Research map / Vision-language and multimodal / Cross-modal learning
Ranking-Based Deep 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 |
|---|---|---|---|
| Use RDCMH's ranking-based deep cross-modal hashing instead of the strongest listed baseline | Cross-modal retrieval · MIRFLICKR, image→text, 16 bits | MAP: 0.7604 -> 0.7723 | Helped |
| Use RDCMH instead of the strongest listed baseline | Cross-modal retrieval · MIRFLICKR, text→image, 16 bits | MAP: 0.7856 -> 0.7931 | Helped |
| Use RDCMH instead of the strongest listed baseline | Cross-modal retrieval · NUS-WIDE, image→text, 16 bits | MAP: 0.6203 -> 0.6231 | Helped |
| Use RDCMH instead of the strongest listed baseline | Cross-modal retrieval · NUS-WIDE, text→image, 16 bits | MAP: 0.6531 -> 0.6641 | Helped |
| Use RDCMH instead of the strongest listed baseline | Cross-modal retrieval · Wiki, image→text, 16 bits | MAP: 0.2873 -> 0.2943 | Helped |
| Use RDCMH instead of SePH | Cross-modal retrieval · Wiki, text→image, 16 bits | MAP: 0.5345 -> 0.2931 | Hurt |
| Use RDCMH instead of the strongest listed baseline with 70% unlabeled training data | Cross-modal retrieval · MIRFLICKR, image→text, 16 bits | MAP: 0.1511 -> 0.1842 | Helped |
| Use RDCMH instead of the strongest listed baseline with 70% unlabeled training data | Cross-modal retrieval · MIRFLICKR, text→image, 16 bits | MAP: 0.1434 -> 0.1769 | Helped |
| Use RDCMH instead of the strongest listed baseline with 70% unlabeled training data | Cross-modal retrieval · NUS-WIDE, image→text, 16 bits | MAP: 0.1256 -> 0.1634 | Helped |
| Use RDCMH instead of the strongest listed baseline with 70% unlabeled training data | Cross-modal retrieval · NUS-WIDE, text→image, 16 bits | MAP: 0.1194 -> 0.1549 | Helped |
| Use RDCMH instead of the strongest listed baseline with 70% unlabeled training data | Cross-modal retrieval · Wiki, image→text, 16 bits | MAP: 0.0623 -> 0.1026 | Helped |
| Use RDCMH instead of the strongest listed baseline with 70% unlabeled training data | Cross-modal retrieval · Wiki, text→image, 16 bits | MAP: 0.0651 -> 0.1038 | Helped |
Closest papers by meaning
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.91)
- Statistical Model-driven Similarity Hashing: Bridging Modalities for Efficient Unsupervised Retrieval (AAAI 2025 · similarity 0.89)
- Asymmetric Cross-Modal Hashing Based on Formal Concept Analysis (AAAI 2025 · similarity 0.89)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.89)
- Distribution-Consistency-Guided Multi-modal Hashing (AAAI 2025 · similarity 0.89)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.89)
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.