Researchers have developed two methods for understanding the complex hierarchical structures within newspaper images. One approach uses a modular pipeline combining YOLO for layout detection and LayoutReader for reading order, while the other introduces Tiramisu, a novel transformer-based architecture designed to model document hierarchy iteratively. The study also introduces Finlam La Liberté, a new dataset for evaluating hierarchical information retrieval in historical newspapers, and makes the Tiramisu training code publicly available. AI
IMPACT This research could improve automated digitization and information retrieval for historical documents.
RANK_REASON The cluster contains an academic paper detailing new AI models and a dataset for a specific research task.
- alphaXiv
- arXiv
- CatalyzeX
- Connected Papers
- DagsHub
- Finlam La Liberté
- Gotit.pub
- Hugging Face
- LayoutReader
- Litmaps
- Merveilles Agbeti-Messan
- ScienceCast
- scite Smart Citations
- YOLO
AI-generated summary · Google Gemini · from 2 sources. How we write summaries →
