像设计师一样观察：基于设计师线索增强的无监督幻灯片质量评估研究
Seeing Like a Designer Without One: A Study on Unsupervised Slide Quality Assessment via Designer Cue Augmentation
AI总结：
本文提出一种无监督幻灯片质量评估方法，融合七种视觉设计指标与CLIP-ViT嵌入，通过Isolation Forest异常评分实现与人类评分最高0.83的相关性，显著优于主流视觉语言模型，支持实时可扩展的客观反馈。
摘要：
我们提出了一种无监督的幻灯片质量评估流程，该流程将七种受专家启发的视觉设计指标（留白、色彩丰富度、边缘密度、亮度对比度、文本密度、色彩和谐度、布局平衡）与CLIP-ViT嵌入相结合，并使用基于Isolation Forest的异常评分来评估演示幻灯片。该方法在12,000张专业讲座幻灯片上训练，并在六场学术演讲（115张幻灯片）上评估，与人类视觉质量评分实现了最高0.83的Pearson相关性，比领先的视觉语言模型（ChatGPT o4-mini-high、ChatGPT o3、Claude Sonnet 4、Gemini 2.5 Pro）的得分强1.79倍至3.23倍。我们证明了与视觉评分的聚合效度、对演讲者表达评分的区分效度，以及与整体印象的探索性一致性。结果表明，将低级设计线索与多模态嵌入相结合能够高度近似观众对幻灯片质量的感知，从而实现可扩展的实时客观反馈。
英文摘要：
We present an unsupervised slide-quality assessment pipeline that combines seven expert-inspired visual-design metrics (whitespace, colorfulness, edge density, brightness contrast, text density, color harmony, layout balance) with CLIP-ViT embeddings, using Isolation Forest-based anomaly scoring to evaluate presentation slides. Trained on 12k professional lecture slides and evaluated on six academic talks (115 slides), our method achieved Pearson correlations up to 0.83 with human visual-quality ratings-1.79x to 3.23x stronger than scores from leading vision-language models (ChatGPT o4-mini-high, ChatGPT o3, Claude Sonnet 4, Gemini 2.5 Pro). We demonstrate convergent validity with visual ratings, discriminant validity against speaker-delivery scores, and exploratory alignment with overall impressions. Our results show that augmenting low-level design cues with multimodal embeddings closely approximates audience perceptions of slide quality, enabling scalable, objective feedback in real time.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
