Aarhus University Seal / Aarhus Universitets segl

crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

Standard

crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity. / Rafner, Janet Frances; Hjorth, Hermes Arthur; Risi, Sebastian; Philipsen, Lotte; Dumas, Charles; Biskjaer, Michael Mose; Noy, Lior; Tylén, Kristian; Bergenholtz, Carsten; Lynch, Jesse John; Zana, Blanka; Sherson, Jacob.

CHI PLAY 2020 - Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play. New York : Association for Computing Machinery, 2020. p. 340-344.

Research output: Contribution to book/anthology/report/proceedingArticle in proceedingsResearchpeer-review

Harvard

Rafner, JF, Hjorth, HA, Risi, S, Philipsen, L, Dumas, C, Biskjaer, MM, Noy, L, Tylén, K, Bergenholtz, C, Lynch, JJ, Zana, B & Sherson, J 2020, crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity. in CHI PLAY 2020 - Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play. Association for Computing Machinery, New York, pp. 340-344. https://doi.org/10.1145/3383668.3419907

APA

Rafner, J. F., Hjorth, H. A., Risi, S., Philipsen, L., Dumas, C., Biskjaer, M. M., Noy, L., Tylén, K., Bergenholtz, C., Lynch, J. J., Zana, B., & Sherson, J. (2020). crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity. In CHI PLAY 2020 - Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play (pp. 340-344). Association for Computing Machinery. https://doi.org/10.1145/3383668.3419907

CBE

Rafner JF, Hjorth HA, Risi S, Philipsen L, Dumas C, Biskjaer MM, Noy L, Tylén K, Bergenholtz C, Lynch JJ, Zana B, Sherson J. 2020. crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity. In CHI PLAY 2020 - Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play. New York: Association for Computing Machinery. pp. 340-344. https://doi.org/10.1145/3383668.3419907

MLA

Rafner, Janet Frances et al. "crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity". CHI PLAY 2020 - Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play. New York: Association for Computing Machinery. 2020, 340-344. https://doi.org/10.1145/3383668.3419907

Vancouver

Rafner JF, Hjorth HA, Risi S, Philipsen L, Dumas C, Biskjaer MM et al. crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity. In CHI PLAY 2020 - Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play. New York: Association for Computing Machinery. 2020. p. 340-344 https://doi.org/10.1145/3383668.3419907

Author

Rafner, Janet Frances ; Hjorth, Hermes Arthur ; Risi, Sebastian ; Philipsen, Lotte ; Dumas, Charles ; Biskjaer, Michael Mose ; Noy, Lior ; Tylén, Kristian ; Bergenholtz, Carsten ; Lynch, Jesse John ; Zana, Blanka ; Sherson, Jacob. / crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity. CHI PLAY 2020 - Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play. New York : Association for Computing Machinery, 2020. pp. 340-344

Bibtex

@inproceedings{c622b533728545ed9d0d1567b2f820c3,
title = "crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity",
abstract = "We present a pilot study on crea.blender, a novel co-creative game designed for large-scale, systematic assessment of distinct con- structs of human creativity. Co-creative systems are systems in which humans and computers (often with Machine Learning) col- laborate on a creative task. This human-computer collaboration raises questions about the relevance and level of human creativity and involvement in the process. We expand on, and explore aspects of these questions in this pilot study. We observe participants play through three different play modes in crea.blender, each aligned with established creativity assessment methods. In these modes, players “blend” existing images into new images under varying constraints. Our study indicates that crea.blender provides a playful experience, affords players a sense of control over the interface, and elicits different types of player behavior, supporting further study of the tool for use in a scalable, playful, creativity assessment.",
keywords = "Co-creative systems, divergent thinking, convergent thinking, GAN",
author = "Rafner, {Janet Frances} and Hjorth, {Hermes Arthur} and Sebastian Risi and Lotte Philipsen and Charles Dumas and Biskjaer, {Michael Mose} and Lior Noy and Kristian Tyl{\'e}n and Carsten Bergenholtz and Lynch, {Jesse John} and Blanka Zana and Jacob Sherson",
year = "2020",
month = nov,
day = "2",
doi = "10.1145/3383668.3419907",
language = "English",
pages = "340--344",
booktitle = "CHI PLAY 2020 - Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play",
publisher = "Association for Computing Machinery",
address = "United States",

}

RIS

TY - GEN

T1 - crea.blender: A Neural Network-Based Image Generation Game to Assess Creativity

AU - Rafner, Janet Frances

AU - Hjorth, Hermes Arthur

AU - Risi, Sebastian

AU - Philipsen, Lotte

AU - Dumas, Charles

AU - Biskjaer, Michael Mose

AU - Noy, Lior

AU - Tylén, Kristian

AU - Bergenholtz, Carsten

AU - Lynch, Jesse John

AU - Zana, Blanka

AU - Sherson, Jacob

PY - 2020/11/2

Y1 - 2020/11/2

N2 - We present a pilot study on crea.blender, a novel co-creative game designed for large-scale, systematic assessment of distinct con- structs of human creativity. Co-creative systems are systems in which humans and computers (often with Machine Learning) col- laborate on a creative task. This human-computer collaboration raises questions about the relevance and level of human creativity and involvement in the process. We expand on, and explore aspects of these questions in this pilot study. We observe participants play through three different play modes in crea.blender, each aligned with established creativity assessment methods. In these modes, players “blend” existing images into new images under varying constraints. Our study indicates that crea.blender provides a playful experience, affords players a sense of control over the interface, and elicits different types of player behavior, supporting further study of the tool for use in a scalable, playful, creativity assessment.

AB - We present a pilot study on crea.blender, a novel co-creative game designed for large-scale, systematic assessment of distinct con- structs of human creativity. Co-creative systems are systems in which humans and computers (often with Machine Learning) col- laborate on a creative task. This human-computer collaboration raises questions about the relevance and level of human creativity and involvement in the process. We expand on, and explore aspects of these questions in this pilot study. We observe participants play through three different play modes in crea.blender, each aligned with established creativity assessment methods. In these modes, players “blend” existing images into new images under varying constraints. Our study indicates that crea.blender provides a playful experience, affords players a sense of control over the interface, and elicits different types of player behavior, supporting further study of the tool for use in a scalable, playful, creativity assessment.

KW - Co-creative systems

KW - divergent thinking

KW - convergent thinking

KW - GAN

U2 - 10.1145/3383668.3419907

DO - 10.1145/3383668.3419907

M3 - Article in proceedings

SP - 340

EP - 344

BT - CHI PLAY 2020 - Extended Abstracts of the 2020 Annual Symposium on Computer-Human Interaction in Play

PB - Association for Computing Machinery

CY - New York

ER -