Research map / Vision-language and multimodal / Cross-modal learning
Cross-Modal Deep Variational Hashing
Venice Erin Liong, Jiwen Lu, Yap-Peng Tan, Jie Zhou
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (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 latent network to fusion network (ablation) | CMDVH · NUS-WIDE image-to-text, 16 bits | mAP: 0.7864 -> 0.8503 | Improved |
| add latent network to fusion network (ablation) | CMDVH · NUS-WIDE image-to-text, 128 bits | mAP: 0.8666 -> 0.8910 | Improved |
| add latent network to fusion network (ablation) | CMDVH · NUS-WIDE text-to-image, 16 bits | mAP: 0.7390 -> 0.8270 | Improved |
| add latent network to fusion network (ablation) | CMDVH · NUS-WIDE text-to-image, 128 bits | mAP: 0.8504 -> 0.8782 | Improved |
| add probabilistic interpretation to modality-specific networks (ablation) | CMDVH · NUS-WIDE image-to-text, 16 bits | mAP: 0.8234 -> 0.8503 | Improved |
| add probabilistic interpretation to modality-specific networks (ablation) | CMDVH · NUS-WIDE image-to-text, 128 bits | mAP: 0.8821 -> 0.8910 | Improved |
| add probabilistic interpretation to modality-specific networks (ablation) | CMDVH · NUS-WIDE text-to-image, 16 bits | mAP: 0.7992 -> 0.8270 | Improved |
| add probabilistic interpretation to modality-specific networks (ablation) | CMDVH · NUS-WIDE text-to-image, 128 bits | mAP: 0.8583 -> 0.8782 | Improved |
| use CMDVH instead of SePH-km | SePH-km · Wiki image-to-text, 128 bits | mAP: 0.4472 -> 0.4442 | Mixed |
| use CMDVH instead of DisCMH | DisCMH · NUS-WIDE image-to-text, 128 bits | mAP: 0.7605 -> 0.8910 | Improved |
| use CMDVH instead of DVSH | DVSH · IAPRTC12 image-to-text, 128 bits | mAP: 0.7236 -> 0.7902 | Improved |
| use CMDVH instead of DCMH | DCMH · NUS-WIDE image-to-text, 64 bits | mAP: 0.6720 -> 0.8801 | Improved |
Closest papers by meaning
- Deep Cross-Modal Hashing (CVPR 2017 · similarity 0.93)
- Deep Variational and Structural Hashing (TPAMI 2018 · similarity 0.92)
- Dual Deep Neural Networks Cross-Modal Hashing (AAAI 2018 · similarity 0.92)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.89)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.89)
- Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization (AAAI 2025 · 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.
