We call on the Document AI (DocAI) community to reevaluate current
metho...
Document Visual Question Answering (DocVQA) refers to the task of answer...
Pretraining has proven successful in Document Intelligence tasks where d...
In this report we present results of the ICDAR 2021 edition of the Docum...
Current tasks and methods in Document Understanding aims to process docu...
This paper presents results of Document Visual Question Answering Challe...
This paper presents a new model for the task of scene text visual questi...
This paper presents final results of ICDAR 2019 Scene Text Visual Questi...
Current visual question answering datasets do not consider the rich sema...