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

21CTO

Sep 1, 2015 · Artificial Intelligence

Why Traditional ML Teaching Fails and a Better Path for Developers

The article critiques the conventional bottom‑up, theory‑heavy machine‑learning curriculum for developers, argues that costly degrees and deep math are unnecessary, and proposes a top‑down, project‑focused approach using modern tools, repeatable processes, suitable datasets, and practical resources to quickly build end‑to‑end ML solutions.

Developer GuideML toolspractical workflow

0 likes · 16 min read

Why Traditional ML Teaching Fails and a Better Path for Developers