 1
AP50 92.9 # 1
AP75 82.6 # 1
APL 88.6 # 1
AR50 96 # 1
AR75 87.7 # 1
ARL 83.2 # 1
Keypoint Detection COCO test-dev MSPN APL 81.5 # 3
APM 72.3 # 3
AP50 93.4 # 1
AP75 83.8 # 3
AR 81.6 # 2
AR50 96.3 # 1
AR75 88.1 # 2
ARL 87.1 # 2
ARM 77.5 # 1
AP 76.1 # 1
Pose Estimation COCO test-dev MSPN AP 76.1 # 5
AP50 93.4 # 1
AP75 83.8 # 5
APL 81.5 # 4
APM 72.3 # 5
AR 81.6 # 4
Pose Estimation MPII Human Pose MSPN PCKh-0.5 92.6% # 5

Methods used in the Paper


METHOD TYPE
🤖 No Methods Found Help the community by adding them if they're not listed; e.g. Deep Residual Learning for Image Recognition uses ResNet