Database Saliency for Fast Image Retrieval
- Submitting institution
-
King's College London
- Unit of assessment
- 11 - Computer Science and Informatics
- Output identifier
- 128738707
- Type
- D - Journal article
- DOI
-
10.1109/TMM.2015.2389616
- Title of journal
- IEEE TRANSACTIONS ON MULTIMEDIA
- Article number
- -
- First page
- 359
- Volume
- 17
- Issue
- 3
- ISSN
- 1520-9210
- Open access status
- Out of scope for open access requirements
- Month of publication
- January
- Year of publication
- 2015
- URL
-
-
- Supplementary information
-
-
- Request cross-referral to
- -
- Output has been delayed by COVID-19
- No
- COVID-19 affected output statement
- -
- Forensic science
- No
- Criminology
- No
- Interdisciplinary
- No
- Number of additional authors
-
3
- Research group(s)
-
-
- Citation count
- 46
- Proposed double-weighted
- No
- Reserve for an output with double weighting
- No
- Additional information
- This paper defines a new perspective of visual saliency in databases by formulating the co-occurrence of visual features in the Bag-of-Words model [Philbin-Chum-Isard CVPR 2007] and integrating it into image reranking. The algorithm is mostly computed offline and thus significantly improves the efficiency of online image re-ranking compared to the state-of-the-art (online time reduced by two orders of magnitude). This paper was recognized as a representative work of using saliency for image retrieval in many subsequent works, e.g., [Nguyen-Zhao-Yan IJCV2017], [Cong-Let-Fu TIP2018], [Ren-Lu-Zhang TMM2020]. The initial idea of this paper was patented (google.patent CN102799614A).
- Author contribution statement
- -
- Non-English
- No
- English abstract
- -