SkillMoV: Mixture-of-View Routing with Prototype-Conditioned Gating for Unified Multi-View Proficiency Estimation (opens in new tab)

Estimating human proficiency from video is a key challenge for automated skill assessment, with applications in sports coaching, music pedagogy, surgical training, and workplace learning. Existing approaches often focus on individual scenarios or rely on shared multi-view aggregation, limiting their ability to adapt to heterogeneous camera viewpoints and activity domains. We introduce SkillMoV, a unified, parameter-efficient framework for multi-...