---
_id: '18227'
abstract:
- lang: eng
  text: Existing cross-modal hashing methods ignore the informative multimodal joint
    information and cannot fully exploit the semantic labels. In this paper, we propose
    a deep fused two-step cross-modal hashing (DFTH) framework with multiple semantic
    supervision. In the first step, DFTH learns unified hash codes for instances by
    a fusion network. Semantic label and similarity reconstruction have been introduced
    to acquire binary codes that are informative, discriminative and semantic similarity
    preserving. In the second step, two modality-specific hash networks are learned
    under the supervision of common hash codes reconstruction, label reconstruction,
    and intra-modal and inter-modal semantic similarity reconstruction. The modality-specific
    hash networks can generate semantic preserving binary codes for out-of-sample
    queries. To deal with the vanishing gradients of binarization, continuous differentiable
    tanh is introduced to approximate the discrete sign function, making the networks
    able to back-propagate by automatic gradient computation. Extensive experiments
    on MIRFlickr25K and NUS-WIDE show the superiority of DFTH over state-of-the-art
    methods.
article_processing_charge: No
article_type: original
author:
- first_name: Peipei
  full_name: Kang, Peipei
  last_name: Kang
- first_name: Zehang
  full_name: Lin, Zehang
  last_name: Lin
- first_name: Zhenguo
  full_name: Yang, Zhenguo
  last_name: Yang
- first_name: Alexander
  full_name: Bronstein, Alexander
  id: 58f3726e-7cba-11ef-ad8b-e6e8cb3904e6
  last_name: Bronstein
  orcid: 0000-0001-9699-8730
- first_name: Qing
  full_name: Li, Qing
  last_name: Li
- first_name: Wenyin
  full_name: Liu, Wenyin
  last_name: Liu
citation:
  ama: Kang P, Lin Z, Yang Z, Bronstein AM, Li Q, Liu W. Deep fused two-step cross-modal
    hashing with multiple semantic supervision. <i>Multimedia Tools and Applications</i>.
    2022;81(11):15653-15670. doi:<a href="https://doi.org/10.1007/s11042-022-12187-6">10.1007/s11042-022-12187-6</a>
  apa: Kang, P., Lin, Z., Yang, Z., Bronstein, A. M., Li, Q., &#38; Liu, W. (2022).
    Deep fused two-step cross-modal hashing with multiple semantic supervision. <i>Multimedia
    Tools and Applications</i>. Springer Nature. <a href="https://doi.org/10.1007/s11042-022-12187-6">https://doi.org/10.1007/s11042-022-12187-6</a>
  chicago: Kang, Peipei, Zehang Lin, Zhenguo Yang, Alex M. Bronstein, Qing Li, and
    Wenyin Liu. “Deep Fused Two-Step Cross-Modal Hashing with Multiple Semantic Supervision.”
    <i>Multimedia Tools and Applications</i>. Springer Nature, 2022. <a href="https://doi.org/10.1007/s11042-022-12187-6">https://doi.org/10.1007/s11042-022-12187-6</a>.
  ieee: P. Kang, Z. Lin, Z. Yang, A. M. Bronstein, Q. Li, and W. Liu, “Deep fused
    two-step cross-modal hashing with multiple semantic supervision,” <i>Multimedia
    Tools and Applications</i>, vol. 81, no. 11. Springer Nature, pp. 15653–15670,
    2022.
  ista: Kang P, Lin Z, Yang Z, Bronstein AM, Li Q, Liu W. 2022. Deep fused two-step
    cross-modal hashing with multiple semantic supervision. Multimedia Tools and Applications.
    81(11), 15653–15670.
  mla: Kang, Peipei, et al. “Deep Fused Two-Step Cross-Modal Hashing with Multiple
    Semantic Supervision.” <i>Multimedia Tools and Applications</i>, vol. 81, no.
    11, Springer Nature, 2022, pp. 15653–70, doi:<a href="https://doi.org/10.1007/s11042-022-12187-6">10.1007/s11042-022-12187-6</a>.
  short: P. Kang, Z. Lin, Z. Yang, A.M. Bronstein, Q. Li, W. Liu, Multimedia Tools
    and Applications 81 (2022) 15653–15670.
date_created: 2024-10-08T12:55:04Z
date_published: 2022-05-01T00:00:00Z
date_updated: 2024-10-14T11:10:00Z
day: '01'
doi: 10.1007/s11042-022-12187-6
extern: '1'
fulldoi: https://doi.org/10.1007/s11042-022-12187-6
intvolume: '        81'
issue: '11'
language:
- iso: eng
month: '05'
oa_version: None
page: 15653-15670
publication: Multimedia Tools and Applications
publication_identifier:
  eissn:
  - 1573-7721
  issn:
  - 1380-7501
publication_status: published
publisher: Springer Nature
quality_controlled: '1'
scopus_import: '1'
status: public
title: Deep fused two-step cross-modal hashing with multiple semantic supervision
type: journal_article
user_id: 2DF688A6-F248-11E8-B48F-1D18A9856A87
volume: 81
year: '2022'
...