Please use this identifier to cite or link to this item:
https://doi.org/10.1109/CVPR.2011.5995528
DC Field | Value | |
---|---|---|
dc.title | Image retrieval with geometry-preserving visual phrases | |
dc.contributor.author | Zhang Y. | |
dc.contributor.author | Jia Z. | |
dc.contributor.author | Chen T. | |
dc.date.accessioned | 2018-08-21T04:59:32Z | |
dc.date.available | 2018-08-21T04:59:32Z | |
dc.date.issued | 2011 | |
dc.identifier.citation | Zhang Y., Jia Z., Chen T. (2011). Image retrieval with geometry-preserving visual phrases. Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition : 809-816. ScholarBank@NUS Repository. https://doi.org/10.1109/CVPR.2011.5995528 | |
dc.identifier.isbn | 9781457703942 | |
dc.identifier.issn | 10636919 | |
dc.identifier.uri | http://scholarbank.nus.edu.sg/handle/10635/146155 | |
dc.description.abstract | The most popular approach to large scale image retrieval is based on the bag-of-visual-word (BoV) representation of images. The spatial information is usually re-introduced as a post-processing step to re-rank the retrieved images, through a spatial verification like RANSAC. Since the spatial verification techniques are computationally expensive, they can be applied only to the top images in the initial ranking. In this paper, we propose an approach that can encode more spatial information into BoV representation and that is efficient enough to be applied to large-scale databases. Other works pursuing the same purpose have proposed exploring the word co-occurrences in the neighborhood areas. Our approach encodes more spatial information through the geometry-preserving visual phrases (GVP). In addition to co-occurrences, the GVP method also captures the local and long-range spatial layouts of the words. Our GVP based searching algorithm increases little memory usage or computational time compared to the BoV method. Moreover, we show that our approach can also be integrated to the min-hash method to improve its retrieval accuracy. The experiment results on Oxford 5K and Flicker 1M dataset show that our approach outperforms the BoV method even following a RANSAC verification. | |
dc.source | Scopus | |
dc.type | Conference Paper | |
dc.contributor.department | OFFICE OF THE PROVOST | |
dc.contributor.department | DEPARTMENT OF COMPUTER SCIENCE | |
dc.description.doi | 10.1109/CVPR.2011.5995528 | |
dc.description.sourcetitle | Proceedings of the IEEE Computer Society Conference on Computer Vision and Pattern Recognition | |
dc.description.page | 809-816 | |
dc.description.coden | PIVRE | |
dc.published.state | published | |
Appears in Collections: | Staff Publications |
Show simple item record
Files in This Item:
There are no files associated with this item.
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.