Fast metric multi-view hashing for multimedia retrieval

The acquisition of multi-view hash representation for heterogeneous data holds paramount importance in the domain of multimedia retrieval. The limited retrieval precision observed in current approaches stems from their inadequate integration of multi-view features and their failure to effectively leverage the metric information available from diverse samples. Commonly employed fusion methods, such as concatenation or weighted sum, are insufficient in capturing the complementarity among multiple view features. Furthermore, these methods neglect the valuable information contributed by dissimilar samples. To address these challenges, we propose an innovative method termed Fast Metric Multi-View Hashing (FMMVH). Our approach showcases the superiority of gate-based fusion over traditional methods, as substantiated by extensive empirical evidence. Additionally, this paper proposes a novel deep metric loss function to enable the utilization of metric information from dissimilar samples. We exclusively train our method using this single loss function. To enhance practical applicability in industrial production environments, we employ model compression techniques to optimize the proposed method. On benchmark datasets such as MIR-Flickr25K, NUS-WIDE, and MS COCO, the performance of our FMMVH method significantly surpasses that of existing state-of-the-art methods, demonstrating improvements of up to 7.47% in mean Average Precision (mAP).

Automated summary

The acquisition of multi-view hash representation for heterogeneous data is highly important for multimedia retrieval. Current approaches suffer from limited retrieval precision due to insufficient integration of multi-view features and failure to effectively utilize metric information from diverse samples. In this paper, we propose an innovative method called Fast Metric Multi-View Hashing (FMMVH), which demonstrates the superiority of gate-based fusion over traditional methods. We also introduce a novel deep metric loss function to leverage metric information from dissimilar samples. By optimizing and employing model compression techniques, our FMMVH method significantly outperforms existing state-of-the-art methods on benchmark datasets, with up to 7.47% improvement in mean Average Precision (mAP).