Please see the Schedule page for the competition presentations.
Challenge Winners:
| Award | Team |
| Winner Task 1 & Winner Task 2 | PingAn-OneConnect-Gammalab-DQA |
| First Runner up Task 1 | Structural LM |
| Second Runner up Task 1 | IIE.SECAI-CUC |
| First Runner up Task 2 | iFLYTEK-DOCR |
The CVPR 2020 “Document Visual Question Answering” (DocVQA) challenge, focuses on a specific type of Visual Question Answering task, where visually understanding the information on a document image is necessary in order to provide an answer. This goes over and above passing a document image through OCR, and involves understanding all types of information conveyed by a document. Textual content (handwritten or typewritten), non-textual elements (marks, tick boxes, separators, diagrams), layout (page structure, forms, tables), and style (font, colours, highlighting), to mention just a few, are pieces of information that can be potentially necessary for responding to the question at hand.
Please check out additional challenge details at: https://rrc.cvc.uab.es/?ch=17
Important Challenge Dates:
13 March 2020: Training set available
15 April 2020: Test set available
30 April 2020: Submission of results
15 June 2020: CVPR workshop
Challenge Organizers
Minesh Mathew, IIIT Hyderabad
Rubèn P. Tito, CVC, UAB
Manuel Carbonell, CVC, UAB
Lluís Gómez i Bigordà, CVC, UAB
Marçal Rusiñol, CVC, UAB
Manuel Carbonell, CVC, UAB
Josep Lladós, CVC, UAB
C. V. Jawahar, IIIT Hyderabad
Dimosthenis Karatzas, CVC, UAB
R. Manmatha, Amazon
More information about the challenge organizers: https://rrc.cvc.uab.es/?ch=17&com=contact
Contact
Email: cvpr2020.document.workshop [at] gmail.com
Sponsors
CVPR2020 Workshop on Text and Documents in the Deep Learning Era 