Research map / Vision-language and multimodal / CLIP and zero-shot
FashionSAP: Symbols and Attributes Prompt for Fine-Grained Fashion Vision-Language Pre-Training
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 |
|---|---|---|---|
| Add prompt token prediction (PTP) (ablation) | FashionSAP · FashionGen image-to-text retrieval ablation | I2T R@1: 43.84 -> 51.99 | Helped |
| Add prompt token prediction (PTP) (ablation) | FashionSAP · FashionIQ ablation evaluation | R@10: 30.02 -> 34.40 | Helped |
| Add token replace prediction (TRP) to PTP (ablation) | FashionSAP · FashionGen subcategory recognition ablation | Macro-F: 86.03 -> 86.65 | Helped |
| Add token replace prediction (TRP) to PTP (ablation) | FashionSAP · FashionIQ ablation evaluation | R@10: 34.40 -> 35.01 | Helped |
| Add fashion symbol image similarity (FSIS) to PTP and TRP (ablation) | FashionSAP · FashionGen text-to-image retrieval ablation | T2I R@1: 55.54 -> 62.82 | Helped |
| Add fashion symbol image similarity (FSIS) to PTP and TRP (ablation) | FashionSAP · FashionGen category recognition ablation | Macro-F: 86.51 -> 89.84 | Helped |
| Add fashion symbol image similarity (FSIS) to PTP and TRP (ablation) | FashionSAP · FashionIQ ablation evaluation | R@10: 35.01 -> 36.26 | Helped |
Closest papers by meaning
- Easy Regional Contrastive Learning of Expressive Fashion Representations (NeurIPS 2024 · similarity 0.89)
- ChatGarment: Garment Estimation, Generation and Editing via Large Language Models (CVPR 2025 · similarity 0.86)
- Seeing the Abstract: Translating the Abstract Language for Vision Language Models (CVPR 2025 · similarity 0.86)
- FashionERN: Enhance-and-Refine Network for Composed Fashion Image Retrieval (AAAI 2024 · similarity 0.85)
- TexFit: Text-Driven Fashion Image Editing with Diffusion Models (AAAI 2024 · similarity 0.85)
- Text-Driven Fashion Image Editing with Compositional Concept Learning and Counterfactual Abduction (CVPR 2025 · similarity 0.85)
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.