News - RoadText Competition on Video Text Detection, Tracking and Recognition
09/01/2023QA Types made public
We are glad to announce that we have make public the question types for Single-Page DocVQA and InfographicsVQA datasets. However, we won't release it for the test sets, as we believe that this should not be used as any kind of help at the time of answering the questions, but to better interpret the method's results. In addition, the public evaluation tool in the RRC platform already provides this information.
Therefore, we have released the question types only for training and validation set of the SP-DocVQA, and validation set of InfographicsVQA. You can find the updated links in the downloads section.
We hope this helps you in your research,
The DocVQA team
Challenge News
Important Dates
24th -31st December 2022: Initial website launch
24th -31st December 2022: Initial training data release
15 February 2023: Full training data along with test data release
1st March 2023: Submission site open
20 March 2023: Deadline for competition submissions
27 March 2023: Extended deadline for competition submissions
1 May 2023: Initial submission of competition report
21 - 26 August 2023: Result announcement and presentation
All deadlines are in the AoE time zone