DocumentCode :
3055661
Title :
Visually Guided Summary Based on Roles of Shots for Understanding News Topics
Author :
Sano, Masanori ; Shibata, Masahiro ; Yagi, Nobuyuki ; KATAYAMA, Norio ; Satoh, S.
Author_Institution :
NHK Sci. & Technol. Res. Labs., Tokyo, Japan
fYear :
2009
fDate :
Nov. 29 2009-Dec. 4 2009
Firstpage :
279
Lastpage :
286
Abstract :
This paper describes a method of generating of a visual summary from archived news video that clearly shows a topic shared by several news items. To grasp the whole topic, recognizing each news item at a glance and the flow of the news items from several viewpoints is an essential and needed. Our method represents a news item with several representative images and pieces of text, and it presents three different viewpoints for visualizing the extracted images and text. The representative images are ones from which user can guess the content of the news item or which are relevant to the news item. In order to extract such images we introduce roles of shots in news video, i.e., by applying production rules. That is, by knowing the way of shooting and editing, shots/images whose roles are lead-in, expository and spotlighting the principal object can be extracted. Our method was applied to several news topics and confirmed its effectiveness.
Keywords :
data visualisation; feature extraction; image representation; image texture; information resources; text editing; editing; image extraction; image representation; news video; shooting; text images; visually guided summary; Context; Data mining; Data visualization; Face; Interviews; Lead; Speech; News analysis; Visually guided summary; metadata; representative image; shot´s role;
fLanguage :
English
Publisher :
ieee
Conference_Titel :
Signal-Image Technology & Internet-Based Systems (SITIS), 2009 Fifth International Conference on
Conference_Location :
Marrakesh
Print_ISBN :
978-1-4244-5740-3
Electronic_ISBN :
978-0-7695-3959-1
Type :
conf
DOI :
10.1109/SITIS.2009.53
Filename :
5633977
Link To Document :
بازگشت