Researchers have introduced BadmintonGRF, a new multimodal dataset designed for estimating ground reaction forces in badminton without markers. The dataset pairs synchronized multi-view video with data from force plates and motion capture systems. It includes a benchmark task that maps 2D pose to GRF, along with preprocessing code and baseline models to facilitate research in this area. AI
Summary written by gemini-2.5-flash-lite from 1 source. How we write summaries →
IMPACT Provides a new dataset and benchmark for markerless estimation of ground reaction forces, potentially advancing research in sports biomechanics and AI-driven performance analysis.
RANK_REASON This is a research paper describing a new dataset and benchmark for a specific scientific task. [lever_c_demoted from research: ic=1 ai=0.7]