Transitive Hashing Network for Heterogeneous Multimedia Retrieval

Abstract

Hashing has been widely applied to large-scale multimedia retrieval due to the storage and retrieval efficiency. Cross-modal hashing enables efficient retrieval from database of one modality in response to a query of another modality. Existing work on cross-modal hashing assumes heterogeneous relationship across modalities for hash function learning. In this paper, we relax the strong assumption by only requiring such heterogeneous relationship in an auxiliary dataset different from the query/database domain. We craft a hybrid deep architecture to simultaneously learn the cross-modal correlation from the auxiliary dataset, and align the dataset distributions between the auxiliary dataset and the query/database domain, which generates transitive hash codes for heterogeneous multimedia retrieval. Extensive experiments exhibit that the proposed approach yields state of the art multimedia retrieval performance on public datasets, i.e. NUS-WIDE, ImageNet-YahooQA.

References in corpus (4)

• DeCAF: A Deep Convolutional Activation Feature for Generic Visual Recognition
• Unifying Visual-Semantic Embeddings with Multimodal Neural Language Models
• Simultaneous Feature Learning and Hash Coding with Deep Neural Networks
• Deep Cross-Modal Hashing

Cited by in corpus (6)

• A Revisit on Deep Hashings for Large-scale Content Based Image Retrieval
• MHTN: Modal-adversarial Hybrid Transfer Network for Cross-modal Retrieval
• Deep Cross-media Knowledge Transfer
• Feature Level Fusion from Facial Attributes for Face Recognition
• Discriminative Cross-View Binary Representation Learning
• Error-Corrected Margin-Based Deep Cross-Modal Hashing for Facial Image Retrieval