Research Article
Next Level Choreography: Applying a Transformer Network to Generate Improvised Dance Motions
@INPROCEEDINGS{10.1007/978-3-031-28993-4_36, author={Zahra Asadi and Jonas Moons and Stefan Leijnen}, title={Next Level Choreography: Applying a Transformer Network to Generate Improvised Dance Motions}, proceedings={ArtsIT, Interactivity and Game Creation. 11th EAI International Conference, ArtsIT 2022, Faro, Portugal, November 21-22, 2022, Proceedings}, proceedings_a={ARTSIT}, year={2023}, month={4}, keywords={Transformer Network Improvisation Dance Human Motion Music}, doi={10.1007/978-3-031-28993-4_36} }- Zahra Asadi
Jonas Moons
Stefan Leijnen
Year: 2023
Next Level Choreography: Applying a Transformer Network to Generate Improvised Dance Motions
ARTSIT
Springer
DOI: 10.1007/978-3-031-28993-4_36
Abstract
With recent developments in artificial intelligence, it is possible to generate human motion using deep learning. In this paper, a transformer deep learning algorithm is investigated to generate improvisation dance motions for the Another Kind of Blue (AKOB) data set. AKOB is an innovative dance group, located in The Hague, Netherlands, with a specialization in combining modern dance and technology. For this study, AKOB recorded various dance movements with different pieces of music using a motion capture system. This data is used to train a transformer network and generate sequences of improvisational dance using seed motions and musical input. The produced movements are visualized and compared to the ground truth of human motions to examine their quality. The results show possible human positions, but the speed of motions is a lot compared to the music. Also, sometimes the transition from one position to another is not feasible.
