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 2021-02-18 16:40
A note on improvement of image sentiment analysis based on introduction of image captioning
Yun Liang, Keisuke Maeda, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Recently, with the popularization of social network services, the images uploaded by users have been increasing. Users tend to share their feelings by sharing pictures. Thus, it is important to analyze image sentiments for effectively collecting and searching from a large amount of data. Previous advances on image sentiment analysis paid attention to the features of the images from low levels such as shape, color and objects, to high levels such as aesthetics and semantics. Furthermore, with the usage of deep metric learning, researchers considered the spatial distribution of the sentiments. However, the aforementioned features cannot reveal the details such as the correlations among objects of a certain image. Therefore, in this paper, to achieve a performance improvement for the image sentiment analysis, we newly introduce image captioning. Concretely, we extract the multi-level features of the images by our convolutional network. Furthermore, we extract the image captioning features by an employed pre-trained image captioning model. Moreover, we integrate the aforementioned features and predict the image sentiments by using the integrated features. We have confirmed the effectiveness of the proposed method through experiments using an open dataset.
Keyword (in Japanese) (See Japanese page) 
(in English) Deep metric learning / Image sentiment analysis / Image captioning / / / / /  
Reference Info. ITE Tech. Rep., vol. 45, no. 4, ME2021-13, pp. 65-69, Feb. 2021.
Paper # ME2021-13 
Date of Issue 2021-02-11 (MMS, ME, AIT) 
ISSN Print edition: ISSN 1342-6893  Online edition: ISSN 2424-1970
Download PDF

Conference Information
Conference Date 2021-02-18 - 2021-02-19 
Place (in Japanese) (See Japanese page) 
Place (in English) Online 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image Processing, etc. 
Paper Information
Registration To ME 
Conference Code 2021-02-IE-ITS-MMS-ME-AIT 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) A note on improvement of image sentiment analysis based on introduction of image captioning 
Sub Title (in English)  
Keyword(1) Deep metric learning  
Keyword(2) Image sentiment analysis  
Keyword(3) Image captioning  
1st Author's Name Yun Liang  
1st Author's Affiliation Hokkaido University (Hokkaido Univ.)
2nd Author's Name Keisuke Maeda  
2nd Author's Affiliation Hokkaido University (Hokkaido Univ.)
3rd Author's Name Takahiro Ogawa  
3rd Author's Affiliation Hokkaido University (Hokkaido Univ.)
4th Author's Name Miki Haseyama  
4th Author's Affiliation Hokkaido University (Hokkaido Univ.)
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 ()
Date Time 2021-02-18 16:40:00 
Presentation Time 25 
Registration for ME 
Paper # ITE-MMS2021-13,ITE-ME2021-13,ITE-AIT2021-13 
Volume (vol) ITE-45 
Number (no) no.4 
Page pp.65-69 
#Pages ITE-5 
Date of Issue ITE-MMS-2021-02-11,ITE-ME-2021-02-11,ITE-AIT-2021-02-11 

[Return to Top Page]

[Return to ITE Web Page]

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