AI Paper Atlas

Research map / 3D vision / Human pose estimation

Towards Unbiased Label Distribution Learning for Facial Pose Estimation Using Anisotropic Spherical Gaussian

Zhiwen Cao, Dongfang Liu, Qifan Wang, Yingjie Chen

ECCV 2022 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 36 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (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
use rotation matrix instead of Euler anglesdirect regression, ResNet-18 · AFLW2000 (train 300W-LP)MAE: 5.28 -> 4.31Improved
use rotation matrix instead of quaterniondirect regression, ResNet-18 · AFLW2000 (train 300W-LP)MAE: 4.66 -> 4.31Improved
use rotation matrix instead of Lie algebradirect regression, ResNet-18 · BIWI 30% (train BIWI 70%)MAE: 3.26 -> 3.08Improved
add spherical Gaussian label distribution learning to direct regression (ablation)rotation matrix model · AFLW2000 (train 300W-LP)MAE: 4.31 -> 3.79Improved
use anisotropic instead of isotropic spherical Gaussian (ablation)ASG distribution · AFLW2000 (train 300W-LP)MAE: 3.79 -> 3.64Improved
use anisotropic instead of isotropic spherical Gaussian (ablation)ASG distribution · BIWI 30% (train BIWI 70%)MAE: 2.93 -> 2.77Improved
use adaptive parameters instead of fixed lambda=1, eta=1 (ablation)ASG distribution · AFLW2000 (train 300W-LP)MAE: 3.79 -> 3.64Improved
use adaptive parameters instead of fixed lambda=5, eta=5 (ablation)ASG distribution · BIWI full (train 300W-LP)MAE: 3.97 -> 3.61Improved
use adaptive parameters instead of fixed lambda=1, eta=5 (ablation)ASG distribution · AFLW2000 (train 300W-LP)MAE: 3.92 -> 3.64Improved
add regression loss L_reg to classification loss (ablation)ASG distribution · AFLW2000 (train 300W-LP)MAE: 3.67 -> 3.64Improved
add classification loss L_cls to regression loss (ablation)ASG distribution · AFLW2000 (train 300W-LP)MAE: 4.31 -> 3.64Improved
add ASG label distribution with ResNet-18 vs img2poseASG (ours) · BIWI full (train 300W-LP)MAE: 3.79 -> 3.61Improved

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 2 of 2 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

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