AI Paper Atlas

Research map / Vision-language and multimodal / Human and embodied modeling

Understanding Aesthetics with Language: A Photo Critique Dataset for Aesthetic Assessment

Daniel Vera Nieto, Luigi Celona, Clara Fernandez Labrador

NeurIPS 2022 · Vision-language and multimodal › Human and embodied modeling · approach: Multimodal and affective interaction modeling · 7 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
Use ViT-L/16 pre-trained on ImageNet-21k instead of Hosu et al. methodAestheticViT · AVA aesthetic scoreSRCC: 0.756 -> 0.793Improved
Use ViT-L/16 21k instead of Chen et al. for classificationAestheticViT · AVAaccuracy (%): 83.20 -> 82.85Hurt
Use 32x32 patches (ViT-B/32) instead of 16x16 (ViT-B/16) (ablation)ViT-B · AVASRCC: 0.759 -> 0.446Hurt
Scale ViT-B/16 to ViT-L/16 (ImageNet-21k) (ablation)ViT · AVASRCC: 0.773 -> 0.793Improved
Pre-train ViT-B/16 on ImageNet-21k instead of ImageNet (ablation)ViT-B/16 · AVASRCC: 0.759 -> 0.773Improved
Fine-tune full AestheticViT instead of linear probe on sentiment score (ablation)ViT · RPCDSRCC: 0.172 -> 0.250Improved
Fine-tune full AestheticViT instead of linear probe on sentiment score (ablation)ViT · AVASRCC: 0.570 -> 0.544Hurt
Fine-tune full AestheticViT instead of linear probe on sentiment score (ablation)ViT · AVAaccuracy (%): 76.43 -> 90.54Improved
Replace NIMA with AestheticViT for sentiment scoreNIMA · RPCDSRCC: 0.120 -> 0.250Improved
Train on RPCD vs PCCD for aesthetic captioningBLIP · captioningBleu4: 0.011 -> 0.017Improved
Train on RPCD vs PCCD for aesthetic captioningBLIP · captioningCIDEr: 0.049 -> 0.048No clear effect

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy