By the same authors

From the same journal

Cross-modal Hashing with Semantic Deep Embedding

Research output: Contribution to journalArticle

Standard

Cross-modal Hashing with Semantic Deep Embedding. / Yan, Cheng; Bai, Xiao; Wang, Shuai; Zhou, Jun; Hancock, Edwin R.

In: Neurocomputing, 23.01.2019.

Research output: Contribution to journalArticle

Harvard

Yan, C, Bai, X, Wang, S, Zhou, J & Hancock, ER 2019, 'Cross-modal Hashing with Semantic Deep Embedding', Neurocomputing. https://doi.org/10.1016/j.neucom.2019.01.040

APA

Yan, C., Bai, X., Wang, S., Zhou, J., & Hancock, E. R. (2019). Cross-modal Hashing with Semantic Deep Embedding. Neurocomputing. https://doi.org/10.1016/j.neucom.2019.01.040

Vancouver

Yan C, Bai X, Wang S, Zhou J, Hancock ER. Cross-modal Hashing with Semantic Deep Embedding. Neurocomputing. 2019 Jan 23. https://doi.org/10.1016/j.neucom.2019.01.040

Author

Yan, Cheng ; Bai, Xiao ; Wang, Shuai ; Zhou, Jun ; Hancock, Edwin R. / Cross-modal Hashing with Semantic Deep Embedding. In: Neurocomputing. 2019.

Bibtex - Download

@article{0a59ce90a08d432eae747e2f1968c739,
title = "Cross-modal Hashing with Semantic Deep Embedding",
abstract = "Cross-modal hashing has demonstrated advantages on fast retrieval tasks. It improves the quality of hash coding by exploiting semantic correlation across different modalities. In supervised cross-modal hashing, the learning of hash function replies on the quality of extracted features, for which deep learning models have been adopted to replace the traditional models based on handcraft features. All deep methods, however, have not sufficiently explored semantic correlation of modalities for the hashing process. In this paper, we introduce a novel end-to-end deep cross-modal hashing framework which integrates feature and hash-code learning into the same network. We take both between and within modalities data correlation into consideration, and propose a novel network structure and a loss function with dual semantic supervision for hash learning. This method ensures that the generated binary codes keep the semantic relationship of the original data points. Cross-modal retrieval experiments on commonly used benchmark datasets show that our method yields substantial performance improvement over several state-of-the-art hashing methods.",
keywords = "Cross-modal, Deep Hashing, Retrieval, Semantic Embedding",
author = "Cheng Yan and Xiao Bai and Shuai Wang and Jun Zhou and Hancock, {Edwin R.}",
note = "{\circledC} 2019 Elsevier B.V. All rights reserved. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy.",
year = "2019",
month = "1",
day = "23",
doi = "10.1016/j.neucom.2019.01.040",
language = "English",
journal = "Neurocomputing",
issn = "0925-2312",
publisher = "Elsevier",

}

RIS (suitable for import to EndNote) - Download

TY - JOUR

T1 - Cross-modal Hashing with Semantic Deep Embedding

AU - Yan, Cheng

AU - Bai, Xiao

AU - Wang, Shuai

AU - Zhou, Jun

AU - Hancock, Edwin R.

N1 - © 2019 Elsevier B.V. All rights reserved. This is an author-produced version of the published paper. Uploaded in accordance with the publisher’s self-archiving policy.

PY - 2019/1/23

Y1 - 2019/1/23

N2 - Cross-modal hashing has demonstrated advantages on fast retrieval tasks. It improves the quality of hash coding by exploiting semantic correlation across different modalities. In supervised cross-modal hashing, the learning of hash function replies on the quality of extracted features, for which deep learning models have been adopted to replace the traditional models based on handcraft features. All deep methods, however, have not sufficiently explored semantic correlation of modalities for the hashing process. In this paper, we introduce a novel end-to-end deep cross-modal hashing framework which integrates feature and hash-code learning into the same network. We take both between and within modalities data correlation into consideration, and propose a novel network structure and a loss function with dual semantic supervision for hash learning. This method ensures that the generated binary codes keep the semantic relationship of the original data points. Cross-modal retrieval experiments on commonly used benchmark datasets show that our method yields substantial performance improvement over several state-of-the-art hashing methods.

AB - Cross-modal hashing has demonstrated advantages on fast retrieval tasks. It improves the quality of hash coding by exploiting semantic correlation across different modalities. In supervised cross-modal hashing, the learning of hash function replies on the quality of extracted features, for which deep learning models have been adopted to replace the traditional models based on handcraft features. All deep methods, however, have not sufficiently explored semantic correlation of modalities for the hashing process. In this paper, we introduce a novel end-to-end deep cross-modal hashing framework which integrates feature and hash-code learning into the same network. We take both between and within modalities data correlation into consideration, and propose a novel network structure and a loss function with dual semantic supervision for hash learning. This method ensures that the generated binary codes keep the semantic relationship of the original data points. Cross-modal retrieval experiments on commonly used benchmark datasets show that our method yields substantial performance improvement over several state-of-the-art hashing methods.

KW - Cross-modal, Deep Hashing, Retrieval, Semantic Embedding

U2 - 10.1016/j.neucom.2019.01.040

DO - 10.1016/j.neucom.2019.01.040

M3 - Article

JO - Neurocomputing

JF - Neurocomputing

SN - 0925-2312

ER -