{"about":{"site":"https://codewithpapers.app","non_affiliation":"Code with Papers and Syntology are not affiliated with, endorsed by, or sponsored by Papers with Code, Meta, or the pwc-archive mirror.","licence":"CC BY-SA 4.0","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","attribution":"https://codewithpapers.app/attribution","modified":"archive material modified by Syntology; see the attribution page"},"url":"/paper/dance-dance-convolution","title":"Dance Dance Convolution","arxiv_id":"1703.06891","date":"2017-03-20","proceeding":"ICML 2017 8","authors":["Chris Donahue","Zachary C. Lipton","Julian McAuley"],"abstract":"Dance Dance Revolution (DDR) is a popular rhythm-based video game. Players\nperform steps on a dance platform in synchronization with music as directed by\non-screen step charts. While many step charts are available in standardized\npacks, players may grow tired of existing charts, or wish to dance to a song\nfor which no chart exists. We introduce the task of learning to choreograph.\nGiven a raw audio track, the goal is to produce a new step chart. This task\ndecomposes naturally into two subtasks: deciding when to place steps and\ndeciding which steps to select. For the step placement task, we combine\nrecurrent and convolutional neural networks to ingest spectrograms of low-level\naudio features to predict steps, conditioned on chart difficulty. For step\nselection, we present a conditional LSTM generative model that substantially\noutperforms n-gram and fixed-window approaches.","url_abs":"http://arxiv.org/abs/1703.06891v3","url_pdf":"http://arxiv.org/pdf/1703.06891v3.pdf","source":{"archive":"pwc-archive (Hugging Face), CC BY-SA 4.0","snapshot":"2025-07-28","licence_url":"https://creativecommons.org/licenses/by-sa/4.0/legalcode","row_kind":"abstracts"},"code_links":[{"paper_slug":"dance-dance-convolution","repo_url":"https://github.com/chrisdonahue/ddc","is_official":1,"mentioned_in_paper":1,"mentioned_in_github":1,"framework":"tf","reach":null}],"tasks":[{"task_slug":"rhythm","task_name":"Rhythm"}],"methods":[{"method_slug":"lstm","method_name":"LSTM"},{"method_slug":"sigmoid-activation","method_name":"Sigmoid Activation"},{"method_slug":"tanh-activation","method_name":"Tanh Activation"}],"datasets_introduced":[{"slug":"fraxtil","name":"Fraxtil","full_name":null},{"slug":"itg","name":"ITG","full_name":"In The Groove"}],"methods_introduced":[],"results":[],"syntology":{"syntology_url":null,"atlas_url":null,"mcp":null,"developers":"https://syntology.ai/developers"},"arxiv_metadata":null,"syntology_extracted_results":null}