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

doi:10.1007/s11633-023-1478-9

CASIA OpenIR > 学术期刊 > Machine Intelligence Research

	ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues
	Ho Yin Au 1; Jie Chen 1; Junkun Jiang 1; Yike Guo 2
发表期刊	Machine Intelligence Research
ISSN	2731-538X
	2024
卷号	21 期号:4 页码:771-781
摘要	To generate dance that temporally and aesthetically matches the music is a challenging problem in three aspects. First, the generated motion should be beats-aligned to the local musical features. Second, the global aesthetic style should be matched between motion and music. And third, the generated motion should be diverse and non-self-repeating. To 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 space. The 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 dance. In 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 motion. We demonstrate that our repertoire-based framework is robustly extensible in both content and style. Both quantitative and qualitative experiments have been carried out to validate the efficiency of our proposed model.
关键词	Generative model cross-modality learning normalizing flow tempo synchronization style transfer
DOI	10.1007/s11633-023-1478-9
引用统计
文献类型	期刊论文
条目标识符	http://ir.ia.ac.cn/handle/173211/58571
专题	学术期刊_Machine Intelligence Research
作者单位	1.Department of Computer Science, Hong Kong Baptist University, Hong Kong 999077, China 2.Department of Computer Science and Engineering, The Hong Kong University of Science and Engineering, Hong Kong 999077, China
推荐引用方式 GB/T 7714	Ho Yin Au,Jie Chen,Junkun Jiang,et al. ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues[J]. Machine Intelligence Research,2024,21(4):771-781.
APA	Ho Yin Au,Jie Chen,Junkun Jiang,&Yike Guo.(2024).ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues.Machine Intelligence Research,21(4),771-781.
MLA	Ho Yin Au,et al."ReChoreoNet: Repertoire-based Dance Re-choreography with Music-conditioned Temporal and Style Clues".Machine Intelligence Research 21.4(2024):771-781.

条目包含的文件
文件名称/大小	文献类型	版本类型	开放类型	使用许可
MIR-2023-06-101.pdf（2161KB）	期刊论文	出版稿	开放获取	CC BY-NC-SA	浏览