The paper investigates whether open‑source Vision‑Language Models (VLMs) can perform zero‑shot action quality assessment (AQA) on Olympic diving videos. Using the AQA‑7 benchmark, the authors propose a regression framework that combines VLM‑generated semantic reasoning, phase‑level sub‑scores, TF‑IDF vectorization, dimensionality reduction, and ensemble learning to predict final competition scores. While individual VLMs achieve moderate Spearman correlations (<0.32), the ensemble approach boosts performance to 0.67, demonstrating that VLM‑derived textual reasoning features are more informative than raw numerical sub‑scores for AQA. whyItMatters":"The study shows that VLMs can serve as explainable, semi‑automated tools for evaluating sports performance, potentially aiding expert judging in complex, subjective Olympic events."
arXiv:2609.28049v1 Announce Type: cross Abstract: Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as ev...
Video understanding is usually benchmarked on curated, single-actor, or professionally filmed clips, and a strong score there is routinely read as evidence a model is robust enough for deployment. Ama...
arXiv:2606. 28570v1 Announce Type: cross Abstract: Athlete assessment is a critical process for tracking physical progress and identifying elite talent.
arXiv:2608. 08736v1 Announce Type: new Abstract: Fitness Action Quality Assessment (AQA) is important for intelligent sports training, yet the capabilities of Multimodal Large Language Models (MLLMs) in this setting remain underexplored.
arXiv:2609.36628v1 Announce Type: new Abstract: Vision-Language Models (VLMs) can generate rich video captions, yet often misidentify which person performs an action or which limb is involved, partic...
VisionQ is a new benchmark for qualitative analysis in computer vision that evaluates vision‑language models (VLMs) on criterion‑conditioned visual discrimination. It is built from over 1,800 peer‑reviewed comparison figures in CVPR and ICCV papers, linking each image crop to author‑stated visual claims through 3,911 hand‑annotated data points. The benchmark includes a 51‑leaf taxonomy of visual criteria, a protocol that hides method identities and reports accuracy per criterion, and a DPO‑tuned Gemma‑4‑E4B judge that improves accuracy on a held‑out test set.
Reliable evaluation of human motion understanding is fundamental to advancing embodied AI, robotics, and animation. However, existing benchmarks suffer from coarse semantic granularity, undifferentiated difficulty, limited annotation quality, and pervasive answer ambiguity, leaving them unable to diagnose where current models fail.
arXiv:2607. 14616v1 Announce Type: new Abstract: Vision--language models have become increasingly capable of interpreting visual scenes, but it remains unclear whether they can use information to make strategically effective decisions.
arXiv:2608. 04589v1 Announce Type: cross Abstract: EgoCross is a cross-domain egocentric video question answering benchmark designed to evaluate whether multimodal large language models can generalize beyond common daily-life scenarios.
arXiv:2608. 07932v2 Announce Type: replace Abstract: Sports video analysis is crucial for athletic analytics and broadcasting enhancement.
arXiv:2603. 10652v3 Announce Type: replace-cross Abstract: In real-world deployment, vision-language models often encounter disturbances such as weather, occlusion, and camera motion.
WorldReward introduces a vision‑language model–based reward system for camera‑conditioned world models, combining action consistency and visual quality evaluation. It processes paired videos by splitting them into action‑aligned chunks, structuring visual evidence, and aggregating decisions through voting. The model is trained on a large, reasoning‑augmented preference dataset and outperforms GPT‑5.5 on a human‑annotated benchmark, improving both action execution and visual quality when applied to RL post‑training.