Advanced search
2 files | 2.06 MB Add to list
Author
Organization
Project
Abstract
With the ever-increasing availability of data, the need for efficient and accurate image retrieval methods has become larger and larger. Deep hashing has proven to be a promising solution, by defining a hash function to convert the data into a manageable lower-dimensional representation. In this paper, we apply recent insights from the field of variational autoencoders to the field of deep image hashing, thus achieving an improvement over the current state of the art as shown by experimental evaluation. The code used in this paper is open-source and available on GitHub (https://github.com/maximverwilst/deepimagehashing-VAE)
Keywords
image hashing, deep hashing, content-based image retrieval, variational autoencoders, unsupervised deep learning, NEAREST-NEIGHBOR, QUANTIZATION, ALGORITHMS

Downloads

  • 2021167265.pdf
    • full text (Accepted manuscript)
    • |
    • open access
    • |
    • PDF
    • |
    • 684.96 KB
  • (...).pdf
    • full text (Published version)
    • |
    • UGent only
    • |
    • PDF
    • |
    • 1.38 MB

Citation

Please use this url to cite or link to this publication:

MLA
Verwilst, Maxim, et al. “Deep Image Hashing Based on Twin-Bottleneck Hashing with Variational Autoencoders.” 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), IEEE, 2021, doi:10.1109/MMSP53017.2021.9733464.
APA
Verwilst, M., Žižakić, N., Gu, L., & Pizurica, A. (2021). Deep image hashing based on twin-bottleneck hashing with variational autoencoders. 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP). Presented at the 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), Tampere, Finland. https://doi.org/10.1109/MMSP53017.2021.9733464
Chicago author-date
Verwilst, Maxim, Nina Žižakić, Lingchen Gu, and Aleksandra Pizurica. 2021. “Deep Image Hashing Based on Twin-Bottleneck Hashing with Variational Autoencoders.” In 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP). IEEE. https://doi.org/10.1109/MMSP53017.2021.9733464.
Chicago author-date (all authors)
Verwilst, Maxim, Nina Žižakić, Lingchen Gu, and Aleksandra Pizurica. 2021. “Deep Image Hashing Based on Twin-Bottleneck Hashing with Variational Autoencoders.” In 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP). IEEE. doi:10.1109/MMSP53017.2021.9733464.
Vancouver
1.
Verwilst M, Žižakić N, Gu L, Pizurica A. Deep image hashing based on twin-bottleneck hashing with variational autoencoders. In: 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP). IEEE; 2021.
IEEE
[1]
M. Verwilst, N. Žižakić, L. Gu, and A. Pizurica, “Deep image hashing based on twin-bottleneck hashing with variational autoencoders,” in 2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP), Tampere, Finland, 2021.
@inproceedings{8716990,
  abstract     = {{With the ever-increasing availability of data, the need for efficient and accurate image retrieval methods has become larger and larger. Deep hashing has proven to be a promising solution, by defining a hash function to convert the data into a manageable lower-dimensional representation. In this paper, we apply recent insights from the field of variational autoencoders to the field of deep image hashing, thus achieving an improvement over the current state of the art as shown by experimental evaluation. The code used in this paper is open-source and available on GitHub (https://github.com/maximverwilst/deepimagehashing-VAE)}},
  author       = {{Verwilst, Maxim and Žižakić, Nina and Gu, Lingchen and Pizurica, Aleksandra}},
  booktitle    = {{2021 IEEE 23rd International Workshop on Multimedia Signal Processing (MMSP)}},
  isbn         = {{9781665432887}},
  issn         = {{2163-3517}},
  keywords     = {{image hashing,deep hashing,content-based image retrieval,variational autoencoders,unsupervised deep learning,NEAREST-NEIGHBOR,QUANTIZATION,ALGORITHMS}},
  language     = {{eng}},
  location     = {{Tampere, Finland}},
  pages        = {{6}},
  publisher    = {{IEEE}},
  title        = {{Deep image hashing based on twin-bottleneck hashing with variational autoencoders}},
  url          = {{http://doi.org/10.1109/MMSP53017.2021.9733464}},
  year         = {{2021}},
}

Altmetric
View in Altmetric
Web of Science
Times cited: