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 2024-10-21 15:45
Descriptive text generation with person names for TV program video
Naotsuna Fujimori (NHK), Masahide Naemura (NHK Foundation), Takahiro Mochizuki (NHK)
Abstract (in Japanese) (See Japanese page) 
(in English) In order to enhance the efficacy of program production, it is imperative that technology be employed to automatically generate metadata pertaining to the content of program images. To this end, we have been investigating a technology for generating explanatory text, including the proper names of individuals, which has proven challenging with conventional image captioning technology. In this study, we developed a method for automatically generating descriptive text, including the name of each individual present in a given shot, by combining fundamental technologies such as face and person recognition. We then evaluated the efficacy of this method using broadcast program video.
Keyword (in Japanese) (See Japanese page) 
(in English) Image Captioning / Face Recognition / Person Recognition / Clustering / Phrase Grounding / / /  
Reference Info. ITE Tech. Rep., vol. 48, no. 33, ME2024-92, pp. 15-18, Oct. 2024.
Paper # ME2024-92 
Date of Issue 2024-10-14 (ME) 
ISSN Online edition: ISSN 2424-1970
Download PDF

Conference Information
Committee ME  
Conference Date 2024-10-21 - 2024-10-22 
Place (in Japanese) (See Japanese page) 
Place (in English) Kikai-Shinko-Kaikan Bldg. 
Topics (in Japanese) (See Japanese page) 
Topics (in English)  
Paper Information
Registration To ME 
Conference Code 2024-10-ME 
Language Japanese 
Title (in Japanese) (See Japanese page) 
Sub Title (in Japanese) (See Japanese page) 
Title (in English) Descriptive text generation with person names for TV program video 
Sub Title (in English)  
Keyword(1) Image Captioning  
Keyword(2) Face Recognition  
Keyword(3) Person Recognition  
Keyword(4) Clustering  
Keyword(5) Phrase Grounding  
Keyword(6)  
Keyword(7)  
Keyword(8)  
1st Author's Name Naotsuna Fujimori  
1st Author's Affiliation Science & Technology Research Laboratories, Japan Broadcasting Corporation (NHK)
2nd Author's Name Masahide Naemura  
2nd Author's Affiliation NHK Foundation (NHK Foundation)
3rd Author's Name Takahiro Mochizuki  
3rd Author's Affiliation Science & Technology Research Laboratories, Japan Broadcasting Corporation (NHK)
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 2024-10-21 15:45:00 
Presentation Time 30 minutes 
Registration for ME 
Paper # ME2024-92 
Volume (vol) vol.48 
Number (no) no.33 
Page pp.15-18 
#Pages
Date of Issue 2024-10-14 (ME) 


[Return to Top Page]

[Return to ITE Web Page]


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