Dance to the Music! Stick Figures Groove With New ‘seq2seq’ Model & Curriculum Learning | Synced
Researchers from Fudan University and Microsoft have proposed a novel seq2seq architecture that generates dance sequences for music clips running a minute or longer.
Source: Synced | AI Technology & Industry Review
Researchers from Fudan University and Microsoft have proposed a novel seq2seq architecture that generates dance sequences for music clips running a minute or longer.