Research map / Image generation / Autoregressive and latent generation
Thinking Aesthetics Assessment of Image Color Temperature: Models, Datasets and Benchmarks
Jinguang Cheng, Chunxiao Li, Shuai He, Taiyu Chen, Anlong Ming
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 |
|---|---|---|---|
| use ICTA2Net instead of best baseline | IAA models · ICTAA-HP | IEA: 0.717 -> 0.776 | Improved |
| use ICTA2Net instead of best baseline | IAA models · ICTAA-HP | ACC: 0.664 -> 0.726 | Improved |
| use ICTA2Net instead of EAT | IAA models · ICTAA-GP | IEA: 0.746 -> 0.746 | No clear effect |
| add inter-group contrastive loss (ablation) | ICTA2Net · ICTAA-HP | IEA: 0.761 -> 0.776 | Improved |
| add text information (ablation) | ICTA2Net · ICTAA-HP | IEA: 0.759 -> 0.776 | Improved |
| add text information (ablation) | ICTA2Net · ICTAA-GP | IEA: 0.746 -> 0.746 | No clear effect |
| add color temperature encoder (CTE) (ablation) | ICTA2Net · ICTAA-HP | IEA: 0.649 -> 0.776 | Improved |
| add text denoise model (TDM) (ablation) | ICTA2Net · ICTAA-HP | IEA: 0.744 -> 0.776 | Improved |
| add text denoise model (TDM) (ablation) | ICTA2Net · ICTAA-GP | IEA: 0.751 -> 0.746 | Hurt |
| add cross-modal fusion module (CFM) instead of concatenation (ablation) | ICTA2Net · ICTAA-HP | IEA: 0.710 -> 0.776 | Improved |
| add cross-modal fusion module (CFM) instead of concatenation (ablation) | ICTA2Net · ICTAA-GP | IEA: 0.754 -> 0.746 | Hurt |
Closest papers by meaning
- Thinking Image Color Aesthetics Assessment: Models, Datasets and Benchmarks (ICCV 2023 · similarity 0.90)
- Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment (AAAI 2026 · similarity 0.85)
- ColorConceptBench: A Benchmark for Probabilistic Color-Concept Understanding in Text-to-Image Models (NeurIPS 2026 · similarity 0.85)
- The Photographer's Eye: Teaching Multimodal Large Language Models to See, and Critique Like Photographers (CVPR 2025 · similarity 0.84)
- Unlocking the Essence of Beauty: Advanced Aesthetic Reasoning with Relative-Absolute Policy Optimization (ICLR 2026 · similarity 0.83)
- Towards a Perceptual Evaluation Framework for Lighting Estimation (CVPR 2024 · similarity 0.83)
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.
