Expressive Movement Generation with Machine Learning

The MoDa 2.0 web-based frontend is available at http://movehub.omid.al/. We also provide access to the training datasets that we collected as a part of my PhD through MoDa:

• Affect-Expressive Movements Dataset
• GrooveDB Dataset

A prototype of Mova is available here. With this prototype you can choose a sample movement, add features, and visualize the data. You can also watch a tutorial video here.

The source code for PyMO is available at PyMO's Github page.

• Training Data:Affect-Expressive Movements Dataset
• Output Videos
• Source Code

• Training Data: Affect-Expressive Movements Dataset
• Sample Outputs
• Video of Realtime Movement Generation
• Source Code

The complementary materials for our submission to the Workshop on Machine Learning for Creativity at the 23rd ACM SIGKDD Conference on Knowledge Discovery and Data Mining. Halifax, Nova Scotia - Canada. 2017

• Training Data: GrooveDB
• Sample Outputs: https://omid.al/groovenet-material-ml4c
• Source Code

• Training Data: GrooveDB
• Sample Outputs
• Demo of GrooveNet Real-Time Engine
• List of Machine Learning Experiments
• Source Code