DMCA
On the burstiness of visual elements
| Venue: | in CVPR |
| Citations: | 86 - 16 self |
BibTeX
@INPROCEEDINGS{Jégou_onthe,
author = {Hervé Jégou and Matthijs Douze and Cordelia Schmid},
title = {On the burstiness of visual elements},
booktitle = {in CVPR},
year = {}
}
Share
 |
 |
 |
 |
||
OpenURL
Abstract
Figure 1. Illustration of burstiness. Features assigned to the most “bursty ” visual word of each image are displayed. Burstiness, a phenomenon initially observed in text retrieval, is the property that a given visual element appears more times in an image than a statistically independent model would predict. In the context of image search, burstiness corrupts the visual similarity measure, i.e., the scores used to rank the images. In this paper, we propose a strategy to handle visual bursts for bag-of-features based image search systems. Experimental results on three reference datasets show that our method significantly and consistently outperforms the state of the art. 1.
