Abstract
Roles, their emotion, and interactions between them are three key elements for semantic content understanding of movies. In this paper, we proposed a novel movie summarization method to capture the semantic content in movies based on a string of IE-RoleNets. An IE-RoleNet (interaction and emotion rolenet) models the emotion and interactions of roles in a shot of the movie. The whole movie is represented as a string of IE-RoleNets. Summarization of a movie is transformed into finding an optimal substring with user-specified summarization ratio. Hierarchical substring mining is conducted to find an optimal substring of the whole movie. We have conducted objective and subjective experiments on our method. Experimental results show the ability of our method to capture the semantic content of movies.
Highlights
Due to the proliferation of movie videos on websites, it is hard for users to find interesting movies
The main contributions of our work are: (1) we explore both interaction and emotional cues of movie characters, and propose the IE-RoleNet as a means of modeling the semantic information in movies; (2) we use a string of IE-RoleNets to model the dynamic storyline of a movie, and to extract summarization, by mining optimal substrings from the string of IE-RoleNets; (3) we provide both structure-level and role-level summarization
Since there is no standard evaluation framework in video summarization research, we evaluated the performance of the proposed movie summarization method following existing methods
Summary
Due to the proliferation of movie videos on websites, it is hard for users to find interesting movies. Most users turn to web applications, such as movie recommendation and movie retrieval, for help. These applications still provide hundreds and thousands of hours of video content to users. There is a strong demand for a mechanism that allows users to gain an overview of Manuscript received: 2015-02-06; accepted: 2015-05-01 a movie without watching the entire video. Movie abstraction techniques facilitate the browsing and navigation of a movie collection for users. Using movie abstraction as a preview, the user can quickly access each movie and evaluate if it is important, interesting, or enjoyable
Sign-in/Register to view highlights & summary Sign-in/Register to access full text options 
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.
