When Dance Video Archives Challenge Computer Vision
This work addresses the problem of improving pose estimation accuracy for dance videos, which is incremental as it applies known methods to a specific domain.
The authors tackled the challenge of human body pose estimation using dance video archives, proposing a new 3D pose estimation pipeline that combines existing techniques with novel methods for dance analysis, and they conducted extensive experiments to evaluate data parameters, with results made publicly available.
The accuracy and efficiency of human body pose estimation depend on the quality of the data to be processed and of the particularities of these data. To demonstrate how dance videos can challenge pose estimation techniques, we proposed a new 3D human body pose estimation pipeline which combined up-to-date techniques and methods that had not been yet used in dance analysis. Second, we performed tests and extensive experimentations from dance video archives, and used visual analytic tools to evaluate the impact of several data parameters on human body pose. Our results are publicly available for research at https://www.couleur.org/articles/arXiv-1-2025/