Multi-Order Adversarial Representation Learning for Composed Query Image Retrieval

Fu, Z; Chen, X; Dong, J; Ji, S

Multi-Order Adversarial Representation Learning for Composed Query Image Retrieval

Fu, Z Chen, X

Dong, J Ji, S

Permalink

Publisher:: IEEE
Publication Type:: Conference Proceeding
Citation:: ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, 00, pp. 1685-1689
Issue Date:: 2021-05-13

Closed Access

	Filename	Description	Size
	Multi-Order_Adversarial_Representation_Learning_for_Composed_Query_Image_Retrieval.pdf	Published version	3.27 MB	Adobe PDF	View/Open

Copyright Clearance Process

Recently Added
In Progress
Closed Access

This item is closed access and not available.

Full metadata record

Field	Value	Language
dc.contributor.author	Fu, Z
dc.contributor.author	Chen, X https://orcid.org/0000-0002-5517-7255
dc.contributor.author	Dong, J
dc.contributor.author	Ji, S
dc.date	2021-06-06
dc.date.accessioned	2022-06-11T00:21:26Z
dc.date.available	2022-06-11T00:21:26Z
dc.date.issued	2021-05-13
dc.identifier.citation	ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP), 2021, 00, pp. 1685-1689
dc.identifier.uri	http://hdl.handle.net/10453/158090
dc.description.abstract	This paper targets at a task of composed query image retrieval. Given a composed query consists of a reference image and modification text, the task aims to retrieve images which are generally similar to the reference image but differ according to the given modification text. The task is challenging, due to the complexity of the composed query and cross-modality characteristics between the query and candidate images. The common paradigm for the task is to first obtain fused feature of the reference image and the text, and further project them into a common embedding space with candidate images. However, the majority of works usually only aim for the representation of high level, ignoring the low-level representation which may be complementary to the high-level representation. So this paper proposes a new Multi-order Adversarial Network (MAN) which uses multilevel representations and simultaneously explores their low-order and high-order interactions, obtaining low-order and high-order features. The low-order features reflect the pattern of itself and high-order features contains the interaction between features. Moreover, we further introduce an adversarial module to constrain the fusion of the reference image and the text. Extensive experiments on three datasets verify the effectiveness of our MAN and also demonstrate its state-of-the-art performance.
dc.language	en
dc.publisher	IEEE
dc.relation.ispartof	ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing (ICASSP)
dc.relation.ispartof	ICASSP 2021 - 2021 IEEE International Conference on Acoustics, Speech and Signal Processing
dc.relation.isbasedon	10.1109/icassp39728.2021.9414436
dc.rights	info:eu-repo/semantics/closedAccess
dc.title	Multi-Order Adversarial Representation Learning for Composed Query Image Retrieval
dc.type	Conference Proceeding
utslib.citation.volume	00
utslib.location.activity	Toronto, ON, Canada
pubs.organisational-group	/University of Technology Sydney
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology
pubs.organisational-group	/University of Technology Sydney/Faculty of Engineering and Information Technology/School of Computer Science
utslib.copyright.status	closed_access	*
dc.date.updated	2022-06-11T00:21:24Z
pubs.finish-date	2021-06-11
pubs.publication-status	Published
pubs.start-date	2021-06-06
pubs.volume	00

Abstract:

This paper targets at a task of composed query image retrieval. Given a composed query consists of a reference image and modification text, the task aims to retrieve images which are generally similar to the reference image but differ according to the given modification text. The task is challenging, due to the complexity of the composed query and cross-modality characteristics between the query and candidate images. The common paradigm for the task is to first obtain fused feature of the reference image and the text, and further project them into a common embedding space with candidate images. However, the majority of works usually only aim for the representation of high level, ignoring the low-level representation which may be complementary to the high-level representation. So this paper proposes a new Multi-order Adversarial Network (MAN) which uses multilevel representations and simultaneously explores their low-order and high-order interactions, obtaining low-order and high-order features. The low-order features reflect the pattern of itself and high-order features contains the interaction between features. Moreover, we further introduce an adversarial module to constrain the fusion of the reference image and the text. Extensive experiments on three datasets verify the effectiveness of our MAN and also demonstrate its state-of-the-art performance.

Please use this identifier to cite or link to this item:

http://hdl.handle.net/10453/158090