Open Peer Review. Open Publishing. Open Access. Open Discussion. Open Directory. Open Recommendations. Open API. Open Source.
Dance Dance Convolution
Chris Donahue, Zachary C. Lipton, Julian McAuley
Feb 17, 2017 (modified: Mar 15, 2017)ICLR 2017 workshop submissionreaders: everyone
Abstract:Dance Dance Revolution (DDR) is a popular rhythm-based video game. Players perform steps on a dance platform in synchronization with music as directed by on-screen step charts. While many step charts are available in standardized packs, users may grow tired of existing charts, or wish to dance to a song for which no chart exists. We introduce the task of learning to choreograph. Given a raw audio track, the goal is to produce a new step chart. This task decomposes naturally into two subtasks: deciding when to place steps and deciding which steps to select. We demonstrate deep learning solutions for both tasks and establish strong benchmarks for future work.
TL;DR:Introduces the task of automating Dance Dance Revolution choreography; offers a standardized dataset for investigation and a slew of deep learning baselines
Keywords:Deep learning, Supervised Learning, Applications, Games
Enter your feedback below and we'll get back to you as soon as possible.