An Eye Gaze Model for Controlling the Display of Social Status in Believable Virtual Humans

Michael Nixon, Steve DiPaola, Ulysses Bernardet

Research output: Chapter in Book/Report/Conference proceedingConference contribution

Abstract

Abstract—Designing highly believable characters remains a
major concern within digital games. Matching a chosen personality and other dramatic qualities to displayed behavior is
an important part of improving overall believability. Gaze is
a critical component of social exchanges and serves to make
characters engaging or aloof, as well as to establish character’s
role in a conversation.
In this paper, we investigate the communication of status
related social signals by means of a virtual human’s eye gaze.
We constructed a cross-domain verbal-conceptual computational
model of gaze for virtual humans to facilitate the display of social
status. We describe the validation of the model’s parameters,
including the length of eye contact and gazes, movement velocity,
equilibrium response, and head and body posture. In a first set
of studies, conducted on Amazon Mechanical Turk using prerecorded video clips of animated characters, we found statistically
significant differences in how the characters’ status was rated
based on the variation in social status.
In a second step based on these empirical findings, we designed
an interactive system that incorporates dynamic eye tracking and
spoken dialog, along with real-time control of a virtual character.
We evaluated the model using a presential, interactive scenario of
a simulated hiring interview. Corroborating our previous finding,
the interactive study yielded significant differences in perception
of status were found (p = .046). Thus, we believe status is an
important aspect of dramatic believability, and accordingly, this
paper presents our social eye gaze model for realistic procedurally
animated characters and shows its efficacy.
Index Terms—procedural animation, believable characters,
virtual human, gaze, social interaction, nonverbal behaviour,
video games
Original languageEnglish
Title of host publication2018 IEEE Conference on Computational Intelligence and Games (CIG)
PublisherIEEE
Number of pages8
ISBN (Electronic)978-1-5386-4359-4
ISBN (Print)978-1-5386-4360-0
DOIs
Publication statusPublished - 15 Oct 2018
Event2018 IEEE Conference on Computational Intelligence and Games (CIG) - Maastricht, Netherlands
Duration: 14 Aug 201817 Aug 2018

Publication series

Name2018 IEEE Conference on Computational Intelligence and Games (CIG)
PublisherIEEE
ISSN (Print)2325-4270
ISSN (Electronic)2325-4289

Conference

Conference2018 IEEE Conference on Computational Intelligence and Games (CIG)
CountryNetherlands
CityMaastricht
Period14/08/1817/08/18

Fingerprint

Display devices
Real time control
Animation
Communication

Bibliographical note

© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

Cite this

Nixon, M., DiPaola, S., & Bernardet, U. (2018). An Eye Gaze Model for Controlling the Display of Social Status in Believable Virtual Humans. In 2018 IEEE Conference on Computational Intelligence and Games (CIG) (2018 IEEE Conference on Computational Intelligence and Games (CIG)). IEEE. https://doi.org/10.1109/CIG.2018.8490373
Nixon, Michael ; DiPaola, Steve ; Bernardet, Ulysses. / An Eye Gaze Model for Controlling the Display of Social Status in Believable Virtual Humans. 2018 IEEE Conference on Computational Intelligence and Games (CIG). IEEE, 2018. (2018 IEEE Conference on Computational Intelligence and Games (CIG)).
@inproceedings{af7b9210ee804248be89c3e5fdec2654,
title = "An Eye Gaze Model for Controlling the Display of Social Status in Believable Virtual Humans",
abstract = "Abstract—Designing highly believable characters remains amajor concern within digital games. Matching a chosen personality and other dramatic qualities to displayed behavior isan important part of improving overall believability. Gaze isa critical component of social exchanges and serves to makecharacters engaging or aloof, as well as to establish character’srole in a conversation.In this paper, we investigate the communication of statusrelated social signals by means of a virtual human’s eye gaze.We constructed a cross-domain verbal-conceptual computationalmodel of gaze for virtual humans to facilitate the display of socialstatus. We describe the validation of the model’s parameters,including the length of eye contact and gazes, movement velocity,equilibrium response, and head and body posture. In a first setof studies, conducted on Amazon Mechanical Turk using prerecorded video clips of animated characters, we found statisticallysignificant differences in how the characters’ status was ratedbased on the variation in social status.In a second step based on these empirical findings, we designedan interactive system that incorporates dynamic eye tracking andspoken dialog, along with real-time control of a virtual character.We evaluated the model using a presential, interactive scenario ofa simulated hiring interview. Corroborating our previous finding,the interactive study yielded significant differences in perceptionof status were found (p = .046). Thus, we believe status is animportant aspect of dramatic believability, and accordingly, thispaper presents our social eye gaze model for realistic procedurallyanimated characters and shows its efficacy.Index Terms—procedural animation, believable characters,virtual human, gaze, social interaction, nonverbal behaviour,video games",
author = "Michael Nixon and Steve DiPaola and Ulysses Bernardet",
note = "{\circledC} 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.",
year = "2018",
month = "10",
day = "15",
doi = "10.1109/CIG.2018.8490373",
language = "English",
isbn = "978-1-5386-4360-0",
series = "2018 IEEE Conference on Computational Intelligence and Games (CIG)",
publisher = "IEEE",
booktitle = "2018 IEEE Conference on Computational Intelligence and Games (CIG)",
address = "United States",

}

Nixon, M, DiPaola, S & Bernardet, U 2018, An Eye Gaze Model for Controlling the Display of Social Status in Believable Virtual Humans. in 2018 IEEE Conference on Computational Intelligence and Games (CIG). 2018 IEEE Conference on Computational Intelligence and Games (CIG), IEEE, 2018 IEEE Conference on Computational Intelligence and Games (CIG), Maastricht, Netherlands, 14/08/18. https://doi.org/10.1109/CIG.2018.8490373

An Eye Gaze Model for Controlling the Display of Social Status in Believable Virtual Humans. / Nixon, Michael; DiPaola, Steve; Bernardet, Ulysses.

2018 IEEE Conference on Computational Intelligence and Games (CIG). IEEE, 2018. (2018 IEEE Conference on Computational Intelligence and Games (CIG)).

Research output: Chapter in Book/Report/Conference proceedingConference contribution

TY - GEN

T1 - An Eye Gaze Model for Controlling the Display of Social Status in Believable Virtual Humans

AU - Nixon, Michael

AU - DiPaola, Steve

AU - Bernardet, Ulysses

N1 - © 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works.

PY - 2018/10/15

Y1 - 2018/10/15

N2 - Abstract—Designing highly believable characters remains amajor concern within digital games. Matching a chosen personality and other dramatic qualities to displayed behavior isan important part of improving overall believability. Gaze isa critical component of social exchanges and serves to makecharacters engaging or aloof, as well as to establish character’srole in a conversation.In this paper, we investigate the communication of statusrelated social signals by means of a virtual human’s eye gaze.We constructed a cross-domain verbal-conceptual computationalmodel of gaze for virtual humans to facilitate the display of socialstatus. We describe the validation of the model’s parameters,including the length of eye contact and gazes, movement velocity,equilibrium response, and head and body posture. In a first setof studies, conducted on Amazon Mechanical Turk using prerecorded video clips of animated characters, we found statisticallysignificant differences in how the characters’ status was ratedbased on the variation in social status.In a second step based on these empirical findings, we designedan interactive system that incorporates dynamic eye tracking andspoken dialog, along with real-time control of a virtual character.We evaluated the model using a presential, interactive scenario ofa simulated hiring interview. Corroborating our previous finding,the interactive study yielded significant differences in perceptionof status were found (p = .046). Thus, we believe status is animportant aspect of dramatic believability, and accordingly, thispaper presents our social eye gaze model for realistic procedurallyanimated characters and shows its efficacy.Index Terms—procedural animation, believable characters,virtual human, gaze, social interaction, nonverbal behaviour,video games

AB - Abstract—Designing highly believable characters remains amajor concern within digital games. Matching a chosen personality and other dramatic qualities to displayed behavior isan important part of improving overall believability. Gaze isa critical component of social exchanges and serves to makecharacters engaging or aloof, as well as to establish character’srole in a conversation.In this paper, we investigate the communication of statusrelated social signals by means of a virtual human’s eye gaze.We constructed a cross-domain verbal-conceptual computationalmodel of gaze for virtual humans to facilitate the display of socialstatus. We describe the validation of the model’s parameters,including the length of eye contact and gazes, movement velocity,equilibrium response, and head and body posture. In a first setof studies, conducted on Amazon Mechanical Turk using prerecorded video clips of animated characters, we found statisticallysignificant differences in how the characters’ status was ratedbased on the variation in social status.In a second step based on these empirical findings, we designedan interactive system that incorporates dynamic eye tracking andspoken dialog, along with real-time control of a virtual character.We evaluated the model using a presential, interactive scenario ofa simulated hiring interview. Corroborating our previous finding,the interactive study yielded significant differences in perceptionof status were found (p = .046). Thus, we believe status is animportant aspect of dramatic believability, and accordingly, thispaper presents our social eye gaze model for realistic procedurallyanimated characters and shows its efficacy.Index Terms—procedural animation, believable characters,virtual human, gaze, social interaction, nonverbal behaviour,video games

UR - http://www.ieee-cig.org/

UR - https://ieeexplore.ieee.org/document/8490373

U2 - 10.1109/CIG.2018.8490373

DO - 10.1109/CIG.2018.8490373

M3 - Conference contribution

SN - 978-1-5386-4360-0

T3 - 2018 IEEE Conference on Computational Intelligence and Games (CIG)

BT - 2018 IEEE Conference on Computational Intelligence and Games (CIG)

PB - IEEE

ER -

Nixon M, DiPaola S, Bernardet U. An Eye Gaze Model for Controlling the Display of Social Status in Believable Virtual Humans. In 2018 IEEE Conference on Computational Intelligence and Games (CIG). IEEE. 2018. (2018 IEEE Conference on Computational Intelligence and Games (CIG)). https://doi.org/10.1109/CIG.2018.8490373