King's College London

Research portal

Database Saliency for Fast Image Retrieval

Research output: Contribution to journalArticlepeer-review

Standard

Database Saliency for Fast Image Retrieval. / Gao, Yuan; Shi, Miaojing; Tao, Dacheng et al.

In: IEEE TRANSACTIONS ON MULTIMEDIA, Vol. 17, No. 3, 31.03.2015, p. 359 - 369.

Research output: Contribution to journalArticlepeer-review

Harvard

Gao, Y, Shi, M, Tao, D & Xu, C 2015, 'Database Saliency for Fast Image Retrieval', IEEE TRANSACTIONS ON MULTIMEDIA, vol. 17, no. 3, pp. 359 - 369. https://doi.org/10.1109/TMM.2015.2389616

APA

Gao, Y., Shi, M., Tao, D., & Xu, C. (2015). Database Saliency for Fast Image Retrieval. IEEE TRANSACTIONS ON MULTIMEDIA, 17(3), 359 - 369. https://doi.org/10.1109/TMM.2015.2389616

Vancouver

Gao Y, Shi M, Tao D, Xu C. Database Saliency for Fast Image Retrieval. IEEE TRANSACTIONS ON MULTIMEDIA. 2015 Mar 31;17(3):359 - 369. https://doi.org/10.1109/TMM.2015.2389616

Author

Gao, Yuan ; Shi, Miaojing ; Tao, Dacheng et al. / Database Saliency for Fast Image Retrieval. In: IEEE TRANSACTIONS ON MULTIMEDIA. 2015 ; Vol. 17, No. 3. pp. 359 - 369.

Bibtex Download

@article{ba736566891440b586430081b9e15d77,
title = "Database Saliency for Fast Image Retrieval",
abstract = "The bag-of-visual-words (BoW) model is effective for representing images and videos in many computer vision problems, and achieves promising performance in image retrieval. Nevertheless, the level of retrieval efficiency in a large-scale database is not acceptable for practical usage. Considering that the relevant images in the database of a given query are more likely to be distinctive than ambiguous, this paper defines “database saliency” as the distinctiveness score calculated for every image to measure its overall “saliency” in the database. By taking advantage of database saliency, we propose a saliency- inspired fast image retrieval scheme, S-sim, which significantly improves efficiency while retains state-of-the-art accuracy in image retrieval . There are two stages in S-sim: the bottom-up saliency mechanism computes the database saliency value of each image by hierarchically decomposing a posterior probability into local patches and visual words, the concurrent information of visual words is then bottom-up propagated to estimate the distinctiveness, and the top-down saliency mechanism discriminatively expands the query via a very low-dimensional linear SVM trained on the top-ranked images after initial search, ranking images are then sorted on their distances to the decision boundary as well as the database saliency values. We comprehensively evaluate S-sim on common retrieval benchmarks, e.g., Oxford and Paris datasets. Thorough experiments suggest that, because of the offline database saliency computation and online low-dimensional SVM, our approach significantly speeds up online retrieval and outperforms the state-of-the-art BoW-based image retrieval schemes.",
author = "Yuan Gao and Miaojing Shi and Dacheng Tao and Chao Xu",
year = "2015",
month = mar,
day = "31",
doi = "10.1109/TMM.2015.2389616",
language = "English",
volume = "17",
pages = "359 -- 369",
journal = "IEEE TRANSACTIONS ON MULTIMEDIA",
issn = "1520-9210",
publisher = "Institute of Electrical and Electronics Engineers Inc.",
number = "3",

}

RIS (suitable for import to EndNote) Download

TY - JOUR

T1 - Database Saliency for Fast Image Retrieval

AU - Gao, Yuan

AU - Shi, Miaojing

AU - Tao, Dacheng

AU - Xu, Chao

PY - 2015/3/31

Y1 - 2015/3/31

N2 - The bag-of-visual-words (BoW) model is effective for representing images and videos in many computer vision problems, and achieves promising performance in image retrieval. Nevertheless, the level of retrieval efficiency in a large-scale database is not acceptable for practical usage. Considering that the relevant images in the database of a given query are more likely to be distinctive than ambiguous, this paper defines “database saliency” as the distinctiveness score calculated for every image to measure its overall “saliency” in the database. By taking advantage of database saliency, we propose a saliency- inspired fast image retrieval scheme, S-sim, which significantly improves efficiency while retains state-of-the-art accuracy in image retrieval . There are two stages in S-sim: the bottom-up saliency mechanism computes the database saliency value of each image by hierarchically decomposing a posterior probability into local patches and visual words, the concurrent information of visual words is then bottom-up propagated to estimate the distinctiveness, and the top-down saliency mechanism discriminatively expands the query via a very low-dimensional linear SVM trained on the top-ranked images after initial search, ranking images are then sorted on their distances to the decision boundary as well as the database saliency values. We comprehensively evaluate S-sim on common retrieval benchmarks, e.g., Oxford and Paris datasets. Thorough experiments suggest that, because of the offline database saliency computation and online low-dimensional SVM, our approach significantly speeds up online retrieval and outperforms the state-of-the-art BoW-based image retrieval schemes.

AB - The bag-of-visual-words (BoW) model is effective for representing images and videos in many computer vision problems, and achieves promising performance in image retrieval. Nevertheless, the level of retrieval efficiency in a large-scale database is not acceptable for practical usage. Considering that the relevant images in the database of a given query are more likely to be distinctive than ambiguous, this paper defines “database saliency” as the distinctiveness score calculated for every image to measure its overall “saliency” in the database. By taking advantage of database saliency, we propose a saliency- inspired fast image retrieval scheme, S-sim, which significantly improves efficiency while retains state-of-the-art accuracy in image retrieval . There are two stages in S-sim: the bottom-up saliency mechanism computes the database saliency value of each image by hierarchically decomposing a posterior probability into local patches and visual words, the concurrent information of visual words is then bottom-up propagated to estimate the distinctiveness, and the top-down saliency mechanism discriminatively expands the query via a very low-dimensional linear SVM trained on the top-ranked images after initial search, ranking images are then sorted on their distances to the decision boundary as well as the database saliency values. We comprehensively evaluate S-sim on common retrieval benchmarks, e.g., Oxford and Paris datasets. Thorough experiments suggest that, because of the offline database saliency computation and online low-dimensional SVM, our approach significantly speeds up online retrieval and outperforms the state-of-the-art BoW-based image retrieval schemes.

U2 - 10.1109/TMM.2015.2389616

DO - 10.1109/TMM.2015.2389616

M3 - Article

VL - 17

SP - 359

EP - 369

JO - IEEE TRANSACTIONS ON MULTIMEDIA

JF - IEEE TRANSACTIONS ON MULTIMEDIA

SN - 1520-9210

IS - 3

ER -

View graph of relations

© 2020 King's College London | Strand | London WC2R 2LS | England | United Kingdom | Tel +44 (0)20 7836 5454