ConductorMotion100 大规模音乐-指挥动作数据集

we collect and construct a large scale conducting motion dataset. Based on advanced object detection and pose estimation techniques, we efficiently extract conducting motion data from online video sources. The constructed dataset, named ConductorMotion100, has 100 hours of conducting motion data and aligned Mel spectrograms. Its scale significantly exceeds that of existing conducting motion datasets.

Fan Liu, Delong Chen (本科生), Ruizhi Zhou (本科生), Sai Yang, Feng Xu. Self-Supervised Music-Motion Synchronization Learning for Music-Driven Conducting Motion Generation. Journal of Computer Science and Technology (SCI, CCF-B类期刊).


AIM Group
Artificial Intelligence of Multi-modality Group