About
Contact & Profiles
A5095842805
Research Areas
- Human Pose and Action Recognition
- Music and Audio Processing
- Human Motion and Animation
Beijing University of Posts and Telecommunications
2023
In this paper, we propose a method that takes the audio of solo pipa performance as input and utilizes pre-trained models other instruments to enhance pipa's 3D skeleton motion performance. This approach aims address limited availability training data. The key idea is believe all exhibit similar trends in their large limbs while playing. Therefore, can utilize videos playing pre-train capture limbs. Subsequently, fine-tune model using solo, thereby addressing issue data for solo. We...
10.1145/3638884.3638978
article
EN
2023-12-14
Coming Soon ...