Research map / Vision-language and multimodal / Cross-modal learning
Transitive Hashing Network for Heterogeneous Multimedia 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 transitive hashing rather than DCMH | Cross-modal retrieval · NUS-WIDE I → T | MAP: relative increases of 9.47% | Helped |
| use transitive hashing rather than DCMH | Cross-modal retrieval · NUS-WIDE T → I | MAP: 2.85% | Helped |
| use transitive hashing rather than DCMH | Cross-domain retrieval · ImageNet-YahooQA I → T | MAP: 5.03% | Helped |
| use transitive hashing rather than DCMH | Cross-domain retrieval · ImageNet-YahooQA T → I | MAP: 6.91% | Helped |
| use pairwise cross-entropy loss instead of pairwise inner-product loss (ablation) | THN · ImageNet-YahooQA I → T and T → I | MAP: 24.15% / 23.19% in absolute increase of average MAP | Helped |
| add unsupervised training data from the query and database domains (ablation) | THN · ImageNet-YahooQA I → T | MAP: 4.06% | Helped |
| add unsupervised training data from the query and database domains (ablation) | THN · ImageNet-YahooQA T → I | MAP: 6.09% | Helped |
| add pairwise quantization loss (ablation) | THN · ImageNet-YahooQA I → T | MAP: 5.83% | Helped |
| add pairwise quantization loss (ablation) | THN · ImageNet-YahooQA T → I | MAP: 4.20% | Helped |
Closest papers by meaning
- Pairwise Relationship Guided Deep Hashing for Cross-Modal Retrieval (AAAI 2017 · similarity 0.91)
- Dual Deep Neural Networks Cross-Modal Hashing (AAAI 2018 · similarity 0.91)
- Deep Cross-Modal Hashing (CVPR 2017 · similarity 0.90)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.89)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.88)
- Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization (AAAI 2025 · 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.