Pose estimation in crowds improves by 4.7% AP via COCO-based occlusion augmentation, explicit occlusion prediction branches, and an extended JTA dataset with higher density and variety.
Title resolution pending
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2019 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Human Pose Estimation for Real-World Crowded Scenarios
Pose estimation in crowds improves by 4.7% AP via COCO-based occlusion augmentation, explicit occlusion prediction branches, and an extended JTA dataset with higher density and variety.