Search academic texts

Information × Registration Number 2119U006511, Article popup.category Препринт Title movie2trailer: Unsupervised trailer generation using Anomaly detection (AI translated) popup.author Rehusevych OrestRehusevych Orest popup.publication 01-01-2019 popup.source_user Український католицький університет popup.source https://hdl.handle.net/20.500.14570/4472 popup.publisher Description In this work, we present a novel unsupervised approach for automatic trailer gen- eration - movie2trailer. To our knowledge, it is the first-ever application of anomaly detection to such a creative and challenging part of the trailer creation process as a shot selection. One of the main advantages of our approach over the competitors is that it does not require any prior knowledge and extracts all needed information directly from the input movie. By leveraging the recent advancements in video and audio analysis, we can produce high-quality movie trailers in equal or less time than professional movie editors. The proposed approach reaches state-of-the-art in terms of visual attractiveness and closeness to the "real" trailer. Moreover, it exposes new horizons for researching anomaly detection applications in the movie industry. An example of generated with our approach trailer for the movie "Requiem for a dream" can be observed on YouTube. popup.nrat_date 2025-11-05 Close