Character Network Embedding-based Plot Structure Discovery in Narrative Multimedia

Lee, O-Joun; Jung, Jason J.

doi:10.1145/3326467.3326485

Cited by 6 publications

(30 citation statements)

References 19 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…These studies [12,13] call substructures rooted in each character as 'social roles' of the character. A social role implicitly represents the character role at a particular scene and scale, despite the absence of the exact meanings.…”

Section: Background and Preliminariesmentioning

confidence: 99%

“…However, fixed-size windows of Word2Vec and Doc2Vec are not adequate for graphical data, since the number of adjacent nodes in networks is not constant. Thus, our previous studies [12,13] employed radial neighborhoods in Subgraph2Vec [26] and Graph2Vec [27], which define neighboring substructures based on (i) adjacency of nodes (e.g., c Figure 1) and (ii) adjacency of degrees (e.g., c…”

Section: Background and Preliminariesmentioning

confidence: 99%

“…To resolve these problems, our previous studies [12,13] conducted unsupervised representation learning for structures of the character network. Lee and Jung [12] have proposed three models-Story2Vec-F (Flow-oriented Story2Vec), Story2Vec-D (Denouement-oriented Story2Vec), and Story2Vec-U (Unified Story2Vec).…”

Section: Introductionmentioning

confidence: 99%

“…The three models have shown reasonable accuracy for measuring similarity between movie stories. Also, Lee and Jung [13] have proposed a method for representing the content of each scene by learning compositions of social roles in the scene (Scene2Role2Vec).…”

Section: Introductionmentioning

confidence: 99%

“…The previous studies [12,13] directly jumped up form the social roles to stories. However, between the social role and the story, there is a significant conceptual gap.…”

Section: Introductionmentioning

confidence: 99%

See 4 more Smart Citations

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

Lee

Jung

Kim

2020

Sensors

Self Cite

View full text Add to dashboard Cite

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.

show abstract

Section: Background and Preliminariesmentioning

confidence: 99%

Section: Background and Preliminariesmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

“…The previous studies [12,13] directly jumped up form the social roles to stories. However, between the social role and the story, there is a significant conceptual gap.…”

Section: Introductionmentioning

confidence: 99%

See 3 more Smart Citations