AI Paper Atlas

Research map / 3D vision / Human pose estimation

FDN: Feature Decoupling Network for Head Pose Estimation

AAAI 2020 · 3D vision › Human pose estimation · approach: Category-level object pose estimation · 74 citations (OpenAlex)

Read the paperCheck your idea against 108,967 papers

AI-extracted summary. Written by AI from the paper's title only (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add feature decoupling (FD) module (ablation)FDN baseline · AFLW2000MAE (degrees): 4.65 -> 4.56Helped
add feature decoupling (FD) module (ablation)FDN baseline · BIWIMAE (degrees): 3.63 -> 3.45Helped
add cross-category center (CCC) loss (ablation)FDN with FD module · AFLW2000MAE (degrees): 4.56 -> 4.42Helped
add cross-category center (CCC) loss (ablation)FDN with FD module · BIWIMAE (degrees): 3.45 -> 3.29Helped
use inverted residual backbone instead of ResNet18 (ablation)FDN · BIWIMAE (degrees): 4.02 -> 3.29Helped
FDN vs FSA-NetFSA-Net · AFLW2000MAE (degrees): 5.07 -> 4.42Helped
FDN vs FSA-NetFSA-Net · BIWI protocol 2MAE (degrees): 3.60 -> 3.29Helped
FDN vs FSA-Net on BIWI protocol 1 yawFSA-Net · BIWI protocol 1yaw error (degrees): 4.27 -> 4.52Hurt

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy