Building a large-scale dataset for audio-conditioned dance motion synthesis

• 主要作者: Wu, Jinyi
• 其他作者: Chen Change Loy
• 格式: Thesis-Master by Research
• 語言: English
• 出版: Nanyang Technological University 2022
• 主題: Engineering::Computer science and engineering::Computing methodologies::Image processing and computer vision
• 在線閱讀: https://hdl.handle.net/10356/160410

Generative models for audio-conditioned dance motion synthesis map music features to dance movements. Models are trained with a few assumptions such as strong music-dance correlation, controlled motion data and relatively simple poses. These characteristics are found in all existing datasets for dan...