Next Article in Journal
Multi-Scale Spatio-Temporal Feature Extraction and Depth Estimation from Sequences by Ordinal Classification
Previous Article in Journal
Communication Aspects of Visible Light Positioning (VLP) Systems Using a Quadrature Angular Diversity Aperture (QADA) Receiver
Open AccessFeature PaperArticle

Learning Hierarchical Representations of Stories by Using Multi-Layered Structures in Narrative Multimedia

1
Future IT Innovation Laboratory, Pohang University of Science and Technology, Pohang-si 37673, Korea
2
Department of Computer Engineering, Chung-Ang University, Seoul 06974, Korea
*
Author to whom correspondence should be addressed.
Sensors 2020, 20(7), 1978; https://doi.org/10.3390/s20071978
Received: 10 March 2020 / Revised: 30 March 2020 / Accepted: 30 March 2020 / Published: 1 April 2020
(This article belongs to the Special Issue Computational Intelligence and Intelligent Contents (CIIC))
Narrative works (e.g., novels and movies) consist of various utterances (e.g., scenes and episodes) with multi-layered structures. However, the existing studies aimed to embed only stories in a narrative work. By covering other granularity levels, we can easily compare narrative utterances that are coarser (e.g., movie series) or finer (e.g., scenes) than a narrative work. We apply the multi-layered structures on learning hierarchical representations of the narrative utterances. To represent coarser utterances, we consider adjacency and appearance of finer utterances in the coarser ones. For the movies, we suppose a four-layered structure (character roles ∈ characters ∈ scenes ∈ movies) and propose three learning methods bridging the layers: Char2Vec, Scene2Vec, and Hierarchical Story2Vec. Char2Vec represents a character by using dynamic changes in the character’s roles. To find the character roles, we use substructures of character networks (i.e., dynamic social networks of characters). A scene describes an event. Interactions between characters in the scene are designed to describe the event. Scene2Vec learns representations of a scene from interactions between characters in the scene. A story is a series of events. Meanings of the story are affected by order of the events as well as their content. Hierarchical Story2Vec uses sequential order of scenes to represent stories. The proposed model has been evaluated by estimating the similarity between narrative utterances in real movies. View Full-Text
Keywords: hierarchical representation learning; computational narrative analysis; story embedding; Story2Vec; character network hierarchical representation learning; computational narrative analysis; story embedding; Story2Vec; character network
Show Figures

Figure 1

MDPI and ACS Style

Lee, O.-J.; Jung, J.J.; Kim, J.-T. Learning Hierarchical Representations of Stories by Using Multi-Layered Structures in Narrative Multimedia. Sensors 2020, 20, 1978.

Show more citation formats Show less citations formats
Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Article Access Map by Country/Region

1
Search more from Scilit
 
Search
Back to TopTop