DIL workshop on ICDAR 2021

DIL workshop will be held virtually from 14:00pm to 18:00pm on Sept 6th, Swiss time. Below is the detailed schedule. For online participation, please refer to https://icdar2021.org/attendance/online-participation.

START TIME	END TIME	TOPIC	Chairs	Speaker(s)
14:00pm	14:05pm	Opening	Chenglin Liu
14:05pm	14:35pm	Keynote: Visual Information Extraction for Document Understanding	Chenglin Liu	Lianwen Jin
14:35pm	15:05pm	Keynote: Document AI: Benchmarks, Models and Applications	Hua Wu	Lei Cui
15:05pm	15:25pm	Oral1:A Span Extraction Approach for Information Extraction on Visually-Rich Documents	David Doermann	Hieu M. Vu
		Coffee Break
16:00pm	16:20pm	Oral2:MTL-FoUn: A Multi-Task Learning Approach to Form Understanding	David Doermann	Nishant Prabhu
16:20pm	16:40pm	Oral3:Recurrent neural network transducer for Japanese and Chinese offline handwritten text recognition	David Doermann	Trung Ngo
16:40pm	17:10pm	keynote: Using Knowledge Graphs for Document Analysis Scenarios in Corporate Memories	Jingtuo Liu	Heiko Maus
17:10pm	17:55pm	Poster session：	Errui Ding
		VisualWordGrid: Information Extraction From Scanned Documents Using A Multimodal Approach；
		Multi-task Learning for Newspaper Image Segmentation and Baseline Detection Using Attention-Based U-Net Architecture；
		A Transformer-based Math Language Model for Handwritten Math Expression Recognition；
		Data-Efficient Information Extraction from Documents with Pre-Trained Language Models；
		Exploring Out-of-Distribution Generalization in Text Classifiers Trained on Tobacco-3482 and RVL-CDIP
		Labeling Document Images for E-Commence Products With Tree-Based Segment Re-organizing and Hierarchical Transformer
17:55pm	18:00pm	Best paper award and closing	Jingtuo Liu

Keynote Speaker： Lei Cui

Title: Document AI: Benchmarks, Models and Applications

Bio: Dr. Lei Cui is a Principal Researcher in Natural Language Computing (NLC) group at Microsoft Research Asia. Lei joined MSRA in 2015 after he received his Ph.D. degree from the Department of Computer Science at Harbin Institute of Technology. His research interest is Natural Language Processing, including machine translation, information extraction, text generation, question answering, dialog system, etc. His work has contributed to many important products in Microsoft such as Azure, Office, and Bing. He published more than 30 research papers in top conferences of AI and NLP areas, such as ACL, AAAI, IJCAI, KDD, EMNLP, COLING, etc. Besides, he also served as the reviewer for ACL, EMNLP, NAACL, COLING, and many other conferences. Besides, he also held 15 U.S. patents in AI and NLP. During his Ph.D. study, he won the 2011 Microsoft Fellowship Award and the 2014 IBM Fellowship Award.
Keynote Speaker： Lianwen Jin

Title: Visual Information Extraction for Document Understanding

Bio: Lianwen Jin received the B.S. degree from the University of Science and Technology of China, and the Ph.D. degree from the South China University of Technology, China, in 1991 and 1996, respectively. He is currently a Professor at the School of Electronic and Information Engineering, South China University of Technology. He is the author of more than 200 scientific papers. He has served as AC/SPC/PC member for many international conferences, including ICDAR, ICFHR, ICPR, CVPR, ICCV, IJCAI, AAAI, etc. Dr. Jin was a recipient of the award of New Century Excellent Talent Program of MOE in 2006 and the Guangdong Pearl River Distinguished Professor Award in 2011. His research interests include optical character recognition, handwriting analysis and recognition, document understanding, deep learning and computer vision.
Keynote Speaker： Heiko Maus

Title: Using Knowledge Graphs for Document Analysis Scenarios in Corporate Memories

Bio: Heiko Maus is Team Leader of the Topic Area Knowledge Work, in the Smart Data & Knowledge Services Department of the German Research Center for Artificial Intelligence (DFKI) in Kaiserslautern. Heiko’s focus is on transfer of research results in industry applications and deriving real-world challenges for further research. With the corporate memory infrastructure CoMem (https://comem.ai), the team brings together innovative research and an information system infrastructure for application in industry practice. CoMem is used in research and in industry projects and therefore can provide a variety of usage scenarios.

Program