Search Results for author:
Found 5 papers, 2 papers with code
TRACE: Table Reconstruction Aligned to Corner and Edges
In this work, we analyze the natural characteristics of a table, where a table is composed of cells and each cell is made up of borders consisting of edges.
BROS: A Pre-trained Language Model Focusing on Text and Layout for Better Key Information Extraction from Documents
On the other hand, this paper tackles the problem by going back to the basic: effective combination of text and layout.
Ranked #5 on
Relation Extraction
on FUNSD
BROS: A Pre-trained Language Model for Understanding Texts in Document
Although the recent advance in OCR enables the accurate extraction of text segments, it is still challenging to extract key information from documents due to the diversity of layouts.
Character Region Attention For Text Spotting
This architecture is formed by utilizing detection outputs in the recognizer and propagating the recognition loss through the detection stage.
CLEval: Character-Level Evaluation for Text Detection and Recognition Tasks
We believe that our metrics can play a key role in developing and analyzing state-of-the-art text detection and recognition methods.
