Unsupervised Multi-modal Hashing For Cross-modal Retrieval

Abstract

With the advantage of low storage cost and high efficiency, hashing learning has received much attention in the domain of Big Data. In this paper, we propose a novel unsupervised hashing learning method to cope with this open problem to directly preserve the manifold structure by hashing. To address this problem, both the semantic correlation in textual space and the locally geometric structure in the visual space are explored simultaneously in our framework. Besides, the `2;1-norm constraint is imposed on the projection matrices to learn the discriminative hash function for each modality. Extensive experiments are performed to evaluate the proposed method on the three publicly available datasets and the experimental results show that our method can achieve superior performance over the state-of-the-art methods.

Stats

• citations12
• S2 citations—
• github stars0
• HF likes0
• heat score8.35
• arxiv keyyu2019unsupervised

Related papers

• Discriminative Supervised Hashing For Cross-modal Similarity Search (2018)7.81
• Cluster-wise Unsupervised Hashing For Cross-modal Similarity Search (2019)11.39
• Transitive Hashing Network For Heterogeneous Multimedia Retrieval (2016)8.35
• Efficient Discrete Supervised Hashing For Large-scale Cross-modal Retrieval (2019)11.08
• Adaptive Structural Similarity Preserving For Unsupervised Cross Modal Hashing (2022)10.97
• Learning Discriminative Hashing Codes For Cross-modal Retrieval Based On Multi-view Features (2018)3.58
• Unsupervised Deep Cross-modality Spectral Hashing (2020)11.39
• Weakly-paired Cross-modal Hashing (2019)0.00