CoSMo, a lightweight multimodal Transformer, segments comic book page streams into semantic sections and outperforms larger zero-shot vision-language models on a new 20,800-page dataset.
Large language models for page stream segmentation, 2024
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
citation-role summary
background 1
citation-polarity summary
fields
cs.CV 1years
2025 1verdicts
CONDITIONAL 1roles
background 1polarities
support 1representative citing papers
citing papers explorer
-
CoSMo: A Multimodal Transformer for Page Stream Segmentation in Comic Books
CoSMo, a lightweight multimodal Transformer, segments comic book page streams into semantic sections and outperforms larger zero-shot vision-language models on a new 20,800-page dataset.