loading...
 This Article 
   
 Share 
   
 Bibliographic References 
   
 Add to: 
 
Digg
Furl
Spurl
Blink
Simpy
Google
Del.icio.us
Y!MyWeb
 
 Search 
   
2009 10th Workshop on Image Analysis for Multimedia Interactive Services
Exploiting visual reranking to improve pseudo-relevance feedback for spoken-content-based video retrieval
London, United Kingdom
May 06-May 08
ISBN: 978-1-4244-3609-5
ASCII Text
x 
 
Stevan Rudinac, Martha Larson, Alan Hanjalic, "Exploiting visual reranking to improve pseudo-relevance feedback for spoken-content-based video retrieval," Image Analysis for Multimedia Interactive Services, International Workshop on, pp. 17-20, 2009 10th Workshop on Image Analysis for Multimedia Interactive Services, 2009.
 
 
BibTex
x
 
@article{ 10.1109/WIAMIS.2009.5031421,
author = {Stevan Rudinac and Martha Larson and Alan Hanjalic},
title = {Exploiting visual reranking to improve pseudo-relevance feedback for spoken-content-based video retrieval},
journal ={Image Analysis for Multimedia Interactive Services, International Workshop on},
volume = {0},
year = {2009},
isbn = {978-1-4244-3609-5},
pages = {17-20},
doi = {http://doi.ieeecomputersociety.org/10.1109/WIAMIS.2009.5031421},
publisher = {IEEE Computer Society},
address = {Los Alamitos, CA, USA},
}
 
 
RefWorks Procite/RefMan/Endnote
x 
 
TY - CONF
JO - Image Analysis for Multimedia Interactive Services, International Workshop on
TI - Exploiting visual reranking to improve pseudo-relevance feedback for spoken-content-based video retrieval
SN - 978-1-4244-3609-5
SP17
EP20
A1 - Stevan Rudinac,
A1 - Martha Larson,
A1 - Alan Hanjalic,
PY - 2009
VL - 0
JA - Image Analysis for Multimedia Interactive Services, International Workshop on
ER -
 
Stevan Rudinac, Delft University of Technology, The Netherlands
Martha Larson, Delft University of Technology, The Netherlands
Alan Hanjalic, Delft University of Technology, The Netherlands
In this paper we propose an approach that utilizes visual features and conventional text-based pseudo-relevance feedback (PRF) to improve the results of semantic-theme-based video retrieval. Our visual reranking method is based on an Average Item Distance (AID) score. AID-based visual reranking is designed to improve the suitability of items at the top of the initial results list, i.e., those feedback items selected for use in query expansion. Our method is intended to help target feedback items representative of visual regularity typifying the semantic theme of the query. Experiments performed on the VideoCLEF 2008 data set and on a number of retrieval scenarios combining the inputs from speech-transcript-based (i.e., text-based) search and visual reranking demonstrate the benefits of using AID-based visual representatives to compensate for the inherent problems of PRF, such as topic drift.
Citation:
Stevan Rudinac, Martha Larson, Alan Hanjalic, "Exploiting visual reranking to improve pseudo-relevance feedback for spoken-content-based video retrieval," wiamis, pp.17-20, 2009 10th Workshop on Image Analysis for Multimedia Interactive Services, 2009
Usage of this product signifies your acceptance of the Terms of Use.