Research map / Image generation / Autoregressive and latent generation
Personalized Image Aesthetics Assessment With Rich Attributes
Check your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 |
|---|---|---|---|
| Add personality traits as conditional information | ResNet-50 PIAA · PARA 100-shot | SROCC: 0.6952\pm 0.0014 -> 0.7046\pm 0.0015 | Helped |
| Add personality traits as conditional information | ResNet-50 PIAA · PARA 100-shot | PLCC: 0.7429\pm 0.0012 -> 0.7509\pm 0.0010 | Helped |
| Add personality traits as conditional information | ResNet-50 PIAA · PARA 10-shot | SROCC: 0.6811\pm 0.0015 -> 0.6912\pm 0.0009 | Helped |
| Add personality traits as conditional information | ResNet-50 PIAA · PARA without finetune | PLCC: 0.7295\pm 0.0014 -> 0.7380\pm 0.0007 | Helped |
| Use photographic experience rather than personality traits as the condition (ablation) | Conditional ResNet-50 PIAA · PARA 100-shot | SROCC: 0.7046\pm 0.0015 -> 0.6982\pm 0.0010 | Hurt |
| Use artistic experience rather than personality traits as the condition (ablation) | Conditional ResNet-50 PIAA · PARA 100-shot | SROCC: 0.7046\pm 0.0015 -> 0.6976\pm 0.0012 | Hurt |
| Fine-tune with 100 personal examples instead of no personal examples (ablation) | Unconditional ResNet-50 PIAA · PARA | SROCC: 0.6808\pm 0.0015 -> 0.6952\pm 0.0014 | Helped |
| Fine-tune with 10 personal examples instead of no personal examples (ablation) | Unconditional ResNet-50 PIAA · PARA | SROCC: 0.6808\pm 0.0015 -> 0.6811\pm 0.0015 | No clear effect |
| Use Swin-TF Small rather than ResNet-50 as the unconditional GIAA backbone (ablation) | Unconditional GIAA · PARA GIAA test | PLCC: 0.9208 -> 0.9355 | Helped |
Closest papers by meaning
- Rethinking Personalized Aesthetics Assessment: Employing Physique Aesthetics Assessment as An Exemplification (CVPR 2025 · similarity 0.88)
- ArtiMuse: Fine-Grained Image Aesthetics Assessment with Joint Scoring and Expert-Level Understanding (CVPR 2026 · similarity 0.87)
- Advancing Comprehensive Aesthetic Insight with Multi-Scale Text-Guided Self-Supervised Learning (AAAI 2025 · similarity 0.85)
- ELTA: An Enhancer against Long-Tail for Aesthetics-oriented Models (ICML 2024 · similarity 0.85)
- Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment (AAAI 2026 · similarity 0.85)
- Learning Multi-Dimensional Human Preference for Text-to-Image Generation (CVPR 2024 · similarity 0.84)
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.