KVP10k : A Comprehensive Dataset for Key-Value Pair Extraction in Business Documents
- Oshri Naparstek
- Roi Pony
- et al.
- 2024
- ICDAR 2024
Bio
Ahmed Nassar joined the IBM Research – Zurich Laboratory in 2021 as a post-doctoral researcher in 'Scalable Knowledge Ingestion' group. His main research interest are in computer vision and deep learning.
His previous work has covered detecting street-side objects through CNNs and assigning their correspondence in multiple views.
Publications
Docling Technical Report
- 2024
- arXiv
ESG Accountability Made Easy: DocQA at Your Service
- Lokesh Mishra
- Cesar Berrospi Ramis
- et al.
- 2024
- AAAI 2024
MolGrapher: Graph-based Visual Recognition of Chemical Structures
- Lucas Morin
- Martin Danelljan
- et al.
- 2023
- ICCV 2023
Optimized Table Tokenization for Table Structure Recognition
- Maxim Lysak
- Ahmed Nassar
- et al.
- 2023
- ICDAR 2023
DocLayNet: A Large Human-Annotated Dataset for Document-Layout Segmentation
- Birgit Pfitzmann
- Christoph Auer
- et al.
- 2022
- KDD 2022
TableFormer: Table Structure Understanding with Transformers
- 2022
- CVPR 2022
Robust PDF Document Conversion Using Recurrent Neural Networks
- Nikolaos Livathinos
- Cesar Berrospi
- et al.
- 2021
- IAAI 2021
Patents
- US
- 11687700
Projects
Blog posts
Response to accusations regarding TableFormer paper
NewsAhmed Nassar, Nikos Livathinos, Maxim Lysak, and Peter Staar
Top collaborators
PS
Peter Staar
Principal RSM; Master Inventor; Manager of `AI for Knowledge` group.
NL
Nikos Livathinos
Senior Software Engineer & Certified Architect
CA
Christoph Auer
Senior Research Scientist
ML
Maksym Lysak
Software Engineering & R&D of AI Systems