Comparison of Eye-gaze Detection using CNN and Vision Transformer

被引：0

作者：

Niikura D. ^{[1
]}

Abe K. ^{[1
]}

机构：

[1] Graduate School of System Design and Technology, Tokyo Denki University, 5, Senjuasahicho, Adachi-ku, Tokyo

来源：

IEEJ Transactions on Electronics, Information and Systems | 2024年 / 144卷 / 07期

关键词：

convolutional neural network; eye-gaze detection; eye-gaze input; input interface; Vision Transformer;

D O I：

10.1541/ieejeiss.144.683

中图分类号：

TN911 [通信理论];

学科分类号：

081002 ;

摘要：

We propose an eye-gaze input system that utilizes a laptop PC and its inner camera. This system can discriminate the user's eye-gaze direction by using Convolutional Neural Network (CNN) or Vision Transformer (ViT). In this paper, we present the results of a comparison of the newly created eye-gaze direction discrimination model of ViT and the past model created by a CNN. We evaluated the accuracy of discrimination models created by ViT and CNN through the experiments. As a result, the ViT model has higher accuracy than the CNN model in discriminating the center direction. © 2024 The Institute of Electrical Engineers of Japan.

引用

页码：683 / 684

页数：1

共 50 条

[41] Local Selective Vision Transformer for Depth Estimation Using a Compound Eye Camera [J].

Oh, Wooseok ;

Yoo, Hwiyeon ;

Ha, Taeoh ;

Oh, Songhwai .

PATTERN RECOGNITION LETTERS, 2023, 167 :82-89

[42] An Intrusion Detection System Using Vision Transformer for Representation Learning [J].

Ban, Xinbo ;

Liu, Ao ;

He, Long ;

Gong, Li .

FRONTIERS IN CYBER SECURITY, FCS 2023, 2024, 1992 :531-544

[43] Explainable Anomaly Detection Using Vision Transformer Based SVDD [J].

Baek, Ji-Won ;

Chung, Kyungyong .

CMC-COMPUTERS MATERIALS & CONTINUA, 2023, 74 (03) :6573-6586

[44] Development of an Eye-Gaze Input System With High Speed and Accuracy through Target Prediction Based on Homing Eye Movements [J].

Murata, Atsuo ;

Doi, Toshihisa ;

Kageyama, Kazushi ;

Karwowski, Waldemar .

IEEE ACCESS, 2021, 9 :22688-22697

[45] A vision transformer based CNN for underwater image enhancement ViTClarityNet [J].

Fathy, Mohamed E. ;

Mohamed, Samer A. ;

Awad, Mohammed I. ;

Abd El Munim, Hossam E. .

SCIENTIFIC REPORTS, 2025, 15 (01)

[46] MoviNet: A novel network for cross-modal map extraction by vision transformer and CNN [J].

Chen, Zheng ;

Fang, Junhua ;

Chao, Pingfu ;

Zhao, Pengpeng ;

Xu, Jiajie ;

Zhao, Lei .

KNOWLEDGE-BASED SYSTEMS, 2023, 278

[47] Pupil Center Detection for Infrared Irradiation Eye Image Using CNN [J].

Kondo, Nagisa ;

Chinsatit, Warapon ;

Saitoh, Takeshi .

2017 56TH ANNUAL CONFERENCE OF THE SOCIETY OF INSTRUMENT AND CONTROL ENGINEERS OF JAPAN (SICE), 2017, :100-105

[48] Diabetic Retinopathy Classification using Vision Transformer [J].

Mutawa, A. M. ;

Sruthi, Sai .

2022 6TH EUROPEAN CONFERENCE ON ELECTRICAL ENGINEERING & COMPUTER SCIENCE, ELECS, 2022, :25-30

[49] Anterior Cruciate Ligament (ACL) Tear Detection Using Hybrid CNN Transformer [J].

Sriram, Suthir ;

Singh, Deependra K. ;

Sairam, D. V. ;

Vijayaraj, Nivethitha ;

Murugan, Thangavel .

IEEE ACCESS, 2025, 13 :48019-48032

[50] COVID-Transformer: Interpretable COVID-19 Detection Using Vision Transformer for Healthcare [J].

Shome, Debaditya ;

Kar, T. ;

Mohanty, Sachi Nandan ;

Tiwari, Prayag ;

Muhammad, Khan ;

AlTameem, Abdullah ;

Zhang, Yazhou ;

Saudagar, Abdul Khader Jilani .

INTERNATIONAL JOURNAL OF ENVIRONMENTAL RESEARCH AND PUBLIC HEALTH, 2021, 18 (21)

← 1 2 3 4 5 →