Research map / Vision-language and multimodal / Cross-modal learning
Collective Deep Quantization for Efficient Cross-Modal Retrieval
Yue Cao, Mingsheng Long, Jianmin Wang, Shichen Liu
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 |
|---|---|---|---|
| jointly learn deep representations with collective quantization loss instead of two-step (ablation) | CDQ-2 · NUS-WIDE I->T | average MAP: +2.21% | Improved |
| use adaptive cross-entropy loss instead of pairwise inner-product loss (ablation) | CDQ-ip · NUS-WIDE T->I | average MAP: +20.91% | Improved |
| add adaptive coefficient alpha in cross-entropy loss (ablation) | CDQ-α · MIR-Flickr T->I | average MAP: +2.57% | Improved |
| CDQ deep quantization vs CHN deep hashing | CHN · NUS-WIDE T->I 32 bits | MAP: 0.7704 -> 0.8478 | Improved |
| CDQ deep quantization vs CHN deep hashing | CHN · MIR-Flickr I->T 32 bits | MAP: 0.8571 -> 0.8618 | Improved |
Closest papers by meaning
- Collaborative Quantization for Cross-Modal Similarity Search (CVPR 2016 · similarity 0.93)
- Mutual Quantization for Cross-Modal Search With Noisy Labels (CVPR 2022 · similarity 0.90)
- Deep Joint-Semantics Reconstructing Hashing for Large-Scale Unsupervised Cross-Modal Retrieval (ICCV 2019 · similarity 0.90)
- Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization (AAAI 2025 · similarity 0.90)
- Unsupervised Dual Deep Hashing With Semantic-Index and Content-Code for Cross-Modal Retrieval (TPAMI 2024 · similarity 0.89)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (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.
