Movie indexing and summarization using social network techniques

Abstract

Movie summarization and indexing is the study which takes into account the understanding of the audiences. Besides, movie summarization focuses on reducing the length of a movie. Regarding this work, we propose a character network analysis to index and summarize the given movie. The method is based on the discovery and analysis of characters with respect to their appearance and the relationships among them in the movie. The strategy analysis is used to detect scenes, to segment the sub-plots of the story, and to extract character network and the main storyline of the movie. As a result, the social strength of each character in the social network is measured using measurement techniques that will then be used to mine the main plotline of the movie. In the final stage, the main storyline is used to provide a summarized version of the movie based on the social power of the characters. Experiments were carried out with 17 series of the Star Wars, the Lord of the Rings and the Harry Potter. The experimental evaluation results show that this study should index and extract summarization versions while keeping the understanding of the audiences.

Extraction and Analysis of Fictional Character Networks

“…Tran et al [65,244,246] propose a method for the automatic summarization of movies. They first extract a co-occurrence network, and use a combination of standard topological measures to identify the main characters.…”

Movie Summarization via Sparse Graph Construction

“…We model TP identification (and by extension summarization) as a supervised classification task. However, we depart from previous approaches to movie analysis which mostly focus on interactions between characters (Do, Tran, and Tran 2018;Tran et al 2017;Gorinski and Lapata 2015) and model connections between events. Moreover, we discard the simplifying assumption that a screenplay consists of a sequence of scenes (Gorinski and Lapata 2015;Papalampidi, Keller, and Lapata 2019;Papalampidi et al 2020) and instead represent interactions between scenes as a sparse graph.…”

Personalized Movie Summarization Using Deep CNN‐Assisted Facial Expression Recognition

“…In recent years, many MS techniques have been presented by researchers that can be broadly categorized into automatic MS techniques [1][2][3][4][5][6][7][8][9][10] and user-preference based MS techniques [11][12][13][14][15]. In automatic MS techniques, there is no direct preference from the users to generate a summary.…”

“…Another text based movie summarization scheme presented by Hesham et al [9] generated a short summary as a trailer using subtitles of the movies. Hang Do et al [10] summarized movies based on developing characters network. The relationships between characters are based on their appearance, which is used to segment the full-length movie into scenes.…”