Metraipolis › archive › dc_6bb8b41e98e1

Can Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment — arXiv:2609.19354

Source
arXiv (en)
Original
https://arxiv.org/abs/2609.19354
License (as archived)
CC0-1.0
Archived
2026-10-10T03:22:54.216Z
SHA-256 of the archived text
c1713ce44f1893aed2bc37544d92997391ace6fbfbdea57f853fb4b346ba11a9
Stable URL of this page
https://metraipolis.com/documento/dc_6bb8b41e98e1

How to cite

Can Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment — arXiv:2609.19354 — arXiv (en), https://arxiv.org/abs/2609.19354 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_6bb8b41e98e1 (Metraipolis archive dc_6bb8b41e98e1, sha256 c1713ce44f1893aed2bc37544d92997391ace6fbfbdea57f853fb4b346ba11a9)
BibTeX
@misc{dc6bb8b41e98e1,
  title = {Can Vision-Language Models Judge Olympic Diving? From Reasoning to Scores in Zero-Shot Action Quality Assessment — arXiv:2609.19354},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2609.19354},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_6bb8b41e98e1; sha256 c1713ce44f1893aed2bc37544d92997391ace6fbfbdea57f853fb4b346ba11a9},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.19354. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

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 this https URL diving judge vlm

Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-18 in cs.AI).
Categorie arXiv: Computer Vision and Pattern Recognition (cs.CV) ; Artificial Intelligence (cs.AI); Machine Learning (cs.LG).
Pagina del lavoro: https://arxiv.org/abs/2609.19354 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito).
Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina.
Letto il 2026-10-10T03:04:13.799Z dalla pagina https://arxiv.org/catchup/cs.AI/2026-09-18?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).