Difference between revisions of "Content-Based Topic Segmentation in a News Video by Leveraging Wikipedia"
(+ wikilinks) |
(infobox) |
||
| Line 1: | Line 1: | ||
| + | {{Infobox work | ||
| + | | title = Content-Based Topic Segmentation in a News Video by Leveraging Wikipedia | ||
| + | | date = 2014 | ||
| + | | authors = [[Jong Wook Kim]]<br />[[Sae-Hong Cho]] | ||
| + | | doi = 10.14257/astl.2014.46.22 | ||
| + | | link = http://onlinepresent.org/proceedings/vol46_2014/22.pdf | ||
| + | }} | ||
'''Content-Based Topic Segmentation in a News Video by Leveraging Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2014, written by [[Jong Wook Kim]] and [[Sae-Hong Cho]]. | '''Content-Based Topic Segmentation in a News Video by Leveraging Wikipedia''' - scientific work related to [[Wikipedia quality]] published in 2014, written by [[Jong Wook Kim]] and [[Sae-Hong Cho]]. | ||
== Overview == | == Overview == | ||
A news video shared on the Web is composed of a series of independent events that happened on particular day or days. Due to the nature of news videos in which events are not clustered based on topical similarities and the continuously increasing sizes of news videos shared on the Web site, it is becoming more difficult for users to navigate through such sites to find the relevant pierce of information. The goal of this paper is to develop an effective technique to detect topic boundaries of a given news video. The topic boundaries obtained by algorithm are used to index a new video in order to support effective navigation and search for users. In particular, the proposed method in this paper maps the original closed-caption texts of a news video from the keyword-space into the concept-space by leveraging [[Wikipedia]] based semantic interpreter and then, computes topic boundaries in the concept-space. | A news video shared on the Web is composed of a series of independent events that happened on particular day or days. Due to the nature of news videos in which events are not clustered based on topical similarities and the continuously increasing sizes of news videos shared on the Web site, it is becoming more difficult for users to navigate through such sites to find the relevant pierce of information. The goal of this paper is to develop an effective technique to detect topic boundaries of a given news video. The topic boundaries obtained by algorithm are used to index a new video in order to support effective navigation and search for users. In particular, the proposed method in this paper maps the original closed-caption texts of a news video from the keyword-space into the concept-space by leveraging [[Wikipedia]] based semantic interpreter and then, computes topic boundaries in the concept-space. | ||
Revision as of 13:51, 4 August 2019
Authors | Jong Wook Kim Sae-Hong Cho |
|---|---|
Publication date | 2014 |
DOI | 10.14257/astl.2014.46.22 |
Links | Original |
Content-Based Topic Segmentation in a News Video by Leveraging Wikipedia - scientific work related to Wikipedia quality published in 2014, written by Jong Wook Kim and Sae-Hong Cho.
Overview
A news video shared on the Web is composed of a series of independent events that happened on particular day or days. Due to the nature of news videos in which events are not clustered based on topical similarities and the continuously increasing sizes of news videos shared on the Web site, it is becoming more difficult for users to navigate through such sites to find the relevant pierce of information. The goal of this paper is to develop an effective technique to detect topic boundaries of a given news video. The topic boundaries obtained by algorithm are used to index a new video in order to support effective navigation and search for users. In particular, the proposed method in this paper maps the original closed-caption texts of a news video from the keyword-space into the concept-space by leveraging Wikipedia based semantic interpreter and then, computes topic boundaries in the concept-space.
