Content-Based Story Segmentation of News Video by Multimodal Analysis

2009 ◽  
Author(s):  
Hua-Yong Liu ◽  
Tingting He
Keyword(s):  
Multimodal Analysis ◽  
Story Segmentation ◽  
News Video

News Video Story Segmentation with Multi-Modality Features

2020 ◽  
Author(s):  
Mingjie Zhou ◽  
Zhou Fan ◽  
Ruomei Wang ◽  
Fuwei Zhang ◽  
Guifeng Zheng
Keyword(s):  
Story Segmentation ◽  
News Video

Unsupervised story segmentation and indexing of broadcast news video

2021 ◽  
Author(s):  
Pranabjyoti Haloi ◽  
M.K. Bhuyan ◽  
Dibyajyoti Chatterjee ◽  
Pooja Rani Borah
Keyword(s):  
Broadcast News ◽  
Story Segmentation ◽  
News Video

News video story segmentation method using fusion of audio-visual features

2007 ◽  
Author(s):  
Jun Wen ◽  
Ling-da Wu ◽  
Pu Zeng ◽  
Xi-dao Luan ◽  
Yu-xiang Xie
Keyword(s):  
Visual Features ◽  
Segmentation Method ◽  
Story Segmentation ◽  
News Video

scholarly journals Multimodal Indexing of Multilingual News Video

2010 ◽  
Vol 2010 ◽  
pp. 1-18 ◽  
Author(s):  
Hiranmay Ghosh ◽  
Sunil Kumar Kopparapu ◽  
Tanushyam Chattopadhyay ◽  
Ashish Khare ◽  
Sujal Subhash Wattamwar ◽  
...  
Keyword(s):  
Automatic Analysis ◽  
Experimental Results ◽  
Indian Language ◽  
Automatic Indexing ◽  
News Stories ◽  
Multimodal Analysis ◽  
Regional Language ◽  
News Video ◽  
Tools And Techniques ◽  
Keyword List

The problems associated with automatic analysis of news telecasts are more severe in a country like India, where there are many national and regional language channels, besides English. In this paper, we present a framework for multimodal analysis of multilingual news telecasts, which can be augmented with tools and techniques for specific news analytics tasks. Further, we focus on a set of techniques for automatic indexing of the news stories based on keywords spotted in speech as well as on the visuals of contemporary and domain interest. English keywords are derived from RSS feed and converted to Indian language equivalents for detection in speech and on ticker texts. Restricting the keyword list to a manageable number results in drastic improvement in indexing performance. We present illustrative examples and detailed experimental results to substantiate our claim.

Sign in / Sign up

Export Citation Format

Share Document