Abstract
Humans are entertained and emotionally captivated by a good story. Artworks, such as operas, theatre plays, movies, TV series, cartoons, etc., contain implicit stories, which are conveyed visually (e.g., through scenes) and audially (e.g., via music and speech). Story theorists have explored the structure of various artworks and identified forms and paradigms that are common to most well-written stories. Further, typical story structures have been formalized in different ways and used by professional screenwriters as guidelines. Currently, computers cannot yet identify such a latent narrative structure of a movie story. Therefore, in this work, we raise the novel challenge of understanding and formulating the movie story structure and introduce the first ever story-based labeled dataset—the Flintstones Scene Dataset (FSD). The dataset consists of 1, 569 scenes taken from a manual annotation of 60 episodes of a famous cartoon series, The Flintstones, by 105 distinct annotators. The various labels assigned to each scene by different annotators are summarized by a probability vector over 10 possible story elements representing the function of each scene in the advancement of the story, such as the Climax of Act One or the Midpoint. These elements are learned from guidelines for professional script-writing. The annotated dataset is used to investigate the effectiveness of various story-related features and multi-label classification algorithms for the task of predicting the probability distribution of scene labels. We use cosine similarity and KL divergence to measure the quality of predicted distributions. The best approaches demonstrated 0.81 average similarity and 0.67 KL divergence between the predicted label vectors and the ground truth vectors based on the manual annotations. These results demonstrate the ability of machine learning approaches to detect the narrative structure in movies, which could lead to the development of story-related video analytics tools, such as automatic video summarization and recommendation systems.
Highlights
A story is a report of connected events—real or imaginary, and an event comprises a series of consecutive interactions between characters and objects [1]
With only the knowledge of temporal label distributions, the temporal label distributions baseline outperformed the other baselines for both metrics
We proposed a novel task: story-related movie scene classification, as an important step towards understanding the story structure within narrative videos such as movies, TV series or animated cartoons
Summary
A story is a report of connected events—real or imaginary, and an event comprises a series of consecutive interactions between characters and objects (including other characters, nature, etc.) [1]. A story plot is defined as a sequence of events that have logical connections with each. Towards story-based classification of movie scenes other [2]. Literature researchers have identified structural similarities between different stories: they claim that most stories can be attributed to a fairly small set of unique plots [3,4,5] (i.e., narratives—generalizations of frequently re-occurring sequences of events) about a few archetypal characters [6]. While in a novel a conflict or an emotion may take place inside the readers imagination, inspired by the written text, a movie is an audio-visual medium, which can reveal the characters’ conflicts and emotions audio-visually (e.g., via a combat scene or an angry tone of voice)
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.
