Deep Cross-Modal Hashing

Abstract

Due to its low storage cost and fast query speed, cross-modal hashing (CMH) has been widely used for similarity search in multimedia retrieval applications. However, almost all existing CMH methods are based on hand-crafted features which might not be optimally compatible with the hash-code learning procedure. As a result, existing CMH methods with handcrafted features may not achieve satisfactory performance. In this paper, we propose a novel cross-modal hashing method, called deep crossmodal hashing (DCMH), by integrating feature learning and hash-code learning into the same framework. DCMH is an end-to-end learning framework with deep neural networks, one for each modality, to perform feature learning from scratch. Experiments on two real datasets with text-image modalities show that DCMH can outperform other baselines to achieve the state-of-the-art performance in cross-modal retrieval applications.

12 pages

References in corpus (2)

• Practical and Optimal LSH for Angular Distance
• Circulant Binary Embedding

Cited by in corpus (13)

• Deep Sketch Hashing: Fast Free-hand Sketch-Based Image Retrieval
• HashGAN:Attention-aware Deep Adversarial Hashing for Cross Modal Retrieval
• Transitive Hashing Network for Heterogeneous Multimedia Retrieval
• Deep Cross-Modal Correlation Learning for Audio and Lyrics in Music Retrieval
• Zero-Shot Sketch-Image Hashing
• A New Evaluation Protocol and Benchmarking Results for Extendable Cross-media Retrieval
• Dual Asymmetric Deep Hashing Learning
• Learning Shared Semantic Space with Correlation Alignment for Cross-modal Event Retrieval
• Weakly Supervised Deep Image Hashing through Tag Embeddings
• Discriminative Cross-View Binary Representation Learning
• Triplet-Based Deep Hashing Network for Cross-Modal Retrieval
• Audio-Visual Embedding for Cross-Modal MusicVideo Retrieval through Supervised Deep CCA
• Shared Predictive Cross-Modal Deep Quantization