CREMA: Contextual Reconstruction and Extraction of Multimodal Assets from academic papers

Dec 3, 2025·
Woonghee Lee
,
Jehyun Lee
,
Chang-soo Lee
,
Kwanyoung Park
· 0 min read
Abstract
System that extracts visual elements (figures, tables, equations) from academic papers, translates the body text, and reconstructs the document while preserving the original layout and visual elements, so that non-English-speaking researchers can read a paper with its figures and tables where the authors put them.
Type
Publication
Software Copyright Registration · Korea Copyright Commission
publications