Electronic Proceedings Article
@InProceedings
Internet-Beitrag in Tagungsband, Workshop


Show entries of:

this year (2024) | last year (2023) | two years ago (2022) | Notes URL

Action:

login to update
Options:




Library Locked Library locked




Author, Editor
Author(s):
Rohrbach, Marcus
Stark, Michael
Szarvas, György
Schiele, Bernt		dblp
dblp
dblp
dblp
Not MPG Author(s):
Szarvas, György
Editor(s):
Feris, Rogerio
Caetano, Tiberio
Lampert, Christoph
Forsyth, David		dblp
dblp
dblp
dblp
Not MPII Editor(s):
Feris, Rogerio
Caetano, Tiberio
Lampert, Christoph
Forsyth, David

BibTeX cite key*:

rohrbach10eccvw

Title, Conference

Title*:

Combining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge Transfer


rohrbach10eccvw.pdf (310.77 KB)

Booktitle*:

First International Workshop on Parts and Attributes in conjunction with ECCV 2010

Event Address*:

Crete, Greece
URL of the conference:

http://rogerioferis.com/PartsAndAttributes/

Event Date*:
(no longer used):


URL for downloading the paper:

http://rogerioferis.com/PartsAndAttributes/pages/material/LanguagePnA2010.pdf

Event Start Date:

9 July 2010
Event End Date:

9 July 2010

Language:

English
Organization:


Publisher

Publisher's Name:


This proceedings has no publisher!
Publisher's URL:


Address*:

s.l.
Type:


Vol, No, pp., Year

Series:


Volume:


Number:


Month:


Pages:




Sequence Number:


Year*:

2010
ISBN/ISSN:






Abstract, Links, ©

URL for Reference:


Note:


(LaTeX) Abstract:

Knowledge transfer between object classes has been identified as an important tool for scalable recognition. However, determining which knowledge to transfer where remains a key challenge. While most approaches employ varying levels of human supervision, we follow the idea of mining linguistic knowledge bases to automatically infer transferable knowledge. In contrast to previous work, we explicitly aim to design robust semantic relatedness measures and to combine different language sources for attribute-based knowledge transfer. On the challenging Animals with Attributes (AwA) data set, we report largely improved attribute-based zero-shot object class recognition performance that matches the performance of human supervision.

URL for the Abstract:




Tags, Categories, Keywords:


HyperLinks / References / URLs:


Copyright Message:


Personal Comments:

pages: 1-14 auf Wunsch von D2 gelöscht

Download
Access Level:

Public

Correlation
MPG Unit:
Max-Planck-Institut für Informatik
MPG Subunit:
Computer Vision and Multimodal Computing
Appearance:
MPG publications list

BibTeX Entry:
@INPROCEEDINGS{rohrbach10eccvw,
AUTHOR = {Rohrbach, Marcus and Stark, Michael and Szarvas, Gy{\"o}rgy and Schiele, Bernt},
 EDITOR = {Feris, Rogerio and Caetano, Tiberio and Lampert, Christoph and Forsyth, David},
 TITLE = {Combining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge Transfer},
 BOOKTITLE = {First International Workshop on Parts and Attributes in conjunction with ECCV 2010},
 YEAR = {2010},
 ADDRESS = {Crete, Greece},
}

Entry last modified by Anja Becker, 04/14/2011
Show details for Edit History (please click the blue arrow to see the details)Edit History (please click the blue arrow to see the details)
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
11/18/2010 17:19:21
Revisions
9.
8.
7.
6.
5.		Editor(s)
Anja Becker
Anja Becker
Anja Becker
Anja Becker
Anja Becker		Edit Dates
14.04.2011 09:55:37
14.04.2011 09:55:12
21.01.2011 11:47:10
21.01.2011 11:46:47
21.01.2011 11:45:39
Show details for Attachment SectionAttachment Section
Hide details for Attachment SectionAttachment Section

File Attachment Icon
rohrbach10eccvw.pdf