ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues

作     者：Ho Yin Au Jie Chen Junkun Jiang Yike Guo Ho Yin Au;Jie Chen;Junkun Jiang;Yike Guo

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.