Accepted Papers
Best Paper:
Task Grouping for Multilingual Text Recognition. Jing Huang (Facebook); Kevin J Liang (Facebook); Rama Kovvuri (Facebook); Tal Hassner (Facebook AI). [Paper]
Accepted Papers
Task Grouping for Multilingual Text Recognition (Oral). Jing Huang (Facebook); Kevin J Liang (Facebook); Rama Kovvuri (Facebook); Tal Hassner (Facebook AI). [Paper]
End-to-end Document Recognition and Understanding with Dessurt (Oral). Brian L Davis (Brigham Young University); Bryan S Morse (Brigham Young University); Chris Tensmeyer (Adobe Research); Brian Price (Adobe); Curtis Wigington (Adobe Research); Vlad I Morariu (Adobe Research). [Paper]
OCR-IDL: OCR Annotations for Industry Document Library Dataset (Oral). Ali Furkan Biten (Computer Vision Center); Rubèn Tito (Computer Vision Center); Lluis Gomez (Universitat Autónoma de Barcelona); Ernest Valveny (Universitat Autónoma de Barcelona); Dimosthenis Karatzas (Computer Vision Centre). [Paper]
On Calibration of Scene-Text Recognition Models (Oral). Ron Slossberg (Technion); Oron Anschel (AWS); Ron Litman (Amazon); Amir Markovitz (Amazon); Aviad Aberdam (Amazon); Shahar Tsiper (Amazon); Shai Mazor (Amazon); Jonathan Wu (Amazon); R. Manmatha (Amazon). [Paper]
Self-paced learning to improve text row detection in historical documents with missing labels. Mihaela Gaman (University of Bucharest); Radu Tudor Ionescu (University of Bucharest); Marius Popescu (University of Bucharest). [Paper] [Poster]
Incorporating self-attention mechanism and multi-task learning into scene text detection. Ning Ding (Tsinghua University); Liangrui Peng (Tsinghua University). [Poster] [Video]
Doc2Graph: a Task Agnostic Document Understanding Framework based on Graph Neural Networks. Andrea Gemelli (University of Florence); Sanket Biswas (Computer Vision Centre); Enrico Civitelli (University of Florence); Josep Llados ("Computer Vision Center, Barcelona"); Prof. Dr. Simone Marinai ("University of Florence, Italy - Pattern Rec"). [Paper] [Poster]
MUST-VQA: MUltilingual Scene-text VQA. Emanuele Vivoli (University of Florence); Ali Furkan Biten (Computer Vision Center); Andres Mafla (Computer Vision Center); Dimosthenis Karatzas (Computer Vision Centre); Lluis Gomez (Universitat Autónoma de Barcelona). [Paper] [Poster] [Video]
Spotlight Presentations (Extended Abstracts)
Character decomposition to resolve class imbalance problem in Hangul OCR. Geonuk Kim (AIRS Company, Hyundai Motors); jaemin son (Hyundai Motor Group, AIRS company); kanghyu lee (Hyundai motors); Jaesik Min (Hyundai Motor Group). [Paper] [Poster]
TextAdaIN: Paying Attention to Shortcut Learning in Text Recognizers. Oren Nuriel (Amazon); Ron Litman (Amazon); Sharon Fogel (Amazon).
Shift Variance in Scene Text Detection. Markus Glitzner (MVTec Software GmbH); Jan-Hendrik Neudeck (MVTec Software GmbH); Philipp Härtinger (MVTec Software GmbH). [Paper] [Poster] [Video]
Rooms with Text: A Dataset for Overlaying Text Detection. Oleg Smirnov (Amazon); Aditya Tewari (Amazon.com). [Paper]