AI Paper Atlas

Research map / Label-efficient and robust learning / Recognition and long-tail

Neural Photofit: Gaze-Based Mental Image Reconstruction

Florian Strohm, Ekta Sood, Sven Mayer, Philipp Müller, Mihai Bâce, Andreas Bulling

ICCV 2021 · Label-efficient and robust learning › Recognition and long-tail · approach: Margin-based face recognition losses · 13 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 one-second fixation maps (30) instead of five-second maps (6) (ablation)Neural Photofit · Synthetic FaceMaker faces, test setaccuracy (All): 56.8% -> 61.9%Improved
use one-second fixation maps (30) instead of five-second maps (6) (ablation)Neural Photofit · Synthetic FaceMaker faces, test setMASD (All): 25.15 -> 23.37Improved
use multiple fixation maps over time instead of one 30 s map (ablation)Neural Photofit · Synthetic FaceMaker faces, test setaccuracy (All): 57.9% -> 61.9%Improved
use multiple fixation maps over time instead of one 30 s map (ablation)Neural Photofit · Synthetic FaceMaker faces, test setMASD (All): 23.96 -> 23.37Improved
use multiple fixation maps over time instead of one 30 s map (ablation)Neural Photofit · Synthetic FaceMaker faces, test set (nose features)accuracy: 54.7% -> 45.3%Hurt
add attention mechanism to scoring network (ablation)Neural Photofit · Synthetic FaceMaker faces, test setaccuracy (All): 52.2% -> 61.9%Improved
add attention mechanism to scoring network (ablation)Neural Photofit · Synthetic FaceMaker faces, test setMASD (All): 26.35 -> 23.37Improved
add attention mechanism to scoring network (ablation)Neural Photofit · Synthetic FaceMaker faces, test set (eyes features)accuracy: 56.8% -> 77.0%Improved
use gaze-based scoring network instead of mean of auxiliary facesNeural Photofit · Synthetic FaceMaker faces, test setMASD (All): 30.26 -> 23.37Improved
use gaze-based scoring network instead of random feature selectionNeural Photofit · Synthetic FaceMaker faces, test setaccuracy (All): 16.7% -> 61.9%Improved
use Neural Photofit reconstruction instead of baseline in human preferenceNeural Photofit · User studypreference rate: 50% -> 79%Improved

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