Can Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment

A regression framework built on open-source Vision-Language Models reached a Spearman correlation of 0.67 with a four-model configuration when scoring Olympic diving videos from the AQA-7 benchmark, according to an arXiv paper (2609.19354v1). Standalone VLMs achieved Spearman correlations below 0.32, and the paper reports that textual reasoning features consistently outperformed raw numerical sub-scores. The authors position VLMs as assistive tools for explainable, semi-automated sports performance evaluation, with code published on GitHub.

arXiv:2609.19354v1 Announce Type: new Abstract: Automated action quality assessment AQA in Olympic sports remains a challenging task due to the complexity of human motion and the subjectivity inherent in expert judging. This work evaluates the capability of open-source Vision-Language Models VLMs to perform zero-shot action quality assessment on Olympic diving videos using the AQA-7 benchmark dataset. In this regard, a regression-based framework is pro-posed to leverage both the semantic reasoning and phase-level sub-scores generated by the VLMs, combining TF-IDF vectorization, dimensionality reduction, and ensemble learning to predict final competition scores. Experimental results show that standalone VLMs achieve moderate Spearman correlations below 0.32, while the proposed ensemble regression framework substantially improves performance in the reported evaluation, reaching a Spearman correlation of 0.67 with a four-model configuration. Textual reasoning features con-sistently outperformed raw numerical sub-scores, highlighting the richness of VLM-generated explanations for action quality analysis. These findings suggest that VLMs hold strong potential as assistive tools for explainable and semi-automated sports performance evaluation. The code is publicly available on GitHub https://github.com/hvelesaca/olympic diving judge vlm