• Home
  • Search
  • Dual-Level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval
  • Open Access IconOpen Access
  • Cite Icon48
  • https://doi.org/10.1109/tcsvt.2020.3001583Copy DOI Icon

Dual-Level Semantic Transfer Deep Hashing for Efficient Social Image Retrieval

  • Abstract
  • Literature Map
  • References
  • Citations
  • Similar Papers
Abstract

Social network stores and disseminates a tremendous amount of user shared images. Deep hashing is an efficient indexing technique to support large-scale social image retrieval, due to its deep representation capability, fast retrieval speed and low storage cost. Particularly, unsupervised deep hashing has well scalability as it does not require any manually labelled data for training. However, owing to the lacking of label guidance, existing methods suffer from severe semantic shortage when optimizing a large amount of deep neural network parameters. Differently, in this paper, we propose a <italic xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">Dual-level Semantic Transfer Deep Hashing</i> (DSTDH) method to alleviate this problem with a unified deep hash learning framework. Our model targets at learning the semantically enhanced deep hash codes by specially exploiting the user-generated tags associated with the social images. Specifically, we design a complementary dual-level semantic transfer mechanism to efficiently discover the potential semantics of tags and seamlessly transfer them into binary hash codes. On the one hand, instance-level semantics are directly preserved into hash codes from the associated tags with adverse noise removing. Besides, an image-concept hypergraph is constructed for indirectly transferring the latent high-order semantic correlations of images and tags into hash codes. Moreover, the hash codes are obtained simultaneously with the deep representation learning by the discrete hash optimization strategy. Extensive experiments on two public social image retrieval datasets validate the superior performance of our method compared with state-of-the-art hashing methods. The source codes of our method can be obtained at <uri xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">https://github.com/research2020-1/DSTDH</uri>

Similar Papers
  • Research Article
  • Citations180

Scalable Deep Hashing for Large-scale Social Image Retrieval.

  • Sep 16, 2019
  • IEEE Transactions on Image Processing
  • Hui Cui +4
  • Conference Article

Deep Captioning Hashing Network for Complex Scene Image Retrieval

  • Nov 01, 2019
  • Song Liu +5
  • Research Article
  • Citations60

Adaptive Partial Multi-View Hashing for Efficient Social Image Retrieval

  • Nov 11, 2020
  • IEEE Transactions on Multimedia
  • Chaoqun Zheng +4
  • Research Article
  • Citations15

Semantic Cluster Unary Loss for Efficient Deep Hashing.

  • May 15, 2018
  • IEEE Transactions on Image Processing
  • Shifeng Zhang +2
  • Research Article
  • Citations9

Unsupervised Discriminative Deep Hashing With Locality and Globality Preservation

  • Jan 01, 2021
  • IEEE Signal Processing Letters
  • Zhuyi Ni +4
  • Research Article
  • Citations4

Deep Hashing with Semantic Hash Centers for Image Retrieval

  • Jul 23, 2025
  • ACM Transactions on Information Systems
  • Li Chen +5
  • Research Article
  • Citations21

Deep multi-negative supervised hashing for large-scale image retrieval

  • Nov 22, 2024
  • Expert Systems With Applications
  • Yingfan Liu +5
  • Research Article
  • Citations37

Supervised deep hashing with a joint deep network

  • May 07, 2020
  • Pattern Recognition
  • Yaxiong Chen +2
  • Conference Article
  • Citations1

Performance Comparison of Unsupervised Deep Hashing with Data-independent Hashing for Content-Based Audio Retrieval

  • Apr 13, 2019
  • Petcharat Panyapanuwat +1
  • PDF
  • Research Article
  • Citations2

Triplet Deep Hashing with Joint Supervised Loss Based on Deep Neural Networks

  • Oct 09, 2019
  • Computational Intelligence and Neuroscience
  • Mingyong Li +4
  • Research Article
  • Citations4

Deep hashing with top similarity preserving for image retrieval

  • Feb 08, 2018
  • Multimedia Tools and Applications
  • Qiang Li +3
  • Research Article
  • Citations5

Asymmetric deep hashing for person re-identifications

  • Apr 01, 2022
  • Tsinghua Science and Technology
  • Yali Zhao +2
  • Research Article
  • Citations27

Supervised Deep Hashing for Hierarchical Labeled Data

  • Apr 27, 2018
  • Proceedings of the AAAI Conference on Artificial Intelligence
  • Dan Wang +6
  • Conference Article
  • Citations4

Graph Regularized Unsupervised Deep Hashing for Large Scale Image Retrieval

  • May 01, 2020
  • Shuying Yu +2
  • Conference Article
  • Citations18

Asymmetric Deep Hashing for Efficient Hash Code Compression

  • Oct 12, 2020
  • Shu Zhao +5
Cactus Communications logo

Copyright 2026 Cactus Communications. All rights reserved.