FAemb: a function approximation-based embedding method for image retrieval

Thanh-Toan Do; Quang D. Tran; Ngai Man Cheung

doi:10.1109/CVPR.2015.7298978

FAemb: a function approximation-based embedding method for image retrieval

Thanh-Toan Do, Quang D. Tran, Ngai Man Cheung

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

25 Citations (Scopus)

Abstract

The objective of this paper is to design an embedding method mapping local features describing image (e.g. SIFT) to a higher dimensional representation used for image retrieval problem. By investigating the relationship between the linear approximation of a nonlinear function in high dimensional space and state-of-the-art feature representation used in image retrieval, i.e., VLAD, we first introduce a new approach for the approximation. The embedded vectors resulted by the function approximation process are then aggregated to form a single representation used in the image retrieval framework. The evaluation shows that our embedding method gives a performance boost over the state of the art in image retrieval, as demonstrated by our experiments on the standard public image retrieval benchmarks.

Original language	English
Title of host publication	2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)
Editors	Kristen Grauman, Erik Learned-Miller, Antonio Torralba, Andrew Zisserman
Place of Publication	Piscataway NJ USA
Publisher	IEEE, Institute of Electrical and Electronics Engineers
Pages	3556-3564
Number of pages	9
ISBN (Electronic)	9781467369640, 9781467369633
DOIs	https://doi.org/10.1109/CVPR.2015.7298978
Publication status	Published - 2015
Externally published	Yes
Event	IEEE Conference on Computer Vision and Pattern Recognition 2015 - Hynes Convention Center, Boston, United States of America Duration: 7 Jun 2015 → 12 Jun 2015 http://www.pamitc.org/cvpr15/ (Website) https://ieeexplore.ieee.org/xpl/conhome/7293313/proceeding (Proceedings)

Publication series

Name	Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition
Volume	07-12-June-2015
ISSN (Print)	1063-6919
ISSN (Electronic)	1063-6919

Conference

Conference	IEEE Conference on Computer Vision and Pattern Recognition 2015
Abbreviated title	CVPR 2015
Country/Territory	United States of America
City	Boston
Period	7/06/15 → 12/06/15
Internet address	http://www.pamitc.org/cvpr15/ (Website) https://ieeexplore.ieee.org/xpl/conhome/7293313/proceeding (Proceedings)

Access to Document

10.1109/CVPR.2015.7298978

Cite this

Do, T.-T., Tran, Q. D., & Cheung, N. M. (2015). FAemb: a function approximation-based embedding method for image retrieval. In K. Grauman, E. Learned-Miller, A. Torralba, & A. Zisserman (Eds.), 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR) (pp. 3556-3564). (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015). IEEE, Institute of Electrical and Electronics Engineers. https://doi.org/10.1109/CVPR.2015.7298978

Do, Thanh-Toan ; Tran, Quang D. ; Cheung, Ngai Man. / FAemb : a function approximation-based embedding method for image retrieval. 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). editor / Kristen Grauman ; Erik Learned-Miller ; Antonio Torralba ; Andrew Zisserman. Piscataway NJ USA : IEEE, Institute of Electrical and Electronics Engineers, 2015. pp. 3556-3564 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition).

@inproceedings{eab8845f66584a8ea7ee6ff011d96a88,

title = "FAemb: a function approximation-based embedding method for image retrieval",

abstract = "The objective of this paper is to design an embedding method mapping local features describing image (e.g. SIFT) to a higher dimensional representation used for image retrieval problem. By investigating the relationship between the linear approximation of a nonlinear function in high dimensional space and state-of-the-art feature representation used in image retrieval, i.e., VLAD, we first introduce a new approach for the approximation. The embedded vectors resulted by the function approximation process are then aggregated to form a single representation used in the image retrieval framework. The evaluation shows that our embedding method gives a performance boost over the state of the art in image retrieval, as demonstrated by our experiments on the standard public image retrieval benchmarks.",

author = "Thanh-Toan Do and Tran, {Quang D.} and Cheung, {Ngai Man}",

year = "2015",

doi = "10.1109/CVPR.2015.7298978",

language = "English",

series = "Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition",

publisher = "IEEE, Institute of Electrical and Electronics Engineers",

pages = "3556--3564",

editor = "Grauman, {Kristen } and Learned-Miller, {Erik } and Torralba, {Antonio } and Zisserman, {Andrew }",

booktitle = "2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)",

address = "United States of America",

note = "IEEE Conference on Computer Vision and Pattern Recognition 2015, CVPR 2015 ; Conference date: 07-06-2015 Through 12-06-2015",

url = "http://www.pamitc.org/cvpr15/, https://ieeexplore.ieee.org/xpl/conhome/7293313/proceeding",

}

Do, T-T, Tran, QD & Cheung, NM 2015, FAemb: a function approximation-based embedding method for image retrieval. in K Grauman, E Learned-Miller, A Torralba & A Zisserman (eds), 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition, vol. 07-12-June-2015, IEEE, Institute of Electrical and Electronics Engineers, Piscataway NJ USA, pp. 3556-3564, IEEE Conference on Computer Vision and Pattern Recognition 2015, Boston, Massachusetts, United States of America, 7/06/15. https://doi.org/10.1109/CVPR.2015.7298978

FAemb: a function approximation-based embedding method for image retrieval. / Do, Thanh-Toan; Tran, Quang D.; Cheung, Ngai Man.
2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). ed. / Kristen Grauman; Erik Learned-Miller; Antonio Torralba; Andrew Zisserman. Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers, 2015. p. 3556-3564 (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition; Vol. 07-12-June-2015).

Research output: Chapter in Book/Report/Conference proceeding › Conference Paper › Research › peer-review

TY - GEN

T1 - FAemb

T2 - IEEE Conference on Computer Vision and Pattern Recognition 2015

AU - Do, Thanh-Toan

AU - Tran, Quang D.

AU - Cheung, Ngai Man

PY - 2015

Y1 - 2015

N2 - The objective of this paper is to design an embedding method mapping local features describing image (e.g. SIFT) to a higher dimensional representation used for image retrieval problem. By investigating the relationship between the linear approximation of a nonlinear function in high dimensional space and state-of-the-art feature representation used in image retrieval, i.e., VLAD, we first introduce a new approach for the approximation. The embedded vectors resulted by the function approximation process are then aggregated to form a single representation used in the image retrieval framework. The evaluation shows that our embedding method gives a performance boost over the state of the art in image retrieval, as demonstrated by our experiments on the standard public image retrieval benchmarks.

AB - The objective of this paper is to design an embedding method mapping local features describing image (e.g. SIFT) to a higher dimensional representation used for image retrieval problem. By investigating the relationship between the linear approximation of a nonlinear function in high dimensional space and state-of-the-art feature representation used in image retrieval, i.e., VLAD, we first introduce a new approach for the approximation. The embedded vectors resulted by the function approximation process are then aggregated to form a single representation used in the image retrieval framework. The evaluation shows that our embedding method gives a performance boost over the state of the art in image retrieval, as demonstrated by our experiments on the standard public image retrieval benchmarks.

UR - http://www.scopus.com/inward/record.url?scp=84959181422&partnerID=8YFLogxK

U2 - 10.1109/CVPR.2015.7298978

DO - 10.1109/CVPR.2015.7298978

M3 - Conference Paper

AN - SCOPUS:84959181422

T3 - Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition

SP - 3556

EP - 3564

BT - 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR)

A2 - Grauman, Kristen

A2 - Learned-Miller, Erik

A2 - Torralba, Antonio

A2 - Zisserman, Andrew

PB - IEEE, Institute of Electrical and Electronics Engineers

CY - Piscataway NJ USA

Y2 - 7 June 2015 through 12 June 2015

ER -

Do TT, Tran QD, Cheung NM. FAemb: a function approximation-based embedding method for image retrieval. In Grauman K, Learned-Miller E, Torralba A, Zisserman A, editors, 2015 IEEE Conference on Computer Vision and Pattern Recognition (CVPR). Piscataway NJ USA: IEEE, Institute of Electrical and Electronics Engineers. 2015. p. 3556-3564. (Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition). doi: 10.1109/CVPR.2015.7298978

FAemb: a function approximation-based embedding method for image retrieval

Abstract

Publication series

Conference

Access to Document

Other files and links

Cite this