Research map / Vision-language and multimodal / Cross-modal learning
Cross-Modal Hamming Hashing
Yue Cao, Bin Liu, Mingsheng Long, Jianmin Wang
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 exponential focal loss in place of cross-entropy loss (ablation) | CMHH · NUS-WIDE | average MAP (I->T / T->I): 2.7%/3.9% | Improved |
| add exponential focal loss in place of cross-entropy loss (ablation) | CMHH · MIRFlickr-25K | average MAP (I->T / T->I): 2.4%/2.1% | Improved |
| add exponential focal loss in place of cross-entropy loss (ablation) | CMHH · IAPR TC-12 | average MAP (I->T / T->I): 3.6%/1.2% | Improved |
| add focal reweighting (w_ij) to the loss (ablation) | CMHH · NUS-WIDE | average MAP (I->T / T->I): 2.0%/2.8% | Improved |
| add focal reweighting (w_ij) to the loss (ablation) | CMHH · MIRFlickr-25K | average MAP (I->T / T->I): 2.5%/2.1% | Improved |
| add focal reweighting (w_ij) to the loss (ablation) | CMHH · IAPR TC-12 | average MAP (I->T / T->I): 2.2%/2.8% | Improved |
| add exponential quantization loss (ablation) | CMHH · NUS-WIDE | average MAP (I->T / T->I): 1.9%/2.2% | Improved |
| add exponential quantization loss (ablation) | CMHH · MIRFlickr-25K | average MAP (I->T / T->I): 1.7%/2.0% | Improved |
| add exponential quantization loss (ablation) | CMHH · IAPR TC-12 | average MAP (I->T / T->I): 2.6%/2.3% | Improved |
| use CMHH instead of DCMH | deep cross-modal hashing · NUS-WIDE | average MAP (I->T / T->I): 3.5%/4.3% | Improved |
| use CMHH instead of DCMH | deep cross-modal hashing · MIRFlickr-25K | average MAP (I->T / T->I): 2.9%/2.6% | Improved |
| use CMHH instead of DCMH | deep cross-modal hashing · IAPR TC-12 | average MAP (I->T / T->I): 5.0%/1.4% | Improved |
Closest papers by meaning
- Cross-Modal Hashing Method With Properties of Hamming Space: A New Perspective (TPAMI 2024 · similarity 0.94)
- Deep Cross-Modal Hashing (CVPR 2017 · similarity 0.93)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.90)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.90)
- Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization (AAAI 2025 · similarity 0.89)
- Asymmetric Cross-Modal Hashing Based on Formal Concept Analysis (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.
