Abstract
This study aims at measuring conflict degrees of each shot in visual narrative multimedia (e.g., movies and TV series) by analyzing visual storytelling techniques, such as camerawork. To describe incidents in stories, directors use the techniques as like as visual language. Thus, visual storytelling techniques used in a shot should be correlated with incidents shown by the shot. In this study, we first present various taxonomies of the visual storytelling techniques and discuss which techniques have more correlations with conflicts than the others. Then, based on usages of the techniques in each shot, we measure intensity of conflicts described by the shot. Finally, we validated correlations of visual storytelling techniques with stories’ content by examining correlations of the proposed conflict measurement with conflict degrees annotated by scholars and practitioners in film studies.
| Original language | English |
|---|---|
| Pages (from-to) | 18-26 |
| Number of pages | 9 |
| Journal | CEUR Workshop Proceedings |
| Volume | 3026 |
| State | Published - 2021 |
| Event | 2nd International Conference on Human-Centered Artificial Intelligence, Computing4Human 2021 - Da Nang, Viet Nam Duration: 27 Oct 2021 → 28 Oct 2021 |
Bibliographical note
Publisher Copyright:Copyright © by the paper’s authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).
Keywords
- Camerawork Analysis
- Computational Narrative Understanding
- Conflict Measurement
- Visual Storytelling