IEICE Technical Committee Submission System
Conference Paper's Information
Online Proceedings
[Sign in]
Tech. Rep. Archives
 Go Top Page Go Previous   [Japanese] / [English] 

Paper Abstract and Keywords
Presentation 2020-02-28 16:50
A Note on Image Retrieval Focusing on Objects in Images -- Improving Retrieval Performance Based on Object Recognition Using RetinaNet --
Rintaro Yanagi, Ren Togo, Takahiro Ogawa, Miki Haseyama (Hokkaido Univ.)
Abstract (in Japanese) (See Japanese page) 
(in English) Image retrieval method using a text as a query is effective because it enables users to prepare query easily. In these methods, it is expected to improve retrieval performance of cross-modal retrieval method that can retrieve a desired image from a query sentence without labels on the candidate images. Conventional cross-modal retrieval method is realized by embedding lingual and visual features into common semantic space. However, the conventional cross-modal retrieval method may lose information of nouns in a query sentence and objects in candidate images while they embed lingual and visual features. Then, in this paper, we propose a novel image retrieval method that can focus on all of noun of input text based on image recognition method. In the proposed method, firstly, we calculate similarities between all of noun of input text and objects recognized by retrieval candidate images. Then, by using these similarities with the conventional image retrieval method, we obtain retrieval results that contain all of noun of input text. We confirmed the effectiveness of the proposed method through evaluations using open dataset.
Keyword (in Japanese) (See Japanese page) 
(in English) Image retrieval / Object recognition / Cross-modal retrieval / / / / /  
Reference Info. IEICE Tech. Rep.
Paper #  
Date of Issue  
ISSN Print edition: ISSN 0913-5685  Online edition: ISSN 2432-6380
Download PDF

Conference Information
Committee ITE-HI IE ITS ITE-MMS ITE-ME ITE-AIT  
Conference Date 2020-02-27 - 2020-02-28 
Place (in Japanese) (See Japanese page) 
Place (in English) Hokkaido Univ. 
Topics (in Japanese) (See Japanese page) 
Topics (in English) Image Processing, etc. 
Paper Information
Registration To ITE-ME 
Conference Code 2020-02-HI-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 Image Retrieval Focusing on Objects in Images 
Sub Title (in English) Improving Retrieval Performance Based on Object Recognition Using RetinaNet 
Keyword(1) Image retrieval  
Keyword(2) Object recognition  
Keyword(3) Cross-modal retrieval  
Keyword(4)  
Keyword(5)  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Rintaro Yanagi  
1st Author's Affiliation Hokkaido University (Hokkaido Univ.)
2nd Author's Name Ren Togo  
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 ()
Speaker
Date Time 2020-02-28 16:50:00 
Presentation Time 15 
Registration for ITE-ME 
Paper #  
Volume (vol) IEICE-119 
Number (no)  
Page  
#Pages IEICE- 
Date of Issue  


[Return to Top Page]

[Return to IEICE Web Page]


The Institute of Electronics, Information and Communication Engineers (IEICE), Japan