Research map / Vision-language and multimodal / Cross-modal learning
Collaborative Quantization for Cross-Modal Similarity Search
Check 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 |
|---|---|---|---|
| jointly learn modality-specific quantizers and align paired image-text quantized representations | CMCQ · FLICKR25K and NUS-WIDE, image-to-text and text-to-image | MAP@50 | Helped |
| jointly learn modality-specific quantizers and align paired image-text quantized representations | CMCQ · Wiki, text to image | MAP@50 | Helped |
| add quantized-space intra-document correlation (ablation) | CMCQ · Wiki, FLICKR25K, and NUS-WIDE, cross-modal search | MAP@100 | Helped |
| add common-space intra-document alignment (ablation) | CMCQ · Wiki, FLICKR25K, and NUS-WIDE, cross-modal search | MAP@100 | Helped |
| use separate quantization dictionaries for the two modalities instead of one shared dictionary (ablation) | CMCQ · Wiki, FLICKR25K, and NUS-WIDE, cross-modal search | MAP@100 | Helped |
| increase code length from 16 bits to 128 bits | CMCQ · Wiki, image to text | MAP@50: 0.2478 -> 0.2614 | Helped |
| increase code length from 16 bits to 128 bits | CMCQ · FLICKR25K, text to image | MAP@50: 0.7248 -> 0.7550 | Helped |
Closest papers by meaning
- Vision-guided Text Mining for Unsupervised Cross-modal Hashing with Community Similarity Quantization (AAAI 2025 · similarity 0.91)
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.88)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.87)
- Learning to Rematch Mismatched Pairs for Robust Cross-Modal Retrieval (CVPR 2024 · similarity 0.87)
- Statistical Model-driven Similarity Hashing: Bridging Modalities for Efficient Unsupervised Retrieval (AAAI 2025 · similarity 0.87)
- Cross-Modal and Uni-Modal Soft-Label Alignment for Image-Text Retrieval (AAAI 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.