DocumentCode
2132133
Title
Automatic Multimodal Aggregation of News from Television and the Web
Author
Messina, Alberto
Author_Institution
Centro Ric. e Innovazione Tecnol., RAI, Torino
fYear
2008
fDate
15-19 Dec. 2008
Firstpage
979
Lastpage
982
Abstract
This demonstration concerns a system designed and implemented to automatically build multimodal aggregations of informative news items coming from the two domains of digital television and the Web. Though in recent times several technological solutions have addressed the problem of clustering online articles, little is available which is capable of integrating these two sources of information. The demonstrated system is based on a novel hybrid clustering approach able to construct a directed graph of items representing a certain event (e.g., the tour of the Olympic torch), and to deliver an RSS service in which each item includes contributions coming from the two domains. In-house experimental evaluations have already proved the efficacy and accuracy of the service.
Keywords
Internet; digital television; directed graphs; multimedia systems; pattern clustering; RSS service; World Wide Web; digital television; directed graph; hybrid clustering; informative news items; multimodal aggregation; Computer architecture; Computer science; Conferences; Data mining; Digital TV; Feeds; Indexing; Information resources; Streaming media; TV interference; Multimodal aggregation; hybrid clustering; multimedia indexing; news gathering;
fLanguage
English
Publisher
ieee
Conference_Titel
Data Mining Workshops, 2008. ICDMW '08. IEEE International Conference on
Conference_Location
Pisa
Print_ISBN
978-0-7695-3503-6
Electronic_ISBN
978-0-7695-3503-6
Type
conf
DOI
10.1109/ICDMW.2008.18
Filename
4734032
Link To Document