Research map / Vision-language and multimodal / Human and embodied modeling
Context-Aware Visual Compatibility Prediction
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 test-time neighbourhood context, increasing k from 0 to 15 (ablation) | Context-Aware Visual Compatibility Prediction · Polyvore Original FITB | accuracy: 62.2 -> 96.9 | Helped |
| Add test-time neighbourhood context, increasing k from 0 to 15 (ablation) | Context-Aware Visual Compatibility Prediction · Polyvore Resampled FITB | accuracy: 47.0 -> 92.7 | Helped |
| Add test-time neighbourhood context, increasing k from 0 to 15 (ablation) | Context-Aware Visual Compatibility Prediction · Polyvore Original outfit compatibility | AUC: 0.86 -> 0.99 | Helped |
| Add test-time neighbourhood context, increasing k from 0 to 15 (ablation) | Context-Aware Visual Compatibility Prediction · Polyvore Resampled outfit compatibility | AUC: 0.76 -> 0.99 | Helped |
| Add test-time neighbourhood context, increasing k from 0 to 30 (ablation) | Context-Aware Visual Compatibility Prediction · Fashion-Gen FITB | accuracy: 51.9 -> 77.1 | Helped |
| Add test-time neighbourhood context, increasing k from 0 to 30 (ablation) | Context-Aware Visual Compatibility Prediction · Fashion-Gen outfit compatibility | AUC: 0.72 -> 0.91 | Helped |
| Add test-time neighbourhood context, increasing k from 0 to 10 (ablation) | Context-Aware Visual Compatibility Prediction · Amazon Men also bought | link prediction score: 57.9 -> 97.1 | Helped |
| Add test-time neighbourhood context, increasing k from 0 to 10 (ablation) | Context-Aware Visual Compatibility Prediction · Amazon Men bought together | link prediction score: 79.5 -> 94.0 | Helped |
| Use the full outfits rather than randomly selected three-item subsets (ablation) | Context-Aware Visual Compatibility Prediction (k = 15) · Polyvore Original FITB | accuracy: 88.2 -> 96.9 | Helped |
| Use the full outfits rather than randomly selected three-item subsets (ablation) | Context-Aware Visual Compatibility Prediction (k = 15) · Polyvore Resampled FITB | accuracy: 82.1 -> 92.7 | Helped |
| Train with context and test across genders rather than train without context (ablation) | Amazon also bought model · Amazon Men-trained model tested on Women | link prediction score: 58.3 -> 86.0 | Helped |
| Train with context and test across genders rather than train without context (ablation) | Amazon also bought model · Amazon Women-trained model tested on Men | link prediction score: 66.5 -> 90.9 | Helped |
Closest papers by meaning
- Complete the Look: Scene-Based Complementary Product Recommendation (CVPR 2019 · similarity 0.91)
- Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation (AAAI 2024 · similarity 0.88)
- Aligning Vision Models with Human Aesthetics in Retrieval: Benchmarks and Algorithms (NeurIPS 2024 · similarity 0.86)
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · similarity 0.85)
- StyleTailor: Towards Personalized Fashion Styling via Hierarchical Negative Feedback (AAAI 2026 · similarity 0.84)
- ICAR: Image-Based Complementary Auto Reasoning (AAAI 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.