Jun 15, 2018 · Artificial Intelligence

JD AI Research Institute Wins CVPR 2018 LIP Human Pose Estimation Competition

In June 2018, JD AI Research Institute's Computer Vision and Multimedia Lab won both the single‑person and multi‑person tracks of the CVPR 2018 Look Into Person (LIP) competition, achieving 90.9% and 72.2% accuracy respectively through enhanced multi‑scale CNN models, data augmentation, and focal loss techniques.

CVPR 2018Deep LearningJD AI

0 likes · 5 min read

JD AI Research Institute Wins CVPR 2018 LIP Human Pose Estimation Competition

Baobao Algorithm Notes

Jan 21, 2018 · Artificial Intelligence

Winning the AI Challenger Human Pose Keypoint Contest with Multi‑Scale Fusion

The Firefly team secured first place in the AI Challenger human skeletal keypoint detection contest by employing a top‑down approach that combines Faster R‑CNN for person detection, a multi‑scale region‑feature fusion strategy, varied Gaussian and binary supervision, OKS‑NMS post‑processing, and extensive experiments demonstrating the impact of input size, supervision radius, and model stacking.

AI ChallengerOKS-NMShuman pose estimation

0 likes · 15 min read

Winning the AI Challenger Human Pose Keypoint Contest with Multi‑Scale Fusion