Composite Proxy-based Hierarchical Contrastive Hashing for Cross-modal Retrieval
- 5 June 2026
- journal article
- Published by Institute of Electrical and Electronics Engineers (IEEE) in IEEE Transactions on Circuits and Systems for Video Technology
- Vol. PP (10518215) , 1
Abstract
Supervised cross-modal hashing retrieval leverages labeled information to map heterogeneous multimodal data into a unified hash space, enabling efficient and accurate similarity search. Proxy-based method directly projects labeled information into proxy hash codes and consequently leverages them to guide the hashing network training, achieving excellent retrieval performance. Although making impressive progress, these methods fail to capture label-to-label semantic relationships in multi-label data, i.e., semantic affinities between different labels and co-occurrence relations of different labels, which generally results in sub-optimal hash codes. To address this limitation, we propose a novel cross-modal hashing method, termed Composite Proxy-based Hierarchical Contrastive Hashing (CPHCH), which can capture complex semantic relationships by composite semantic proxies. Specifically, a Graph convolutional network-based Semantic Enhancement (GSE) module is first designed to explicitly capture the semantic similarities and co-occurrence relations between labels by integrating CLIP’s semantic priors with Pointwise Mutual Information (PMI) statistics. And then the learned semantic similarities and co-occurrence relationships are injected into the composite proxy hash codes learning, thereby enhancing their semantic discriminative ability. Finally, we propose a Hierarchy-aware Dynamic Contrastive Weighting Learning (HDCWL) module, which hierarchically weights the similarities between data-proxy hash codes using a Jaccard similarity matrix, ensuring prioritized alignment of fully matched samples while preserving fine-grained semantic differences in partially matched samples. Experimental results demonstrate that CPHCH significantly outperforms baseline methods on cross-modal retrieval tasks.Keywords
Funding Information
- Natural Science Foundation of Shandong Province (ZR2023MF031)
- National Natural Science Foundation of China (62102186)
This publication has 53 references indexed in Scilit:
- MEDIAN: Adaptive Intermediate-grained Aggregation Network for Composed Image Retrieval2025
- Text-Guided Knowledge Transfer for Remote Sensing Image-Text RetrievalIEEE Geoscience and Remote Sensing Letters, 2024
- Scalable Unsupervised Hashing via Exploiting Robust Cross-Modal ConsistencyIEEE Transactions on Big Data, 2024
- Deep Semantic-Aware Proxy Hashing for Multi-Label Cross-Modal RetrievalIEEE Transactions on Circuits and Systems for Video Technology, 2023
- Self-constraining and attention-based hashing network for bit-scalable cross-modal retrievalNeurocomputing, 2020
- Central Similarity Quantization for Efficient Image and Video Retrieval2020
- Cross-Modal Hamming Hashing2018
- Self-Supervised Adversarial Hashing Networks for Cross-Modal Retrieval2018
- Deep Cross-Modal Hashing2017
- Microsoft COCO: Common Objects in Context2014