Research map / Vision-language and multimodal / Human and embodied modeling
Multi-Schema Proximity Network for Composed Image Retrieval
Jiangming Shi, Xiangbo Yin, Yeyun Chen, Yachao Zhang, Zhizhong Zhang, Yuan Xie, Yanyun Qu
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 |
|---|---|---|---|
| add Multi-Schema Interaction (MSI) (ablation) | SPRC · CIRR test | Recall@1: 51.96 -> 54.02 | Improved |
| add Multi-Schema Interaction (MSI) (ablation) | SPRC · FashionIQ val (avg of Dress, Shirt, Toptee) | avg Recall@10: 54.17 -> 55.16 | Improved |
| add Relaxed Proximity Loss (RPLoss) (ablation) | SPRC · CIRR test | Recall@1: 51.96 -> 53.49 | Improved |
| add Relaxed Proximity Loss (RPLoss) (ablation) | SPRC · FashionIQ val (avg of Dress, Shirt, Toptee) | avg Recall@10: 54.17 -> 54.92 | Improved |
| add RPLoss on top of MSI (ablation) | SPRC + MSI · CIRR test | Recall@1: 54.02 -> 54.65 | Improved |
| add RPLoss on top of MSI (ablation) | SPRC + MSI · FashionIQ val (avg of Dress, Shirt, Toptee) | avg Recall@10: 55.16 -> 55.70 | Improved |
| add MSI on top of RPLoss (ablation) | SPRC + RPLoss · CIRR test | Recall@1: 53.49 -> 54.65 | Improved |
| add MSI and RPLoss together to SPRC (ablation) | SPRC · CIRR test | Recall@1: 51.96 -> 54.65 | Improved |
| add MSI and RPLoss together to SPRC (ablation) | SPRC · FashionIQ val (avg of Dress, Shirt, Toptee) | avg Recall@10: 54.17 -> 55.70 | Improved |
| add MSI and RPLoss to SPRC | SPRC · CIRR test | Recall_subset@1: 80.65 -> 81.15 | No clear effect |
| add MSI and RPLoss to SPRC | SPRC · LaSCo val | Recall@5: 22.21 -> 24.62 | Improved |
| add MSI and RPLoss to SPRC | SPRC · LaSCo val | Recall@50: 55.10 -> 58.18 | Improved |
Closest papers by meaning
- Instance-Level Composed Image Retrieval (NeurIPS 2025 · similarity 0.90)
- ConText-CIR: Learning from Concepts in Text for Composed Image Retrieval (CVPR 2025 · similarity 0.90)
- Generative Zero-Shot Composed Image Retrieval (CVPR 2025 · similarity 0.89)
- Do Composed Image Retrieval Benchmarks Require Multimodal Composition? (NeurIPS 2026 · similarity 0.88)
- Visual Delta Generator with Large Multi-modal Models for Semi-supervised Composed Image Retrieval (CVPR 2024 · similarity 0.88)
- CCIN: Compositional Conflict Identification and Neutralization for Composed Image Retrieval (CVPR 2025 · similarity 0.87)
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.
