Unsupervised Cross-Media Hashing with Structure Preservation

TL;DR

This paper introduces an unsupervised cross-media hashing technique that preserves data structure and improves retrieval accuracy across heterogeneous multimedia sources by learning unified hash codes.

Contribution

It proposes a novel unsupervised hashing method incorporating local affinity and distance constraints within a matrix factorization framework for cross-media retrieval.

Findings

Outperforms state-of-the-art methods on large-scale datasets

Preserves intrinsic geometric structure of data

Generates effective unified hash codes for different media types

Abstract

Recent years have seen the exponential growth of heterogeneous multimedia data. The need for effective and accurate data retrieval from heterogeneous data sources has attracted much research interest in cross-media retrieval. Here, given a query of any media type, cross-media retrieval seeks to find relevant results of different media types from heterogeneous data sources. To facilitate large-scale cross-media retrieval, we propose a novel unsupervised cross-media hashing method. Our method incorporates local affinity and distance repulsion constraints into a matrix factorization framework. Correspondingly, the proposed method learns hash functions that generates unified hash codes from different media types, while ensuring intrinsic geometric structure of the data distribution is preserved. These hash codes empower the similarity between data of different media types to be evaluated directly. Experimental results on two large-scale multimedia datasets demonstrate the effectiveness of the proposed method, where we outperform the state-of-the-art methods.