Human Scanpath Prediction in Target-Present Visual Search with Semantic-Foveal Bayesian Attention

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Luzio, João, Bernardino, Alexandre, Moreno, Plinio
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866916948565032960
author Luzio, João
Bernardino, Alexandre
Moreno, Plinio
author_facet Luzio, João
Bernardino, Alexandre
Moreno, Plinio
contents In goal-directed visual tasks, human perception is guided by both top-down and bottom-up cues. At the same time, foveal vision plays a crucial role in directing attention efficiently. Modern research on bio-inspired computational attention models has taken advantage of advancements in deep learning by utilizing human scanpath data to achieve new state-of-the-art performance. In this work, we assess the performance of SemBA-FAST, i.e. Semantic-based Bayesian Attention for Foveal Active visual Search Tasks, a top-down framework designed for predicting human visual attention in target-present visual search. SemBA-FAST integrates deep object detection with a probabilistic semantic fusion mechanism to generate attention maps dynamically, leveraging pre-trained detectors and artificial foveation to update top-down knowledge and improve fixation prediction sequentially. We evaluate SemBA-FAST on the COCO-Search18 benchmark dataset, comparing its performance against other scanpath prediction models. Our methodology achieves fixation sequences that closely match human ground-truth scanpaths. Notably, it surpasses baseline and other top-down approaches and competes, in some cases, with scanpath-informed models. These findings provide valuable insights into the capabilities of semantic-foveal probabilistic frameworks for human-like attention modelling, with implications for real-time cognitive computing and robotics.
format Preprint
id arxiv_https___arxiv_org_abs_2507_18503
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Human Scanpath Prediction in Target-Present Visual Search with Semantic-Foveal Bayesian Attention
Luzio, João
Bernardino, Alexandre
Moreno, Plinio
Computer Vision and Pattern Recognition
In goal-directed visual tasks, human perception is guided by both top-down and bottom-up cues. At the same time, foveal vision plays a crucial role in directing attention efficiently. Modern research on bio-inspired computational attention models has taken advantage of advancements in deep learning by utilizing human scanpath data to achieve new state-of-the-art performance. In this work, we assess the performance of SemBA-FAST, i.e. Semantic-based Bayesian Attention for Foveal Active visual Search Tasks, a top-down framework designed for predicting human visual attention in target-present visual search. SemBA-FAST integrates deep object detection with a probabilistic semantic fusion mechanism to generate attention maps dynamically, leveraging pre-trained detectors and artificial foveation to update top-down knowledge and improve fixation prediction sequentially. We evaluate SemBA-FAST on the COCO-Search18 benchmark dataset, comparing its performance against other scanpath prediction models. Our methodology achieves fixation sequences that closely match human ground-truth scanpaths. Notably, it surpasses baseline and other top-down approaches and competes, in some cases, with scanpath-informed models. These findings provide valuable insights into the capabilities of semantic-foveal probabilistic frameworks for human-like attention modelling, with implications for real-time cognitive computing and robotics.
title Human Scanpath Prediction in Target-Present Visual Search with Semantic-Foveal Bayesian Attention
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2507.18503