Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications

Imke Grabe; Miguel Gonzalez Duque; Jichen Zhu

Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications

Imke Grabe
, Miguel Gonzalez Duque
, Jichen Zhu

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

Abstract

Abstract
With the rise of Generative Adversarial Networks (GANs), AI has increasingly become a partner to human designers in
co-creating cultural artifacts. While generative models have been applied in various creative tasks across disciplines, a
theoretical foundation for understanding human-GAN collaboration is yet to be developed. Drawing from the mixed-initiative
co-creation community, we propose a preliminary framework to analyze co-creative GAN applications. We identify four
primary interaction patterns: Curating, Exploring, Evolving, and Conditioning. The suggested framework enables us to discuss
the affordances and limitations of the different kind of interactions underlying co-creative GAN applications

Originalsprog	Engelsk
Titel	Proceeding of the 3rd Workshop on Human-AI Co-Creation with Generative Models (HAI-GEN ‘22)at ACM IUI Workshops
Publikationsdato	2022
Status	Udgivet - 2022
Begivenhed	Workshop on Human-AI Co-Creation with Generative Models - VIRTUAL, Virtual, Finland Varighed: 21 mar. 2022 → 22 mar. 2022 Konferencens nummer: 3 https://hai-gen.github.io/2022/

Workshop

Workshop	Workshop on Human-AI Co-Creation with Generative Models
Nummer	3
Lokation	VIRTUAL
Land/Område	Finland
By	Virtual
Periode	21/03/2022 → 22/03/2022
Internetadresse	https://hai-gen.github.io/2022/

Emneord

Generative Adversarial Networks
Co-creation
Human-AI Collaboration
Mixed-Initiative Interaction
Interaction Patterns

Adgang til dokumentet

paper9Forlagets udgivne version, 2,01 MBLicens: CC BY

Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications
Grabe, I.
09/08/2023
1 Mediebidrag
Presse/medie

Citationsformater

@inproceedings{23afff6aa7a74ad4b52af2fb9b042d52,

title = "Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications",

abstract = "Abstract With the rise of Generative Adversarial Networks (GANs), AI has increasingly become a partner to human designers in co-creating cultural artifacts. While generative models have been applied in various creative tasks across disciplines, a theoretical foundation for understanding human-GAN collaboration is yet to be developed. Drawing from the mixed-initiative co-creation community, we propose a preliminary framework to analyze co-creative GAN applications. We identify four primary interaction patterns: Curating, Exploring, Evolving, and Conditioning. The suggested framework enables us to discuss the affordances and limitations of the different kind of interactions underlying co-creative GAN applications",

keywords = "Generative Adversarial Networks, Co-creation, Human-AI Collaboration, Mixed-Initiative Interaction, Interaction Patterns, Generative Adversarial Networks, Co-creation, Human-AI Collaboration, Mixed-Initiative Interaction, Interaction Patterns",

author = "Imke Grabe and Duque, \{Miguel Gonzalez\} and Jichen Zhu",

year = "2022",

language = "English",

booktitle = "Proceeding of the 3rd Workshop on Human-AI Co-Creation with Generative Models (HAI-GEN {\textquoteleft}22)at ACM IUI Workshops",

note = "Workshop on Human-AI Co-Creation with Generative Models, HAI-GEN ; Conference date: 21-03-2022 Through 22-03-2022",

url = "https://hai-gen.github.io/2022/",

}

Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications. / Grabe, Imke; Duque, Miguel Gonzalez; Zhu, Jichen.
Proceeding of the 3rd Workshop on Human-AI Co-Creation with Generative Models (HAI-GEN ‘22)at ACM IUI Workshops. 2022.

Publikation: Konference artikel i Proceeding eller bog/rapport kapitel › Konferencebidrag i proceedings › Forskning › peer review

TY - GEN

T1 - Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications

AU - Grabe, Imke

AU - Duque, Miguel Gonzalez

AU - Zhu, Jichen

N1 - Conference code: 3

PY - 2022

Y1 - 2022

N2 - Abstract With the rise of Generative Adversarial Networks (GANs), AI has increasingly become a partner to human designers in co-creating cultural artifacts. While generative models have been applied in various creative tasks across disciplines, a theoretical foundation for understanding human-GAN collaboration is yet to be developed. Drawing from the mixed-initiative co-creation community, we propose a preliminary framework to analyze co-creative GAN applications. We identify four primary interaction patterns: Curating, Exploring, Evolving, and Conditioning. The suggested framework enables us to discuss the affordances and limitations of the different kind of interactions underlying co-creative GAN applications

AB - Abstract With the rise of Generative Adversarial Networks (GANs), AI has increasingly become a partner to human designers in co-creating cultural artifacts. While generative models have been applied in various creative tasks across disciplines, a theoretical foundation for understanding human-GAN collaboration is yet to be developed. Drawing from the mixed-initiative co-creation community, we propose a preliminary framework to analyze co-creative GAN applications. We identify four primary interaction patterns: Curating, Exploring, Evolving, and Conditioning. The suggested framework enables us to discuss the affordances and limitations of the different kind of interactions underlying co-creative GAN applications

KW - Generative Adversarial Networks

KW - Co-creation

KW - Human-AI Collaboration

KW - Mixed-Initiative Interaction

KW - Interaction Patterns

KW - Generative Adversarial Networks

KW - Co-creation

KW - Human-AI Collaboration

KW - Mixed-Initiative Interaction

KW - Interaction Patterns

M3 - Article in proceedings

BT - Proceeding of the 3rd Workshop on Human-AI Co-Creation with Generative Models (HAI-GEN ‘22)at ACM IUI Workshops

T2 - Workshop on Human-AI Co-Creation with Generative Models

Y2 - 21 March 2022 through 22 March 2022

ER -

Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications

Abstract

Workshop

Emneord

Adgang til dokumentet

Fingeraftryk

Presse/Medier

Towards a Framework for Human-AI Interaction Patterns in Co-Creative GAN Applications

Citationsformater