TableStructureFormer: an improved masked-attention mask transformer model with long-distance feature aggregation and deep detail supervision for table structure recognition

Abstract Table structure recognition, as the most important subtask in image-based table recognition, recognizes the logical relationship between adjacent cells and represents the structured essence of the table. However, in reality, tables often appear in many different styles, such as those contai...

ver descrição completa

Detalhes bibliográficos

Principais autores:	Chenglong Yu, Weibin Li, Zixuan Zhu, Wei Li, Jianchao Du, Shiwei Zhang
Formato:	Artigo
Idioma:	Inglês
Publicado em:	Springer 2025-06-01
coleção:	Complex & Intelligent Systems
Assuntos:	Image-based table recognition Table structure recognition Row–column segmentation Masked-attention mask transformer Dual-path adaptive weighted attention Deep detail supervision
Acesso em linha:	https://doi.org/10.1007/s40747-025-01975-w
Tags:	Adicionar Tag Sem tags, seja o primeiro a adicionar uma tag!