Abstract
Broadcast news video has been playing a more and more important role in our daily life. However, how to effectively organize the broadcast news video into story semantic units is still a challenge issue. In this paper, we propose a novel style learning based story boundary detection method (SL-SBD) to explore the boundary and structural style of each program and segment the broadcast news video into story units. Compared with traditional methods, SL-SBD calculates the appearing-candidate range of news story boundary based on topic caption tracking techniques for more reliable boundary detection. Parallel to this, SL-SBD makes use of a wealth of boundary description features to explore the boundary characteristics of each program, and proposes a two-level style learning strategy including a detector and a refiner, to enhance the learning process with strong combination of boundary style and structural style collectively. We evaluate our method on Chinese News Vision dataset, and the encouraging experimental results demonstrate the effectiveness of SL-SBD over traditional story boundary detection methods.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
