Random Online Hashing for Cross-Modal Retrieval

In the past decades, supervised cross-modal hashing methods have attracted considerable attentions due to their high searching efficiency on large-scale multimedia databases. Many of these methods leverage semantic correlations among heterogeneous modalities by constructing a similarity matrix or building a common semantic space with the collective matrix factorization method. However, the similarity matrix may sacrifice the scalability and cannot preserve more semantic information into hash codes in the existing methods. Meanwhile, the matrix factorization methods cannot embed the main modality-specific information into hash codes. To address these issues, we propose a novel supervised cross-modal hashing method called random online hashing (ROH) in this article. ROH proposes a linear bridging strategy to simplify the pair-wise similarities factorization problem into a linear optimization one. Specifically, a bridging matrix is introduced to establish a bidirectional linear relation between hash codes and labels, which preserves more semantic similarities into hash codes and significantly reduces the semantic distances between hash codes of samples with similar labels. Additionally, a novel maximum eigenvalue direction (MED) embedding method is proposed to identify the direction of maximum eigenvalue for the original features and preserve critical information into modality-specific hash codes. Eventually, to handle real-time data dynamically, an online structure is adopted to solve the problem of dealing with new arrival data chunks without considering pairwise constraints. Extensive experimental results on three benchmark datasets demonstrate that the proposed ROH outperforms several state-of-the-art cross-modal hashing methods.

I. Introduction

Information retrieval, as one of the most common tools, is often used to find out what users need by providing some key clues. With the advent of the big data era, users are faced with the challenge of retrieving interesting information not only from massive homogeneous data, but also from multimedia data. In this context, cross-modal retrieval methods have emerged and become increasingly important in modern life. These methods can search for interesting things across heterogeneous modalities, such as illustrating a textual scene with images visually or searching for a picture based on vague textual description. To further improve the efficiency of the cross-modal retrieval, learning to hash has been proposed in recent years, which allows condensing high-dimensional images and texts into binary codes. Owing to the high efficiency of binary codes in storage and computation, cross-modal hashing methods have gained significant popularity in the information retrieval community [1], [2], [3], [4], [5].