Conference item icon

Conference item

All about VLAD

Abstract:
The objective of this paper is large scale object instance retrieval, given a query image. A starting point of such systems is feature detection and description, for example using SIFT. The focus of this paper, however, is towards very large scale retrieval where, due to storage requirements, very compact image descriptors are required and no information about the original SIFT descriptors can be accessed directly at run time. We start from VLAD, the state-of-the art compact descriptor introduced by Jegou et al. for this purpose, and make three novel contributions: first, we show that a simple change to the normalization method significantly improves retrieval performance; second, we show that vocabulary adaptation can substantially alleviate problems caused when images are added to the dataset after initial vocabulary learning. These two methods set a new state-of-the-art over all benchmarks investigated here for both mid-dimensional (20k-D to 30k-D) and small (128-D) descriptors. Our third contribution is a multiple spatial VLAD representation, MultiVLAD, that allows the retrieval and localization of objects that only extend over a small part of an image (again without requiring use of the original image SIFT descriptors).
Publication status:
Published
Peer review status:
Peer reviewed

Actions

Access Document

Files:
Publisher copy:
10.1109/CVPR.2013.207

Authors

More by this author
Institution:
University of Oxford
Division:
MPLS
Department:
Engineering Science
Oxford college:
Brasenose College
Role:
Author


Publisher:
IEEE
Host title:
2013 IEEE Conference on Computer Vision and Pattern Recognition
Pages:
1576-1583
Publication date:
2013-10-03
Acceptance date:
2012-11-15
Event title:
26th IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2013)
Event location:
Portland, OR, USA
Event start date:
2013-06-23
Event end date:
2013-06-28
DOI:
ISSN:
1063-6919
EISBN:
978-1-5386-5672-3


Keywords:
Pubs id:
pubs:682365
UUID:
uuid:163cd743-4b36-46ab-bd00-7c1079373802
Local pid:
pubs:682365
Source identifiers:
682365
Deposit date:
2017-03-01
ARK identifier:

Terms of use


Views and Downloads

Views and downloads will return soon






If you are the owner of this record, you can report an update to it here: Report update to this record

TO TOP