MPI-INF Logo
Publications

Server    domino.mpi-inf.mpg.de

Proceedings Article, Paper
@InProceedings
Beitrag in Tagungsband, Workshop

Author, Editor
Author(s):
Ebert, Sandra
Larlus, Diane
Schiele, Bernt		dblp
dblp
dblp
Not MPG Author(s):
Larlus, Diane
Editor(s):
Daniilidis, Kostas
Maragos, Petros
Paragios, Nikos		dblp
dblp
dblp
Not MPII Editor(s):
Daniilidis, Kostas
Maragos, Petros
Paragios, Nikos
BibTeX cite key*:
EbertECCV2010
Title, Booktitle
Title*:
Extracting Structures in Image Collections for Object Recognition
EbertLarlusSchieleECCV2010.pdf (361.75 KB)
Booktitle*:
Computer Vision - ECCV 2010 : 11th European Conference on Computer Vision
Event, URLs
Conference URL::
http://www.ics.forth.gr/eccv2010/intro.php
Downloading URL:
http://www.d2.mpi-inf.mpg.de/sites/default/files/ExtractingStructuresECCV2010.pdf
Event Address*:
Crete, Greece
Language:
English
Event Date*
(no longer used):
Organization:
Event Start Date:
5 September 2010
Event End Date:
11 September 2010
Publisher
Name*:
Springer
URL:
http://www.springer.com/
Address*:
Berlin
Type:
Vol, No, Year, pp.
Series:
Lecture Notes in Computer Science
Volume:
6311
Number:
Month:
Pages:
720-733
Year*:
2010
VG Wort Pages:
ISBN/ISSN:
978-3-642-15548-2
Sequence Number:
DOI:
10.1007/978-3-642-15549-9_52
Note, Abstract, ©
(LaTeX) Abstract:
Many computer vision methods rely on annotated image databases without taking advantage of the increasing number of unlabeled images available. This paper explores an alternative approach involving unsupervised structure discovery and semi-supervised learning (SSL) in image collections. Focusing on object classes, the first part of the paper contributes with an extensive evaluation of state-of-the-art image representations underlining the decisive influence of the local neighborhood structure, its direct consequences on SSL results, and the
importance of developing powerful object representations. In a second part, we propose and explore promising directions to improve results by looking at the local topology between images and feature combination strategies.
Keywords:
computer vision, object recognition, semi-supervised learning
Download
Access Level:
Public

Correlation
MPG Unit:
Max-Planck-Institut für Informatik
MPG Subunit:
Computer Vision and Multimodal Computing
External Affiliations:
TU Darmstadt
Appearance:
MPII WWW Server, MPII FTP Server, MPG publications list, university publications list, working group publication list, Fachbeirat, VG Wort



BibTeX Entry:

@INPROCEEDINGS{EbertECCV2010,
AUTHOR = {Ebert, Sandra and Larlus, Diane and Schiele, Bernt},
 EDITOR = {Daniilidis, Kostas and Maragos, Petros and Paragios, Nikos},
 TITLE = {Extracting Structures in Image Collections for Object Recognition},
 BOOKTITLE = {Computer Vision - ECCV 2010 : 11th European Conference on Computer Vision},
 PUBLISHER = {Springer},
 YEAR = {2010},
 VOLUME = {6311},
 PAGES = {720--733},
 SERIES = {Lecture Notes in Computer Science},
 ADDRESS = {Crete, Greece},
 ISBN = {978-3-642-15548-2},
 DOI = {10.1007/978-3-642-15549-9_52},
}

Entry last modified by Anja Becker, 04/11/2011
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)
[Library]		Created
12/20/2010 18:08:09
Revisions
3.
2.
1.
0.
Editor(s)
Anja Becker
Anja Becker
Anja Becker
Sandra Ebert
Edit Dates
11.04.2011 10:43:04
21.01.2011 11:37:54
19.01.2011 11:37:48
12/20/2010 06:08:09 PM

File Attachment Icon
EbertLarlusSchieleECCV2010.pdf