Saved in:
Bibliographic Details
Main Authors: Perdigão, Luís Maria, Costa, Miguel, Santiago, Carlos, Marques, Manuel
Format: Preprint
Published: 2026
Subjects:
Online Access:https://arxiv.org/abs/2605.24040
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866913157754126336
author Perdigão, Luís Maria
Costa, Miguel
Santiago, Carlos
Marques, Manuel
author_facet Perdigão, Luís Maria
Costa, Miguel
Santiago, Carlos
Marques, Manuel
contents Cycling delivers significant public-health and environmental benefits, yet its uptake in cities is often limited by perceived safety. When street environments appear unsafe, individuals are less likely to cycle, making perception a key barrier to adoption. Recent work has shown that pairwise comparisons of street-view images provide a scalable way to learn subjective safety judgments. However, existing approaches do not explicitly model human visual attention, which plays a central role in how humans perceive safety. We propose an Eye-Tracking-Guided Perceived Cycling Safety framework (EG-PCS) that integrates gaze data into a pairwise learning pipeline based on vision transformers. By supervising the model's attention mechanism with eye-tracking signals, we encourage alignment between learned attention maps and human fixation patterns. Experiments show that gaze-guided models achieve similar ranking performance compared to state-of-the-art approaches while producing attention maps that more accurately reflect human visual attention behavior. Our results demonstrate that incorporating eye-tracking information enhances both predictive accuracy and interpretability in perception-based urban analytics.
format Preprint
id arxiv_https___arxiv_org_abs_2605_24040
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Learning to See Like Humans: Gaze-Aligned Cycling Safety Prediction
Perdigão, Luís Maria
Costa, Miguel
Santiago, Carlos
Marques, Manuel
Computer Vision and Pattern Recognition
Cycling delivers significant public-health and environmental benefits, yet its uptake in cities is often limited by perceived safety. When street environments appear unsafe, individuals are less likely to cycle, making perception a key barrier to adoption. Recent work has shown that pairwise comparisons of street-view images provide a scalable way to learn subjective safety judgments. However, existing approaches do not explicitly model human visual attention, which plays a central role in how humans perceive safety. We propose an Eye-Tracking-Guided Perceived Cycling Safety framework (EG-PCS) that integrates gaze data into a pairwise learning pipeline based on vision transformers. By supervising the model's attention mechanism with eye-tracking signals, we encourage alignment between learned attention maps and human fixation patterns. Experiments show that gaze-guided models achieve similar ranking performance compared to state-of-the-art approaches while producing attention maps that more accurately reflect human visual attention behavior. Our results demonstrate that incorporating eye-tracking information enhances both predictive accuracy and interpretability in perception-based urban analytics.
title Learning to See Like Humans: Gaze-Aligned Cycling Safety Prediction
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2605.24040