Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/141944
Title: Deep variational and structural hashing
Authors: Liong, Venice Erin
Lu, Jiwen
Duan, Ling-Yu
Tan, Yap-Peng
Keywords: Engineering::Electrical and electronic engineering
Issue Date: 2020
Source: Liong, V. E., Lu, J., Duan, L.-Y., & Tan, Y.-P. (2020). Deep variational and structural hashing. IEEE transactions on pattern analysis and machine intelligence, 42(3), 580 - 595. doi:10.1109/TPAMI.2018.2882816
Journal: IEEE transactions on pattern analysis and machine intelligence
Abstract: In this paper, we propose a deep variational and structural hashing (DVStH) method to learn compact binary feature representation inside the network. Then, we design a struct layer rather than a bottleneck hash layer, to obtain binary codes through a simple encoding procedure. By doing these, we are able to obtain binary codes discriminatively and generatively. To make it applicable to cross-modal scalable multimedia retrieval, we extend our method to a cross-modal deep variational and structural hashing (CM-DVStH). We design a deep fusion network with a struct layer to maximize the correlation between image-text input pairs during the training stage so that a unified binary vector can be obtained. We then design modality-specific hashing networks to handle the out-of-sample extension scenario. Specifically, we train a network for each modality which outputs a latent representation that is as close as possible to the binary codes which are inferred from the fusion network. Experimental results on five benchmark datasets are presented to show the efficacy of the proposed approach.
URI: https://hdl.handle.net/10356/141944
ISSN: 0162-8828
DOI: 10.1109/TPAMI.2018.2882816
Rights: © 2018 IEEE. All rights reserved.
Fulltext Permission: none
Fulltext Availability: No Fulltext
Appears in Collections:IGS Journal Articles

SCOPUSTM   
Citations 10

29
Updated on Feb 2, 2023

Web of ScienceTM
Citations 10

23
Updated on Jan 29, 2023

Page view(s)

207
Updated on Feb 5, 2023

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.