Saved in:
Bibliographic Details
Main Authors: Šikić, Franko, Vršnak, Donik, Lončarić, Sven
Format: Preprint
Published: 2024
Subjects:
Online Access:https://arxiv.org/abs/2410.17082
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866929554351718400
author Šikić, Franko
Vršnak, Donik
Lončarić, Sven
author_facet Šikić, Franko
Vršnak, Donik
Lončarić, Sven
contents In this paper, we present a survey of deep learning-based methods for the regression of gaze direction vector from head and eye images. We describe in detail numerous published methods with a focus on the input data, architecture of the model, and loss function used to supervise the model. Additionally, we present a list of datasets that can be used to train and evaluate gaze direction regression methods. Furthermore, we noticed that the results reported in the literature are often not comparable one to another due to differences in the validation or even test subsets used. To address this problem, we re-evaluated several methods on the commonly used in-the-wild Gaze360 dataset using the same validation setup. The experimental results show that the latest methods, although claiming state-of-the-art results, significantly underperform compared with some older methods. Finally, we show that the temporal models outperform the static models under static test conditions.
format Preprint
id arxiv_https___arxiv_org_abs_2410_17082
institution arXiv
publishDate 2024
record_format arxiv
spellingShingle A Survey on Deep Learning-based Gaze Direction Regression: Searching for the State-of-the-art
Šikić, Franko
Vršnak, Donik
Lončarić, Sven
Computer Vision and Pattern Recognition
In this paper, we present a survey of deep learning-based methods for the regression of gaze direction vector from head and eye images. We describe in detail numerous published methods with a focus on the input data, architecture of the model, and loss function used to supervise the model. Additionally, we present a list of datasets that can be used to train and evaluate gaze direction regression methods. Furthermore, we noticed that the results reported in the literature are often not comparable one to another due to differences in the validation or even test subsets used. To address this problem, we re-evaluated several methods on the commonly used in-the-wild Gaze360 dataset using the same validation setup. The experimental results show that the latest methods, although claiming state-of-the-art results, significantly underperform compared with some older methods. Finally, we show that the temporal models outperform the static models under static test conditions.
title A Survey on Deep Learning-based Gaze Direction Regression: Searching for the State-of-the-art
topic Computer Vision and Pattern Recognition
url https://arxiv.org/abs/2410.17082