Research map / Image generation / Autoregressive and latent generation
AID-AppEAL: Automatic Image Dataset and Algorithm for Content Appeal Enhancement and Assessment Labeling
Sherry X. Chen, Yaron Vaxman, Elad Ben Baruch, David Asulin, Aviad Moreshet, Misha Sra, Pradeep Sen
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 changed | Where | Measured | Effect |
|---|---|---|---|
| compare content appeal labels against image aesthetics (IAA) predictions | Appeal labels vs DIAA, MPADA, NIMA · Food dataset | PLCC: 0.168, 0.005, 0.01 | No clear effect |
| compare content appeal labels against IAA predictions | Appeal labels vs DIAA, MPADA, NIMA · Room dataset | PLCC: -0.123, -0.012, -0.147 | No clear effect |
| apply appeal enhancement to food images | AID-AppEAL enhancer · Food user study (enhanced vs original) | responses preferring enhanced (%): 76.53% preferred enhanced | Improved |
| apply appeal enhancement to room images | AID-AppEAL enhancer · Room user study (enhanced vs original) | responses preferring enhanced (%): 82.74% preferred enhanced | Improved |
| use denoising strength 0.3 or 0.45 instead of 0.6 (ablation) | AID-AppEAL enhancer · enhancement qualitative | content appeal improvement | Hurt |
| use denoising strength 0.75 or 0.9 instead of 0.6 (ablation) | AID-AppEAL enhancer · enhancement qualitative | visual coherence | Hurt |
| add appeal heatmap mask to enhancement (ablation) | AID-AppEAL enhancer · enhancement qualitative | preservation of appealing regions | Improved |
| add depth-map ControlNet guidance to enhancement (ablation) | AID-AppEAL enhancer · enhancement qualitative | structure preservation | Improved |
| AID-AppEAL enhancer vs InstructPix2Pix, Null-text Inversion, pix2pix-zero, Text2LIVE | AID-AppEAL enhancer · food and room enhancement (qualitative) | visual comparison | Improved |
Closest papers by meaning
- ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding (CVPR 2026 · similarity 0.88)
- A3: Towards Advertising Aesthetic Assessment (CVPR 2026 · similarity 0.86)
- AI-generated Image Quality Assessment in Visual Communication (AAAI 2025 · similarity 0.86)
- Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning (AAAI 2025 · similarity 0.85)
- Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment (AAAI 2026 · similarity 0.85)
- ELTA: An Enhancer against Long-Tail for Aesthetics-oriented Models (ICML 2024 · similarity 0.85)
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.
