A Simple and efficient deep Scanpath Prediction

TL;DR

This paper demonstrates that simple fully convolutional deep learning models can effectively predict visual scanpaths, achieving competitive or superior results compared to more complex architectures across multiple datasets.

Contribution

It introduces a straightforward fully convolutional approach for scanpath prediction, showing that simplicity can match or outperform complex models.

Findings

Competitive results on multiple datasets

Certain backbone architectures outperform others

Simple models can surpass complex architectures in accuracy

Abstract

Visual scanpath is the sequence of fixation points that the human gaze travels while observing an image, and its prediction helps in modeling the visual attention of an image. To this end several models were proposed in the literature using complex deep learning architectures and frameworks. Here, we explore the efficiency of using common deep learning architectures, in a simple fully convolutional regressive manner. We experiment how well these models can predict the scanpaths on 2 datasets. We compare with other models using different metrics and show competitive results that sometimes surpass previous complex architectures. We also compare the different leveraged backbone architectures based on their performances on the experiment to deduce which ones are the most suitable for the task.