CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866915388472688640 |
|---|---|
| author | Ortega, Marc Serra Vivoli, Emanuele Llabrés, Artemis Karatzas, Dimosthenis |
| author_facet | Ortega, Marc Serra Vivoli, Emanuele Llabrés, Artemis Karatzas, Dimosthenis |
| contents | This paper introduces CoSMo, a novel multimodal Transformer for Page Stream Segmentation (PSS) in comic books, a critical task for automated content understanding, as it is a necessary first stage for many downstream tasks like character analysis, story indexing, or metadata enrichment. We formalize PSS for this unique medium and curate a new 20,800-page annotated dataset. CoSMo, developed in vision-only and multimodal variants, consistently outperforms traditional baselines and significantly larger general-purpose vision-language models across F1-Macro, Panoptic Quality, and stream-level metrics. Our findings highlight the dominance of visual features for comic PSS macro-structure, yet demonstrate multimodal benefits in resolving challenging ambiguities. CoSMo establishes a new state-of-the-art, paving the way for scalable comic book analysis. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2507_10053 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books Ortega, Marc Serra Vivoli, Emanuele Llabrés, Artemis Karatzas, Dimosthenis Computer Vision and Pattern Recognition This paper introduces CoSMo, a novel multimodal Transformer for Page Stream Segmentation (PSS) in comic books, a critical task for automated content understanding, as it is a necessary first stage for many downstream tasks like character analysis, story indexing, or metadata enrichment. We formalize PSS for this unique medium and curate a new 20,800-page annotated dataset. CoSMo, developed in vision-only and multimodal variants, consistently outperforms traditional baselines and significantly larger general-purpose vision-language models across F1-Macro, Panoptic Quality, and stream-level metrics. Our findings highlight the dominance of visual features for comic PSS macro-structure, yet demonstrate multimodal benefits in resolving challenging ambiguities. CoSMo establishes a new state-of-the-art, paving the way for scalable comic book analysis. |
| title | CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books |
| topic | Computer Vision and Pattern Recognition |
| url | https://arxiv.org/abs/2507.10053 |