Salvato in:
| Autori principali: | , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2025
|
| Soggetti: | |
| Accesso online: | https://arxiv.org/abs/2508.19289 |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911124458307584 |
|---|---|
| author | Inui, Tai Oh, Steven Kuan, Magdeline |
| author_facet | Inui, Tai Oh, Steven Kuan, Magdeline |
| contents | 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. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2508_19289 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Seeing Like a Designer Without One: A Study on Unsupervised Slide Quality Assessment via Designer Cue Augmentation Inui, Tai Oh, Steven Kuan, Magdeline Computer Vision and Pattern Recognition Artificial Intelligence 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. |
| title | Seeing Like a Designer Without One: A Study on Unsupervised Slide Quality Assessment via Designer Cue Augmentation |
| topic | Computer Vision and Pattern Recognition Artificial Intelligence |
| url | https://arxiv.org/abs/2508.19289 |