CoDancers: Music-Driven Coherent Group Dance Generation with Choreographic Unit
Open Access
- 30 May 2024
- conference paper
- Published by Association for Computing Machinery (ACM)
- p. 675-683
Abstract
Dance and music are intimately interconnected, with group dance being a crucial part of dance artistry. Consequently, Music-Driven Group Dance Generation has been a fundamental and challenging task in various fields like education, art, and sports. However, existing methods fail to fully explore group dance coherence. Thus, we propose CoDancers, a novel and efficient retrieval-based music-driven group dance generation framework. CoDancers improves performance by decomposing group dance coherence into individual movement coherence and group interaction coherence for specialized design, incorporating a Spatial-Temporal Group Dance Blender block, a Acoustic-Semantic Music Miner block, and a Stereotype-Reducing Dance Generator block. Experimental results on the public dataset demonstrate the superiority of our method over existing baselines, achieving state-of-the-art performance. The code is available at https://github.com/XulongT/CoDancers.Keywords
Funding Information
- National Natural Science Foundation of China (62072459, 62172421)
This publication has 27 references indexed in Scilit:
- TM2D: Bimodality Driven 3D Dance Generation via Music-Text Integration2023
- Music-Driven Group Choreography2023
- Bailando: 3D Dance Generation by Actor-Critic GPT with Choreographic Memory2022
- Cross Modal Retrieval with Querybank Normalisation2022
- Genre-Conditioned Long-Term 3D Dance Generation Driven by Music2022
- AI Choreographer: Music Conditioned 3D Dance Generation with AIST++2021
- Learning to dance: A graph convolutional adversarial network to generate realistic dance motions from audioComputers & Graphics, 2021
- Convolutional Sequence Generation for Skeleton-Based Action Synthesis2019
- Focal Loss for Dense Object Detection2017
- Gradient-based learning applied to document recognitionProceedings of the IEEE, 1998