ViBERTgrid: A Jointly Trained Multi-modal 2D Document Representation for Key Information Extraction from Documents - researchr publication authors

researchr

You are not signed in
Sign in
Sign up

Weihong Lin, Qifang Gao, Lei Sun 0003, Zhuoyao Zhong, Kai Hu, Qin Ren, Qiang Huo. ViBERTgrid: A Jointly Trained Multi-modal 2D Document Representation for Key Information Extraction from Documents. In Josep Lladós 0001, Daniel Lopresti, Seiichi Uchida, editors, 16th International Conference on Document Analysis and Recognition, ICDAR 2021, Lausanne, Switzerland, September 5-10, 2021, Proceedings, Part I. Volume 12821 of Lecture Notes in Computer Science, pages 548-563, Springer, 2021. [doi]

This author has not been identified. Look up 'Weihong Lin' in GoogleThis author has not been identified. Look up 'Qifang Gao' in GoogleThis author has not been identified. Look up 'Lei Sun 0003' in GoogleThis author has not been identified. Look up 'Zhuoyao Zhong' in GoogleThis author has not been identified. Look up 'Kai Hu' in GoogleThis author has not been identified. Look up 'Qin Ren' in GoogleThis author has not been identified. Look up 'Qiang Huo' in Google

runs on WebDSL