SALYPATH: A Deep-Based Architecture for visual attention prediction

TL;DR

SALYPATH is a deep learning architecture designed to predict visual scanpaths by leveraging saliency features, demonstrating improved accuracy over existing models in benchmark datasets.

Contribution

The paper introduces SALYPATH, an end-to-end deep model that predicts visual scanpaths using saliency features, advancing the state-of-the-art in attention prediction.

Findings

Outperforms existing models on benchmark datasets

Effectively predicts scanpaths using saliency features

Validated on two well-known datasets

Abstract

Human vision is naturally more attracted by some regions within their field of view than others. This intrinsic selectivity mechanism, so-called visual attention, is influenced by both high- and low-level factors; such as the global environment (illumination, background texture, etc.), stimulus characteristics (color, intensity, orientation, etc.), and some prior visual information. Visual attention is useful for many computer vision applications such as image compression, recognition, and captioning. In this paper, we propose an end-to-end deep-based method, so-called SALYPATH (SALiencY and scanPATH), that efficiently predicts the scanpath of an image through features of a saliency model. The idea is predict the scanpath by exploiting the capacity of a deep-based model to predict the saliency. The proposed method was evaluated through 2 well-known datasets. The results obtained showed the relevance of the proposed framework comparing to state-of-the-art models.