How good was my shot? Quantifying Player Skill Level in Table Tennis
🤖 AI Summary
This work proposes a novel approach to quantifying the latent skill levels of table tennis players from observable stroke behaviors. By constructing a conditional generative model that jointly encodes tactical strokes and their contextual match situations into a unified latent space, the method captures both skill proficiency and playing style. This is the first framework to enable co-modeling of tactical actions and situational context, yielding a latent representation that effectively discriminates between different skill tiers and technical styles. Experiments on 3D reconstructions of professional matches demonstrate that, when paired with a simple ranking network, the learned representation achieves high accuracy in predicting both relative and absolute skill levels.
Application Category
📝 Abstract
Gauging an individual's skill level is crucial, as it inherently shapes their behavior. Quantifying skill, however, is challenging because it is latent to the observed actions. To explore skill understanding in human behavior, we focus on dyadic sports -- specifically table tennis -- where skill manifests not just in complex movements, but in the subtle nuances of execution conditioned on game context. Our key idea is to learn a generative model of each player's tactical racket strokes and jointly embed them in a common latent space that encodes individual characteristics, including those pertaining to skill levels. By training these player models on a large-scale dataset of 3D-reconstructed professional matches and conditioning them on comprehensive game context -- including player positioning and opponent behaviors -- the models capture individual tactical identities within their latent space. We probe this learned player space and find that it reflects distinct play styles and attributes that collectively represent skill. By training a simple relative ranking network on these embeddings, we demonstrate that both relative and absolute skill predictions can be achieved. These results demonstrate that the learned player space effectively quantifies skill levels, providing a foundation for automated skill assessment in complex, interactive behaviors.
Problem
Research questions and friction points this paper is trying to address.
skill quantification
table tennis
player skill level
latent skill
dyadic sports
Innovation
Methods, ideas, or system contributions that make the work stand out.
generative modeling
latent skill embedding
table tennis
tactical behavior
skill quantification
🔎 Similar Papers
No similar papers found.
