Automatic Annotation of Movements in Dance
摘要
The article outlines research into the application of machine learning and deep learning in the field of dance. The implementation of automated systems for motion recognition and assessment is discussed, looking at various techniques such as pose estimation and human action recognition (HAR). It summarises existing research results and highlights the challenges and potentials using an application example from the #vortanz research project funded by the Federal Ministry of Education and Research (BMBF) from 2021 to 2024 (cf. Jenett et al., #vortanz—Automated pre-annotation in digital university dance education. https://vortanz.ai/#/de , 2021–2024).