A framework to automate the generation of movies' trailers using only subtitles

With the rapidly increasing rate of user-generated videos over the World Wide Web, it becoming a high necessity for users to navigate through them efficiently. Video summarization is considered to be one of the promising and effective approach for efficacious realization of video content by means of identifying and selecting descriptive frames of the video. In this paper, a proposed adaptive framework called Smart-Trailer (S-Trailer) is introduced to automatize the process of creating a movie trailer for any movie through its associated subtitles only. The proposed framework utilizes only English subtitles to be the language of usage. S-Trailer resolves the subtitle file to extract meaningful textual features that used to classify the movie into its corresponding genre(s). Experimentations on real movies showed that the proposed framework returns a considerable classification accuracy rate (0.89) to classify movies into their associated genre(s). The introduced framework generates an automated trailer that contains on average about (43%) accuracy in terms of recalling same scenes issued on the original movie trailer.