Research map / Vision-language and multimodal / Cross-modal learning
Decoupled Prototype Contrastive Alignment Hashing for Cross-Modal Retrieval
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's abstract only. Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Proposes DPCAH, an unsupervised cross-modal hashing method using decoupled prototype contrastive alignment with cross-modal semantic contrastive learning.
Problem
Unsupervised cross-modal hashing struggles to capture inter-modal interactions, enforce multi-level alignment, and keep optimization stable.
Approach
Combines cross-modal semantic contrastive learning with decoupled prototype-based alignment to achieve multi-level alignment for unsupervised hashing; details beyond the abstract are not available.
Closest papers by meaning
- Lightweight Contrastive Distilled Hashing for Online Cross-modal Retrieval (AAAI 2025 · similarity 0.91)
- 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 0.88)
- Dual Self-Paced Cross-Modal Hashing (AAAI 2024 · similarity 0.88)
- An End-To-End Graph Attention Network Hashing for Cross-Modal Retrieval (NeurIPS 2024 · similarity 0.88)
- PromptHash:Affinity-Prompted Collaborative Cross-Modal Learning for Adaptive Hashing Retrieval (CVPR 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.