Research map / Vision-language and multimodal / Human and embodied modeling
A Paradigm for Building Generalized Models of Human Image Perception Through Data Fusion
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 |
|---|---|---|---|
| include imputed attributes alongside observed attributes (ablation) | human-attribute prediction using the fused perception model · Visual realism prediction | Spearman's rank correlation (ρv): .69 -> .70 | Helped |
| include imputed attributes alongside observed attributes (ablation) | human-attribute prediction using the fused perception model · Interestingness prediction | Spearman's rank correlation (ρi): .70 -> .71 | Helped |
| include imputed attributes alongside observed attributes (ablation) | human-attribute prediction using the fused perception model · Visual realism classification | AUC (Av): .84 -> .90 | Helped |
| include imputed attributes alongside observed attributes (ablation) | human-attribute prediction using the fused perception model · Interestingness classification | AUC (Ai): .64 -> .75 | Helped |
| use perception-model-guided computational features instead of the original task-specific algorithms | visual realism predictor · Visual realism prediction | Spearman's rank correlation (ρv): .51 -> .54 | Helped |
| use perception-model-guided computational features instead of the original task-specific algorithms | interestingness predictor · Interestingness prediction | Spearman's rank correlation (ρi): .27 -> .31 | Helped |
| use perception-model-guided computational features instead of the original task-specific algorithms | visual realism classifier · Visual realism classification | AUC (Av): .77 -> .82 | Helped |
| use perception-model-guided computational features instead of the original task-specific algorithms | interestingness classifier · Interestingness classification | AUC (Ai): .59 -> .71 | Helped |
Closest papers by meaning
- Customizing Visual Emotion Evaluation for MLLMs: An Open-vocabulary, Multifaceted, and Scalable Approach (ICLR 2026 · similarity 0.87)
- The Many Senses of Visual Similarity: A Text-Prompted Image Perceptual Metric (NeurIPS 2026 · similarity 0.87)
- PerceptionRubrics: Calibrating Multimodal Evaluation to Human Perception (ICML 2026 · similarity 0.86)
- Learning Multi-Dimensional Human Preference for Text-to-Image Generation (CVPR 2024 · similarity 0.86)
- Bridging Cognitive Gap: Hierarchical Description Learning for Artistic Image Aesthetics Assessment (AAAI 2026 · similarity 0.86)
- Multidimensional Observer Model and Perceptual Dimensions of Human Image Quality Assessment (NeurIPS 2026 · similarity 0.86)
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.