Workshop

Document Image Analysis and Recognition (DIAR) has always been the focus of ICDAR conference. In the past, researchers in this community usually turned to computer vision technology alone to solve the problems of text detection and recognition, layout analysis, and even graphic structure recognition.

In order to understand the messages captured in the multimodal nature of documents, various techniques from Natural Language Processing (NLP), such as Named Entity Recognition and Linking, Visual Questions answering, Text Classification，can be combined with the traditional methods of OCR, Layout Analysis, and Logical Labeling that are well established in the ICDAR community. This workshop follows the tradition of ICDAR workshop and addresses the research between DIAR and NLP including the recent developments in the field of Machine Learning.

For the first time, we try to provide a forum to attract researchers from both communities to share their knowledge and expertise or colleagues who are already working at the edge of both fields in order to bring substantial improvement to document image understanding.