GANs and Poses: An Interactive Generative Music Installation Controlled by Dance Moves

Hamid Eghbal-Zadeh; Richard Vogl; Gerhard Widmer; Peter Knees

GANs and Poses: An Interactive Generative Music Installation Controlled by Dance Moves

Hamid Eghbal-Zadeh, Richard Vogl, Gerhard Widmer, Peter Knees

Institute of Computational Perception

Research output: Chapter in Book/Report/Conference proceeding › Conference proceedings › peer-review

Abstract

GANs and Poses is an interactive multi-media installation using human poses to control artificial neural networks generating parts for a music arrangement. To provide incentive for interaction, a game-style UI rewards the audience with audio-visual feedback, which in turn drives the progress through the musical arrangement. This work uses a variety of artificial neural networks to (i) detect persons and their body posture, (ii) classify dance moves, and (iii) generate drum as well as melody patterns.

Original language	English
Title of host publication	Proceedings of ISMIR2018 Interactive Machine-Learning for Music (IML4M) @Exhibition
Number of pages	5
Publication status	Published - Sept 2018

Fields of science

202002 Audiovisual media
102 Computer Sciences
102001 Artificial intelligence
102003 Image processing
102015 Information systems

JKU Focus areas

Computation in Informatics and Mathematics
Engineering and Natural Sciences (in general)

Cite this

@inproceedings{e9e13676b3a14c2cbc7150b4eaf6157c,

title = "GANs and Poses: An Interactive Generative Music Installation Controlled by Dance Moves",

abstract = "GANs and Poses is an interactive multi-media installation using human poses to control artificial neural networks generating parts for a music arrangement. To provide incentive for interaction, a game-style UI rewards the audience with audio-visual feedback, which in turn drives the progress through the musical arrangement. This work uses a variety of artificial neural networks to (i) detect persons and their body posture, (ii) classify dance moves, and (iii) generate drum as well as melody patterns.",

author = "Hamid Eghbal-Zadeh and Richard Vogl and Gerhard Widmer and Peter Knees",

year = "2018",

month = sep,

language = "English",

booktitle = "Proceedings of ISMIR2018 Interactive Machine-Learning for Music (IML4M) @Exhibition",

}

TY - GEN

T1 - GANs and Poses: An Interactive Generative Music Installation Controlled by Dance Moves

AU - Eghbal-Zadeh, Hamid

AU - Vogl, Richard

AU - Widmer, Gerhard

AU - Knees, Peter

PY - 2018/9

Y1 - 2018/9

N2 - GANs and Poses is an interactive multi-media installation using human poses to control artificial neural networks generating parts for a music arrangement. To provide incentive for interaction, a game-style UI rewards the audience with audio-visual feedback, which in turn drives the progress through the musical arrangement. This work uses a variety of artificial neural networks to (i) detect persons and their body posture, (ii) classify dance moves, and (iii) generate drum as well as melody patterns.

AB - GANs and Poses is an interactive multi-media installation using human poses to control artificial neural networks generating parts for a music arrangement. To provide incentive for interaction, a game-style UI rewards the audience with audio-visual feedback, which in turn drives the progress through the musical arrangement. This work uses a variety of artificial neural networks to (i) detect persons and their body posture, (ii) classify dance moves, and (iii) generate drum as well as melody patterns.

UR - http://ismir2018.ircam.fr/doc/pdfs2/vogl.pdf

M3 - Conference proceedings

BT - Proceedings of ISMIR2018 Interactive Machine-Learning for Music (IML4M) @Exhibition

ER -

GANs and Poses: An Interactive Generative Music Installation Controlled by Dance Moves

Abstract

Fields of science

JKU Focus areas

Other files and links

Strategic FExFE Project on Deep Learning

Cite this

GANs and Poses: An Interactive Generative Music Installation Controlled by Dance Moves

Abstract

Fields of science

JKU Focus areas

Other files and links

Projects

Strategic FExFE Project on Deep Learning

Cite this