登录
洞察 - Multi-Person Pose Estimation
Dual-Path Hierarchical Relation Network for Accurate Multi-Person Pose Estimation
The proposed Dual-Path Hierarchical Relation Network (DHRNet) leverages complementary cross-instance and cross-joint interactive information to enhance multi-person pose estimation performance.
A Novel One-Stage End-to-End Approach for Efficient and Accurate Multi-Person Pose Estimation
A novel one-stage end-to-end algorithm called Joint Coordinate Regression and Association (JCRA) that directly predicts full-body poses without any post-processing, achieving state-of-the-art performance in accuracy and efficiency.
