Research map / Vision-language and multimodal / Cross-modal learning
Unsupervised Generative Adversarial Cross-Modal Hashing
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 adversarial training to Baseline (ablation) | Cross-modal hashing · NUS-WIDE image→text and text→image | average MAP: +0.037 and 0.034 | Helped |
| Add the correlation graph to Baseline-GAN (ablation) | UGACH · NUS-WIDE image→text and text→image | average MAP: +0.025 and 0.016 | Helped |
| Add adversarial training to Baseline (ablation) | Cross-modal hashing · MIRFlickr | MAP | Helped |
| Add the correlation graph to Baseline-GAN (ablation) | UGACH · MIRFlickr | MAP | Helped |
| Use UGACH instead of the strongest unsupervised method CCQ | Cross-modal hashing · NUS-WIDE image→text | average MAP: from $0.505$ to $0.624$ | Helped |
| Use UGACH instead of the strongest unsupervised method CCQ | Cross-modal hashing · NUS-WIDE text→image | average MAP: from $0.494$ to $0.625$ | Helped |
Closest papers by meaning
- Coupled CycleGAN: Unsupervised Hashing Network for Cross-Modal Retrieval (AAAI 2019 · similarity 0.93)
- UGGRH: Unsupervised Generative Completion and Graph-attention Refinement for Incomplete Cross-modal Hashing (NeurIPS 2026 · similarity 0.92)
- Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization (AAAI 2025 · similarity 0.90)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.88)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.88)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.88)
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.