用视觉语言模型分析短视频的视听特征，预测观众参与度。
Understanding Virality: A Rubric based Vision-Language Model Framework for Short-Form Edutainment Evaluation
- 通过VLM提取无监督视听特征并聚类为可解释因子
- 模型预测的参与度与真实数据相关性高，优于传统指标
- 适合需要可解释视频评估的教育类短视频研究者
短时视频评估需超越表面质量指标，转向以人为本的多模态推理。现有框架如VideoScore-2虽评估视觉与语义保真度，但未捕捉特定音视频属性对真实用户参与的影响。本文提出一种数据驱动的评估框架：利用视觉语言模型（VLM）提取无监督音视频特征，聚类为可解释因子，并训练回归模型预测短时教育娱乐视频的参与度。我们构建的YouTube Shorts数据集支持系统性分析VLM特征与人类参与行为的关系。实验显示预测值与实际参与度具有强相关性，表明该轻量级、基于特征的评估器相比传统指标（如SSIM、FID）更具可解释性与可扩展性。通过结合多模态特征重要性与以用户为中心的参与信号，本方法推动了鲁棒且可解释的视频理解发展。
原文摘要 · Abstract (English)
Evaluating short-form video content requires moving beyond surface-level quality metrics toward human-aligned, multimodal reasoning. While existing frameworks like VideoScore-2 assess visual and semantic fidelity, they do not capture how specific audiovisual attributes drive real audience engagement. In this work, we propose a data-driven evaluation framework that uses Vision-Language Models (VLMs) to extract unsupervised audiovisual features, clusters them into interpretable factors, and trains a regression-based evaluator to predict engagement on short-form edutainment videos. Our curated YouTube Shorts dataset enables systematic analysis of how VLM-derived features relate to human engagement behavior. Experiments show strong correlations between predicted and actual engagement, demonstrating that our lightweight, feature-based evaluator provides interpretable and scalable assessments compared to traditional metrics (e.g., SSIM, FID). By grounding evaluation in both multimodal feature importance and human-centered engagement signals, our approach advances toward robust and explainable video understanding.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。