ITE Technical Group Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2013-02-18 10:00
Efficient Saliency Estimation Using Weakly Supervised Learning and Its Application to Video Classification
Tadashi Matsumura (Kobe Univ.), Kimiaki Shirahama (Muroran Inst. of Tech.), Kuniaki Uehara (Kobe Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) This paper develops a ``Focus of Attention'' (FoA) method which detects salient regions in videos based on ``contextual cueing'', meaning that similar regions tend to be salient in videos with similar spatial layouts. To implement this, using training videos where salient regions are labeled in advance, salient regions in a testing video are detected by referring to a training video, which has the spatial layout similar to that of the testing video. However, although a large number of training videos are required for covering various spatial layouts, the preparation of these videos is very laborious. Thus, this paper utilizes ``weakly supervised learning'' to efficiently create training videos, where salient regions are estimated only using labels that indicate what kind of objects are salient. Experimental results shows the effectiveness of our method, compared to using training videos where salient regions are manually labeled. In addition, detected salient regions are useful for video classification, which distinguishes videos where a certain concept is present from the rest of videos.
Keyword (in Japanese) (See Japanese page) 
(in English) Focus of attention / Top-down process / Contextual cueing / Weakly supervised learning / Video classification / / /  
Reference Info. ITE Tech. Rep., vol. 37, no. 8, ME2013-31, pp. 13-18, Feb. 2013.
Paper # ME2013-31 
Date of Issue 2013-02-11 (HI, ME, AIT) 
ISSN Print edition: ISSN 1342-6893
Download PDF

Conference Information
Committee IEICE-ITS IEICE-IE AIT HI ME  
Conference Date 2013-02-18 - 2013-02-19 
Place (in Japanese) (See Japanese page) 
Place (in English) Hokkaido Univ. 
Topics (in Japanese) (See Japanese page) 
Topics (in English) ITS Image Processsing, Image Medium, Vision, etc. 
Paper Information
Registration To ME 
Conference Code 2013-02-ITS-IE-AIT-HI-ME 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Efficient Saliency Estimation Using Weakly Supervised Learning and Its Application to Video Classification 
Sub Title (in English)  
Keyword(1) Focus of attention  
Keyword(2) Top-down process  
Keyword(3) Contextual cueing  
Keyword(4) Weakly supervised learning  
Keyword(5) Video classification  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Tadashi Matsumura  
1st Author's Affiliation Kobe University (Kobe Univ.)
2nd Author's Name Kimiaki Shirahama  
2nd Author's Affiliation Muroran Institute of Technology (Muroran Inst. of Tech.)
3rd Author's Name Kuniaki Uehara  
3rd Author's Affiliation Kobe University (Kobe Univ.)
4th Author's Name  
4th Author's Affiliation ()
5th Author's Name  
5th Author's Affiliation ()
6th Author's Name  
6th Author's Affiliation ()
7th Author's Name  
7th Author's Affiliation ()
8th Author's Name  
8th Author's Affiliation ()
9th Author's Name  
9th Author's Affiliation ()
10th Author's Name  
10th Author's Affiliation ()
11th Author's Name  
11th Author's Affiliation ()
12th Author's Name  
12th Author's Affiliation ()
13th Author's Name  
13th Author's Affiliation ()
14th Author's Name  
14th Author's Affiliation ()
15th Author's Name  
15th Author's Affiliation ()
16th Author's Name  
16th Author's Affiliation ()
17th Author's Name  
17th Author's Affiliation ()
18th Author's Name  
18th Author's Affiliation ()
19th Author's Name  
19th Author's Affiliation ()
20th Author's Name  
20th Author's Affiliation ()
Speaker Author-1 
Date Time 2013-02-18 10:00:00 
Presentation Time 20 minutes 
Registration for ME 
Paper # HI2013-3, ME2013-31, AIT2013-3 
Volume (vol) vol.37 
Number (no) no.8 
Page pp.13-18 
#Pages
Date of Issue 2013-02-11 (HI, ME, AIT) 


[Return to Top Page]

[Return to ITE Web Page]


The Institute of Image Information and Television Engineers (ITE), Japan