ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues
作者机构:Department of Computer ScienceHong Kong Baptist UniversityHong Kong 999077China Department of Computer Science and EngineeringThe Hong Kong University of Science and EngineeringHong Kong 999077China
出 版 物:《Machine Intelligence Research》 (机器智能研究(英文版))
年 卷 期:2024年第21卷第4期
页 面:771-781页
核心收录:
学科分类:0809[工学-电子科学与技术(可授工学、理学学位)] 08[工学] 0811[工学-控制科学与工程] 0812[工学-计算机科学与技术(可授工学、理学学位)]
基 金:supported by the Theme-based Research Scheme Research Grants Council of Hong Kong China(T45-205/21-N)
主 题:Generative model cross-modality learning normalizing flow tempo synchronization style transfer.
摘 要:To generate dance that temporally and aesthetically matches the music is a challenging problem in three ***,the generated motion should be beats-aligned to the local musical ***,the global aesthetic style should be matched between motion and *** third,the generated motion should be diverse and *** address these challenges,we propose ReChoreoNet,which re-choreographs high-quality dance motion for a given piece of music.A data-driven learning strategy is proposed to efficiently correlate the temporal connections between music and motion in a progressively learned cross-modality embedding *** beats-aligned content motion will be subsequently used as autoregressive context and control signal to control a normalizing-flow model,which transfers the style of a prototype motion to the final generated *** addition,we present an aesthetically labelled music-dance repertoire(MDR)for both efficient learning of the cross-modality embedding,and understanding of the aesthetic connections between music and *** demonstrate that our repertoire-based framework is robustly extensible in both content and *** quantitative and qualitative experiments have been carried out to validate the efficiency of our proposed model.