The DOI matches its Crossref record; the references it cites are not checked yet.
CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books
Abstract
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.
Overview
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Run the check — free, no account needed. It reads the open-access text and checks the sources it cites.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
The citation lists haven’t been fetched yet
Cited by 1
Research works printed but not linked: 17
- Bai, 2025, Qwen2.5-vl technical report
- 10.1109/ICPR56361.2022.9956546 · DOI
- 10.1109/icdar.2013.128 · DOI · Paper page
- Heidenreich, 2024, Large language models for page stream segmentation
- 10.1007/978-3-031-72437-4_24 · DOI · Paper page
- 10.1109/CVPR.2017.686 · DOI
- 10.1109/cvpr.2019.00963 · DOI · Paper page
- 10.1145/3558100.3563852 · DOI
- 10.1109/cvpr52733.2024.01232 · DOI
- Sachdeva, 2025, From panels to prose: Generating literary narratives from comics
- Sachdeva, 2024, Tails tell tales: Chapter-wide manga transcriptions with character name, 2053
- 10.52202/079017-4470 · DOI
- 10.1007/978-3-031-70645-5_11 · DOI
- Vivoli, Multimodal transformer for comics text-cloz, 128
- Vivoli, 2025, One missing piece in vision and language: A survey on comics understanding
- Wiedemann, 2018, Page stream segmentation with convolutional neural nets combining textual and visual feature
- Zhang, 2025, Qwen3 embedding: Advancing text embedding and reranking through foundation models
Metadata
- Authors
- Ortega, M. S., Vivoli, E., Llabrés, A., & Karatzas, D.
- Venue
- 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW)
- Publisher
- IEEE
- Published
- 2025-10-19
- Pages
- 7556-7564
- Cited by
- 1
- Funders
- EU (PID2023-146426NB-100)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books. https://app.cochat.ai/papers/10.1109/iccvw69036.2025.00778
- The paper
- Ortega, M. S., Vivoli, E., Llabrés, A., & Karatzas, D. (2025). CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books. 2025 IEEE/CVF International Conference on Computer Vision Workshops (ICCVW). https://doi.org/10.1109/iccvw69036.2025.00778
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.
