Research map / Label-efficient and robust learning / Recognition and long-tail
TransNFCM: Translation-Based Neural Fashion Compatibility Modeling
Read the paperCheck 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 |
|---|---|---|---|
| Use category-specific relation translations instead of category-unaware compatibility | TransNFCM vs. TriNet · FashionVC, visual features | AUC: 70.6 -> 73.6 | Helped |
| Use category-specific relation translations instead of category-unaware compatibility | TransNFCM vs. TriNet · PolyvoreMaryland, visual features | AUC: 70.1 -> 71.8 | Helped |
| Fuse visual and textual features (ablation) | TransNFCM · FashionVC | AUC: 73.6 -> 76.9 | Helped |
| Fuse visual and textual features (ablation) | TransNFCM · PolyvoreMaryland | AUC: 71.8 -> 74.7 | Helped |
| Include textual features alongside visual features (ablation) | TransNFCM · FashionVC | Hit@10: 32.3 -> 38.1 | Helped |
| Include textual features alongside visual features (ablation) | TransNFCM · PolyvoreMaryland | Hit@10: 30.6 -> 34.4 | Helped |
| Add category-specific compatibility to global compatibility (ablation) | TransNFCM · FashionVC, visual features | AUC | Helped |
| Use only category-specific compatibility, omitting the global compatibility term (ablation) | TransNFCM · FashionVC and PolyvoreMaryland | compatibility performance | Hurt |
| Use the global compatibility term rather than only the category-specific term (ablation) | TransNFCM · FashionVC and PolyvoreMaryland | compatibility performance | Helped |
| Remove the cross-modality consistency or visual-semantic loss (ablation) | TransNFCM · FashionVC and PolyvoreMaryland | compatibility performance | Helped |
| Use category-specific translation compatibility rather than conditional similarity | TransNFCM vs. CSN · FashionVC, visual features | AUC: 71.6 -> 73.6 | Helped |
| Use category-specific translation compatibility rather than conditional similarity | TransNFCM vs. CSN · PolyvoreMaryland, visual features | AUC: 70.2 -> 71.8 | Helped |
Closest papers by meaning
- Learning to Match on Graph for Fashion Compatibility Modeling (AAAI 2020 · similarity 0.90)
- Context-Aware Visual Compatibility Prediction (CVPR 2019 · similarity 0.88)
- Towards Better Understanding the Clothing Fashion Styles: A Multimodal Deep Learning Approach (AAAI 2017 · similarity 0.88)
- Deciphering Compatibility Relationships with Textual Descriptions via Extraction and Explanation (AAAI 2024 · similarity 0.87)
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · similarity 0.87)
- FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval (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.