A novel end-to-end dual-camera system for eye gaze synchrony assessment in face-to-face interaction
(2024) In Attention, Perception & Psychophysics 86(7). p.2221-2230- Abstract
Quantification of face-to-face interaction can provide highly relevant information in cognitive and psychological science research. Current commercial glint-dependent solutions suffer from several disadvantages and limitations when applied in face-to-face interaction, including data loss, parallax errors, the inconvenience and distracting effect of wearables, and/or the need for several cameras to capture each person. Here we present a novel eye-tracking solution, consisting of a dual-camera system used in conjunction with an individually optimized deep learning approach that aims to overcome some of these limitations. Our data show that this system can accurately classify gaze location within different areas of the face of two... (More)
Quantification of face-to-face interaction can provide highly relevant information in cognitive and psychological science research. Current commercial glint-dependent solutions suffer from several disadvantages and limitations when applied in face-to-face interaction, including data loss, parallax errors, the inconvenience and distracting effect of wearables, and/or the need for several cameras to capture each person. Here we present a novel eye-tracking solution, consisting of a dual-camera system used in conjunction with an individually optimized deep learning approach that aims to overcome some of these limitations. Our data show that this system can accurately classify gaze location within different areas of the face of two interlocutors, and capture subtle differences in interpersonal gaze synchrony between two individuals during a (semi-)naturalistic face-to-face interaction.
(Less)
- author
- Thorsson, Max LU ; Galazka, Martyna A ; Åsberg Johnels, Jakob and Hadjikhani, Nouchine
- publishing date
- 2024-10
- type
- Contribution to journal
- publication status
- published
- keywords
- Humans, Fixation, Ocular, Eye-Tracking Technology, Female, Male, Adult, Young Adult, Deep Learning, Facial Recognition/physiology, Interpersonal Relations, Social Interaction
- in
- Attention, Perception & Psychophysics
- volume
- 86
- issue
- 7
- pages
- 2221 - 2230
- publisher
- Springer
- external identifiers
-
- pmid:37099200
- scopus:85153613294
- ISSN
- 1943-3921
- DOI
- 10.3758/s13414-023-02679-4
- language
- English
- LU publication?
- no
- additional info
- © 2023. The Author(s).
- id
- b1b0bef1-552b-4445-9a9c-48131b896920
- date added to LUP
- 2024-11-21 22:14:46
- date last changed
- 2025-07-04 23:42:15
@article{b1b0bef1-552b-4445-9a9c-48131b896920,
abstract = {{<p>Quantification of face-to-face interaction can provide highly relevant information in cognitive and psychological science research. Current commercial glint-dependent solutions suffer from several disadvantages and limitations when applied in face-to-face interaction, including data loss, parallax errors, the inconvenience and distracting effect of wearables, and/or the need for several cameras to capture each person. Here we present a novel eye-tracking solution, consisting of a dual-camera system used in conjunction with an individually optimized deep learning approach that aims to overcome some of these limitations. Our data show that this system can accurately classify gaze location within different areas of the face of two interlocutors, and capture subtle differences in interpersonal gaze synchrony between two individuals during a (semi-)naturalistic face-to-face interaction.</p>}},
author = {{Thorsson, Max and Galazka, Martyna A and Åsberg Johnels, Jakob and Hadjikhani, Nouchine}},
issn = {{1943-3921}},
keywords = {{Humans; Fixation, Ocular; Eye-Tracking Technology; Female; Male; Adult; Young Adult; Deep Learning; Facial Recognition/physiology; Interpersonal Relations; Social Interaction}},
language = {{eng}},
number = {{7}},
pages = {{2221--2230}},
publisher = {{Springer}},
series = {{Attention, Perception & Psychophysics}},
title = {{A novel end-to-end dual-camera system for eye gaze synchrony assessment in face-to-face interaction}},
url = {{http://dx.doi.org/10.3758/s13414-023-02679-4}},
doi = {{10.3758/s13414-023-02679-4}},
volume = {{86}},
year = {{2024}},
}