A unified bottom-up model that refines keypoints with disk-relative centroid vectors and uses high-confidence keypoints as dynamic mask centers outperforms prior pose and segmentation models on COCO, CrowdPose, and OCHuman.
Human pose estima- tion for real-world crowded scenarios
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Keypoints as Dynamic Centroids for Unified Human Pose and Segmentation
A unified bottom-up model that refines keypoints with disk-relative centroid vectors and uses high-confidence keypoints as dynamic mask centers outperforms prior pose and segmentation models on COCO, CrowdPose, and OCHuman.