期刊名称：Lecture Notes in Engineering and Computer Science
印刷版ISSN：2078-0958
电子版ISSN：2078-0966
出版年度：2018
卷号：2233&2234
页码：405-408
出版社：Newswood and International Association of Engineers
摘要：Recently, people have begun searching for relevant
information of each scene of TV program videos with other
devices, such as smartphones and tablets. While viewing TV
programs, user’s interests change with each scene of the video.
When they try to get information related to the content of the
scenes, users have to input appropriate query keywords for a
Web search. However, it takes users time and effort to find their
desired information. Although some data casting services
suggest related information to TV programs, the related
information does not synchronize enough with each scene of the
videos. To solve this problem, our system proposes a novel query
keyword extraction method for Web searches, based on
spatio-temporal features of videos, using location names in the
video caption data. We first extract the location names and
classify them into two factors: geographical distance between
locations and semantic distance between location names. The
system recommends related information by setting the
maximum range of each area. Subsequently, we determine the
main topics and sub topics for generating web search queries
based on the length of time. Therefore, through our system,
suitable web pages for each scene can be found based on the
generated query keywords.
