AI Paper Atlas

Research map / 3D vision / Human pose estimation

Hierarchical Attention-Based Age Estimation and Bias Analysis

Shakediel Hiba, Yosi Keller

TPAMI 2023 · 3D vision › Human pose estimation · approach: Heatmap and coordinate pose encoding · 28 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
add Transformer-Encoder augmentation aggregation (ablation)hierarchical age estimator (VGG16) · CACD (SE protocol)MAE: 5.80 -> 5.35Improved
use 10 augmentations aggregated by Transformer-Encoder instead of single augmentation (ablation)age estimator · MORPH II (SE protocol)MAE: 2.63 -> 2.53Improved
use Transformer-Encoder instead of average-pool for 10 augmentations (ablation)age estimator · MORPH II (SE protocol)MAE: 2.58 -> 2.53Improved
increase augmentations from 10 to 15 (ablation)age estimator · MORPH II (SE protocol)MAE: 2.53 -> 2.60Hurt
use 8 encoder layers and 8 heads instead of 4 and 4 (ablation)age estimator · MORPH II (SE protocol)MAE: 2.53 -> 2.57Hurt
use 2 encoder layers and 2 heads instead of 4 and 4 (ablation)age estimator · MORPH II (SE protocol)MAE: 2.53 -> 2.55Hurt
use age bin size 1 instead of 10 (ablation)age estimator · MORPH II (SE protocol)MAE: 2.56 -> 2.53Improved
use age bin size 1 instead of 5 (ablation)age estimator · MORPH II (SE protocol)MAE: 2.56 -> 2.53Improved
add RandAugment learned augmentationsage estimator · MORPH IIMAENo clear effect
train on gender-balanced MORPH II subsetage estimator VGG16 · MORPH II (SE protocol, gender-balanced)MAE: decreased by ~0.95 years for men, ~0.35 years for womenHurt
add SAE (5 augmentations, Transformer-Encoder 1 layer 2 heads) to shallow networkShallow CNN · CIFAR-10accuracy: 56% -> 70%Improved
add SAE with 2 encoder layers to VGG16VGG16 · CIFAR-10accuracy: 87 -> 92Improved

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