Workshop: Workshop on Machine Learning for Creativity and Design
Intentional Dance Choreography with Semi-Supervised Recurrent VAEs
Mathilde Papillon · Mariel Pettee · Nina Miolane
We summarize the model and results of PirouNet, a semi-supervised recurrent variational autoencoder. Given a set of dance sequences of which 1% include qualitative choreographic annotations, PirouNet conditionally generates dance sequences in the style and intention of the choreographer.