Rights statement: ©2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
Accepted author manuscript, 3.09 MB, PDF document
Available under license: CC BY-NC: Creative Commons Attribution-NonCommercial 4.0 International License
Final published version
Research output: Contribution to Journal/Magazine › Journal article › peer-review
Research output: Contribution to Journal/Magazine › Journal article › peer-review
}
TY - JOUR
T1 - Joint Image-Text Hashing for Fast Large-Scale Cross-Media Retrieval Using Self-Supervised Deep Learning
AU - Wu, Gengshen
AU - Han, Jungong
AU - Lin, Zijia
AU - Ding, Guiguang
AU - Zhang, Baochang
AU - Ni, Qiang
N1 - ©2018 IEEE. Personal use of this material is permitted. However, permission to reprint/republish this material for advertising or promotional purposes or for creating new collective works for resale or redistribution to servers or lists, or to reuse any copyrighted component of this work in other works must be obtained from the IEEE.
PY - 2019/12/1
Y1 - 2019/12/1
N2 - Recent years have witnessed the promising future of hashing in the industrial applications for fast similarity retrieval. In this paper, we propose a novel supervised hashing method for large-scale cross-media search, termed Self-Supervised Deep Multimodal Hashing (SSDMH), which learns unified hash codes as well as deep hash functions for different modalities in a self-supervised manner. With the proposed regularized binary latent model, unified binary codes can be solved directly without relaxation strategy while retaining the neighborhood structures by the graph regularization term. Moreover, we propose a new discrete optimization solution, termed as Binary Gradient Descent, which aims at improving the optimization efficiency towards real-time operation. Extensive experiments on three benchmark datasets demonstrate the superiority of SSDMH over state-of-the-art cross-media hashing approaches.
AB - Recent years have witnessed the promising future of hashing in the industrial applications for fast similarity retrieval. In this paper, we propose a novel supervised hashing method for large-scale cross-media search, termed Self-Supervised Deep Multimodal Hashing (SSDMH), which learns unified hash codes as well as deep hash functions for different modalities in a self-supervised manner. With the proposed regularized binary latent model, unified binary codes can be solved directly without relaxation strategy while retaining the neighborhood structures by the graph regularization term. Moreover, we propose a new discrete optimization solution, termed as Binary Gradient Descent, which aims at improving the optimization efficiency towards real-time operation. Extensive experiments on three benchmark datasets demonstrate the superiority of SSDMH over state-of-the-art cross-media hashing approaches.
U2 - 10.1109/TIE.2018.2873547
DO - 10.1109/TIE.2018.2873547
M3 - Journal article
VL - 66
SP - 9868
EP - 9877
JO - IEEE Transactions on Industrial Electronics
JF - IEEE Transactions on Industrial Electronics
SN - 0278-0046
IS - 12
ER -