In this paper, we propose the broadcasting data structure that can clip the requested scene or information in the TV program, and that can reconstitute the TV program depending on review environment or the purpose. As a result, this mechanism enables users to use the clipped broadcasting contents for various purposes.

In Taiwan, there are different types of TV programs, and each program usually has its broadcast length and frequency. We accumulate the broadcasted TV programs’ word-ofmouth on Facebook and apply the Backpropagation Network to predict the latest program audience rating. TV audience rating is an important indicator regarding the popularity of programs and it is also a factor to influence the rev...

With the increasing of the number of digital television (TV) channels in Thailand, this becomes a problem of information overload for TV viewers. There are mass numbers of TV programs to watch but the information about these programs is poor. Therefore, this work presents a personalized recommendation system on mobile device to recommend a TV program that matches viewer’s interests and/or needs...

Many studies have already shown the advantages of building multimodal systems. In this case study we have shown the advantages of combining natural language and a graphical interface in the interactive TV domain. In this paper we describe a multimodal dialogue TV program guide system that is a research prototype built for the case study by adding speech interaction to an already existing TV pro...

This demo presents a method of detecting television programs in TV streams. The objective is to automatically detect the precise start and end of broadcasted television programs. The method first detects inter-programs (commercials, trailers. . . ) as repeated sequences in the broadcast stream, and then deduces the programs boundaries. The extracted programs can then be stored in a database to ...

access to greater and greater amounts of electronic information, we are faced with significant problems when it comes to finding the right information at the right time—the essence of the information-overload problem. One of the proposed solutions to this problem is to develop technologies for automatically learning about the implicit and explicit preferences of individual users to customize an...

The system described in this article helps users in compiling personal TV schedules. The system’s goal is to generate the schedules automatically based on user profiles. To tide over the profile’s training period, the system provides the users with additional tools that help in finding the desired information manually or semiautomatically while generating training input for the profile at the s...