Research map / Vision-language and multimodal / Cross-modal learning
Self-Supervised Multi-Modal Knowledge Graph Contrastive Hashing for Cross-Modal Search
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 CMGCH instead of UCCH | Cross-modal hashing · MSCOCO I→T, 128 bits | MAP: 0.665 -> 0.873 | Helped |
| use CMGCH instead of UCCH | Cross-modal hashing · MSCOCO T→I, 128 bits | MAP: 0.677 -> 0.890 | Helped |
| add the multimodal knowledge graph and graph attention model (ablation) | CMGCH · MSCOCO I→T, 128 bits | MAP: 0.823 -> 0.866 | Helped |
| add the multimodal knowledge graph and graph attention model (ablation) | CMGCH · MSCOCO T→I, 128 bits | MAP: 0.837 -> 0.890 | Helped |
| use graph attention network instead of graph convolutional network (ablation) | CMGCH · MSCOCO I→T, 128 bits | MAP: 0.853 -> 0.866 | Helped |
| use graph attention network instead of graph convolutional network (ablation) | CMGCH · MSCOCO T→I, 128 bits | MAP: 0.844 -> 0.890 | Helped |
| add global inter-modal contrastive learning (ablation) | CMGCH · MSCOCO I→T, 128 bits | MAP: 0.563 -> 0.866 | Helped |
| add global inter-modal contrastive learning (ablation) | CMGCH · MSCOCO T→I, 128 bits | MAP: 0.552 -> 0.890 | Helped |
| add global intra-modal contrastive learning (ablation) | CMGCH · MSCOCO I→T, 128 bits | MAP: 0.714 -> 0.866 | Helped |
| add global intra-modal contrastive learning (ablation) | CMGCH · MSCOCO T→I, 128 bits | MAP: 0.792 -> 0.890 | Helped |
| add inter-modal contrastive learning on the graph (ablation) | CMGCH · MSCOCO I→T, 128 bits | MAP: 0.833 -> 0.866 | Helped |
| add inter-modal contrastive learning on the graph (ablation) | CMGCH · MSCOCO T→I, 128 bits | MAP: 0.841 -> 0.890 | Helped |
Closest papers by meaning
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.91)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.90)
- Semantic-Consistent Bidirectional Contrastive Hashing for Noisy Multi-Label Cross-Modal Retrieval (AAAI 2026 · similarity 0.89)
- Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization (AAAI 2025 · similarity 0.87)
- Asymmetric Cross-Modal Hashing Based on Formal Concept Analysis (AAAI 2025 · similarity 0.87)
- Connect, Collapse, Corrupt: Learning Cross-Modal Tasks with Uni-Modal Data (ICLR 2024 · similarity 0.86)
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.