News - RoadText Competition on Video Text Detection, Tracking and Recognition
02/19/2023Multipage DocVQA Dataset is public!
We have released the dataset for Multipage Document Visual Question Answering (MP-DocVQA). You can find it in the Downloads section under the Task 4 section.
We are currently working on the evaluation protocol to allow you submit your results and be ranked in the leaderboard, but currently it is still closed.
If you are interested in this task, you can find more information in the paper Hierarchical multimodal transformers for Multi-Page DocVQA.
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