ComicScene154: A Scene Dataset for Comic Analysis

TL;DR

ComicScene154 is a new, manually annotated dataset of comic book scenes designed to advance computational analysis of multimodal storytelling, providing a benchmark for scene segmentation and narrative understanding.

Contribution

The paper introduces ComicScene154, a novel dataset for comic analysis, along with a baseline scene segmentation method to facilitate future research.

Findings

ComicScene154 is a valuable resource for multimodal narrative research.

Baseline scene segmentation achieves promising initial results.

Dataset spans diverse genres, enhancing generalizability.

Abstract

Comics offer a compelling yet under-explored domain for computational narrative analysis, combining text and imagery in ways distinct from purely textual or audiovisual media. We introduce ComicScene154, a manually annotated dataset of scene-level narrative arcs derived from public-domain comic books spanning diverse genres. By conceptualizing comics as an abstraction for narrative-driven, multimodal data, we highlight their potential to inform broader research on multi-modal storytelling. To demonstrate the utility of ComicScene154, we present a baseline scene segmentation pipeline, providing an initial benchmark that future studies can build upon. Our results indicate that ComicScene154 constitutes a valuable resource for advancing computational methods in multimodal narrative understanding and expanding the scope of comic analysis within the Natural Language Processing community.