News - Document Visual Question Answering
03/05/2015Datasets are now available
Datasets for training and testing are now available for the new tasks for the 2015 edition of the competition:
T1.4 - End-to-End on Born digital images
T2.4 - End-to-End on Focused scene text images
T3.4 - End-to-End on Video sequences
T4.1 - Text Localisation in Incidental scene text images
T4.3 - Word Recognition in Incidental scene text images
T4.1 - End-to-End on Incidental scene text images
In addition, the datasets for the following task have been updated:
T3.1 - Text Localisation in Video sequences
Challenge News
- 09/01/2023
QA Types made public - 02/19/2023
Multipage DocVQA Dataset is public! - 03/31/2021
ICDAR competition deadline extended - 02/11/2021
Infographics Test Set Available - 08/01/2020
The challenge continues in ICDAR 2021
Important Dates
19 February 2023: MP-DocVQA Dataset released.
ICDAR 2021 edition
6 September 2021: Presentation at the Document VQA workshop at ICDAR 2021
30 April 2021: Results available online
10 April 2021: Deadline for Competition submissions
11 February 2021: Test set available
23 December 2020: Release of full training data for Infographics VQA.
10 November 2020: Release of training data subset for new task "Infographics VQA"
CVPR 2020 edition
16-18 June 2020: CVPR workshop
15 May 2020 (23:59 PST): Submission of results
20 April 2020: Test set available
19 March 2020 : Text Transcriptions for Train_v0.1 Documents available
16 March 2020: Training set v0.1 available