Research map / Vision-language and multimodal / Cross-modal learning
Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval
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 UCH instead of the strongest listed shallow baseline | Cross-modal hashing · MIRFlickr-25K, image query→text database | MAP: 0.635 -> 0.654; 0.636 -> 0.669; 0.639 -> 0.679 | Helped |
| Use UCH instead of the strongest listed shallow baseline | Cross-modal hashing · MIRFlickr-25K, text query→image database | MAP: 0.652 -> 0.661; 0.657 -> 0.667; 0.659 -> 0.668 | Helped |
| Use UCH instead of the strongest listed shallow baseline | Cross-modal hashing · IAPR TC-12, image query→text database | MAP: 0.443 -> 0.447; 0.456 -> 0.471; 0.463 -> 0.485 | Helped |
| Use UCH instead of the strongest listed shallow baseline | Cross-modal hashing · IAPR TC-12, text query→image database | MAP: 0.437 -> 0.446; 0.450 -> 0.469; 0.458 -> 0.488 | Helped |
| Use UCH instead of the strongest listed shallow baseline | Cross-modal hashing · COCO, image query→text database | MAP: 0.475 -> 0.521; 0.490 -> 0.534; 0.524 -> 0.547 | Helped |
| Use UCH instead of the strongest listed shallow baseline | Cross-modal hashing · COCO, text query→image database | MAP: 0.471 -> 0.499; 0.509 -> 0.519; 0.514 -> 0.545 | Helped |
| Replace UGACH with UCH | Cross-modal hashing · MIRFlickr-25K, image→text retrieval | MAP: 0.603 -> 0.654; 0.607 -> 0.669; 0.616 -> 0.679 | Helped |
| Replace UGACH with UCH | Cross-modal hashing · MIRFlickr-25K, text→image retrieval | MAP: 0.590 -> 0.661; 0.632 -> 0.667; 0.642 -> 0.668 | Helped |
| Replace UGACH with UCH | Cross-modal hashing · IAPR TC-12, image→text retrieval | MAP: 0.439 -> 0.447; 0.454 -> 0.471; 0.479 -> 0.485 | Helped |
| Replace UGACH with UCH | Cross-modal hashing · IAPR TC-12, text→image retrieval | MAP: 0.433 -> 0.446; 0.456 -> 0.469; 0.480 -> 0.488 | Helped |
Closest papers by meaning
- Unsupervised Generative Adversarial Cross-Modal Hashing (AAAI 2018 · similarity 0.93)
- Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval (AAAI 2017 · similarity 0.91)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.88)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.88)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.88)
- Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization (AAAI 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.