English
 
Help Privacy Policy Disclaimer
  Advanced SearchBrowse

Item

ITEM ACTIONSEXPORT
 
 
DownloadE-Mail
 DetailsSummary
  Combining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge Transfer

Rohrbach, M., Stark, M., Szarvas, G., & Schiele, B. (2010). Combining Language Sources and Robust Semantic Relatedness for Attribute-Based Knowledge Transfer. In R. Feris, T. Caetano, C. Lampert, & D. Forsyth (Eds.), First International Workshop on Parts and Attributes in conjunction with ECCV 2010 (pp. 1-14).

Item is

 

show all hide all

Basic

show hide
Item Permalink: https://hdl.handle.net/11858/00-001M-0000-000F-15BB-1 Version Permalink: https://hdl.handle.net/11858/00-001M-0000-0024-305B-9
Genre: Conference Paper

Files

show Files
hide Files
:
rohrbach10eccvw.pdf (Any fulltext), 311KB
 
File Permalink:
-
Name:
rohrbach10eccvw.pdf
Description:
-
OA-Status:
Visibility:
Private
MIME-Type / Checksum:
application/pdf
Technical Metadata:
Copyright Date:
-
Copyright Info:
-
License:
-

Locators

show

Creators

show
hide
 Creators:
Rohrbach, Marcus1, Author           
Stark, Michael1, Author           
Szarvas, György2, Author
Schiele, Bernt1, Author           
Affiliations:
1Computer Vision and Multimodal Computing, MPI for Informatics, Max Planck Society, ou_1116547              
2External Organizations, ou_persistent22              

Content

show
hide
Free keywords: -
 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.

Details

show
hide
Language(s): eng - English
 Dates: 2010
 Publication Status: Issued
 Pages: -
 Publishing info: -
 Table of Contents: -
 Rev. Type: -
 Identifiers: eDoc: 536681
URI: http://rogerioferis.com/PartsAndAttributes/pages/material/LanguagePnA2010.pdf
Other: Local-ID: C12576EE0048963A-D508007BA014FF99C12577DF0059A998-rohrbach10eccvw
 Degree: -

Event

show
hide
Title: First International Workshop on Parts and Attributes
Place of Event: Crete, Greece
Start-/End Date: 2010-07-09 - 2010-07-09

Legal Case

show

Project information

show

Source 1

show
hide
Title: First International Workshop on Parts and Attributes in conjunction with ECCV 2010
  Abbreviation : ECCV 2010
Source Genre: Proceedings
 Creator(s):
Feris, Rogerio1, Editor
Caetano, Tiberio1, Editor
Lampert, Christoph1, Editor
Forsyth, David1, Editor
Affiliations:
1 External Organizations, ou_persistent22            
Publ. Info: -
Pages: - Volume / Issue: - Sequence Number: - Start / End Page: 1 - 14 Identifier: -