2026-10-12T20:25:20Z https://www.scidb.cn/oai

10.57760/sciencedb.jcst.00012 2025-09-17T17:32:11Z

2025-09-17 ConductorMotion100 doi:10.57760/sciencedb.jcst.00012 en This repository is the official implementation of “Self-Supervised Music-Motion Synchronization Learning for Music-Driven Conducting Motion Generation”, by Fan Liu, Delong Chen, Ruizhi Zhou, Sai Yang, and Feng Xu. This repository also provide the access to the ConductorMotion100 dataset, which consists of 100 hours of orchestral conductor motions and aligned music Mel spectrogram.The above figure gives a high-level illustration of the proposed two-stage approach. The contrastive learning and generative learning stage are bridged by transferring learned music and motion encoders, as noted in dotted lines. Our approach can generate plausible, diverse, and music-synchronized conducting motion. self-supervised learning; generative adversarial network; human motion generation Fan Liu De-Long Chen Rui-Zhi Zhou Sai Yang Feng Xu PUBLIC https://opendatacommons.org/licenses/by/1-0/ dataset http://www.doi.org/10.1007/s11390-022-2030-z Science Data Bank