MPI-INF Logo
Publications

Server    domino.mpi-inf.mpg.de

Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop

Author, Editor
Author(s):
Kim, Kwang In
Tompkin, James
Theobald, Martin
Kautz, Jan
Theobalt, Christian
dblp
dblp
dblp
dblp
dblp
Not MPG Author(s):
Kautz, Jan
Editor(s):
Fitzgibbon, Andrew W.
Lazebnik, Svetlana
Perona, Pietro
Sato, Yoichi
Schmid, Cordelia
dblp
dblp
dblp
dblp
dblp
BibTeX cite key*:
Kim2012
Title, Booktitle
Title*:
Match Graph Construction for Large Image Databases
Booktitle*:
12th European Conference on Computer Vision
Event, URLs
Conference URL::
http://eccv2012.unifi.it/
Downloading URL:
Event Address*:
Florence, Italy
Language:
English
Event Date*
(no longer used):
Organization:
Event Start Date:
7 October 2012
Event End Date:
13 October 2012
Publisher
Name*:
Springer
URL:
Address*:
New York
Type:
Vol, No, Year, pp.
Series:
Lecture Notes in Computer Science
Volume:
7572
Number:
Month:
Pages:
272-285
Year*:
2012
VG Wort Pages:
ISBN/ISSN:
978-3-642-33711-6
Sequence Number:
DOI:
Note, Abstract, ©
(LaTeX) Abstract:
How best to efficiently establish correspondence among a large set of images or video frames is an interesting unanswered question. For large databases, the high computational cost of performing pair-wise image matching is a major problem. However, for many applications, images are inherently sparsely connected, and so current techniques try to correctly estimate small potentially matching subsets of databases upon which to perform expensive pair-wise matching. Our contribution is to pose the identification of potential matches as a link prediction problem in an image correspondence graph, and to propose an effective
algorithm to solve this problem. Our algorithm facilitates incremental image matching: initially, the match graph is very sparse, but it becomes dense as we alternate between link prediction and verification. We demonstrate the effectiveness
of our algorithm by comparing it with several existing alternatives on large-scale databases. Our resulting match graph is useful for many different applications. As an example, we show the benefits of our graph construction method to a label propagation application which propagates user-provided sparse object labels to other instances of that object in large image collections.
Download
Access Level:
Internal

Correlation
MPG Unit:
Max-Planck-Institut für Informatik
MPG Subunit:
Computer Graphics Group
Audience:
experts only
Appearance:
MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort



BibTeX Entry:

@INPROCEEDINGS{Kim2012,
AUTHOR = {Kim, Kwang In and Tompkin, James and Theobald, Martin and Kautz, Jan and Theobalt, Christian},
EDITOR = {Fitzgibbon, Andrew W. and Lazebnik, Svetlana and Perona, Pietro and Sato, Yoichi and Schmid, Cordelia},
TITLE = {Match Graph Construction for Large Image Databases},
BOOKTITLE = {12th European Conference on Computer Vision},
PUBLISHER = {Springer},
YEAR = {2012},
VOLUME = {7572},
PAGES = {272--285},
SERIES = {Lecture Notes in Computer Science},
ADDRESS = {Florence, Italy},
ISBN = {978-3-642-33711-6},
}


Entry last modified by James Tompkin, 02/05/2013
Hide details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)

Editor(s)
James Tompkin
Created
12/17/2012 02:37:10 PM
Revision
1.
0.


Editor
James Tompkin
James Tompkin


Edit Date
02/05/2013 07:59:16 PM
17/12/2012 14:37:10