Result
Instructions
For training the model, use only the training set. Do not use validation and test sets.
The organizers request the team to upload the final/updated trained model, inference code, ReadMe file, and algorithm details on the competition website on or before 15th May 2024. If there is a mismatch between the results uploaded, the trained model submitted, and the results obtained by the team's inference code, then the team will not be allowed to continue the competition. The team results will not be displayed on the leaderboard in such a case.
The team member can upload the results only once.
The team member needs to upload results corresponding to a task.
Submission for Task A: Isolated Word Recognition
Submission of Brief Description of Algorithm
- Write a maximum of one page description of your proposed method to solve Isolated Word Recognition tasks and name the file as (description.doc/description.pdf/description.txt/description.latex).
Submission of Results
- The output should be saved as ‘script name_result.txt’ (e.g., english_result.txt) which contains names of test word images and corresponding predictions separated by a tab in each line.
- For multiple languages, create a folder containing all “script name_result.txt” files corresponding to the languages to be considered, create a zip file, and upload it.
Submission of Trained Model
- Create a zip file of the trained model and upload
Submission of Inference Code
- Inference code, requirement.txt with software packages required to run the code, and ReadMe file with instructions for running the code. Make a zip file and upload it.
Submission for Task B: Page Level Recognition and Reading
Submission of Brief Description of Algorithm
- Write a maximum of one page description of your proposed method to solve Page Level Recognition and Reading tasks and name the file as (description.doc/description.pdf/description.txt/description.latex).
Submission of Results
- There should be one output file corresponding to an image. The output should be saved as 'image name_result.txt' (e.g., "12304_result.txt" for page image "12304.jpg"), which contains the predicted text of the complete page image.
- For a language, create a folder name as the language name (e.g., English in the case of the English language), which contains all predicted text files corresponding to all test images of that particular language. For multiple languages, create a folder containing four folders corresponding to four languages, make a zip, and upload it.
Submission of Trained Model
- Create a zip file of the trained model and upload
Submission of Inference Code
- Inference code, requirement.txt with software packages required to run the code, and ReadMe file with instructions for running the code. Make a zip file and upload it.
Submission for Dataset for Task C: Visual Question Answer on Handwritten Documents
Submission of Brief Description of Algorithm
- Write a maximum of one page description of your proposed method to solve Visual Question Answer on Handwritten Documents and name the file as (description.doc/description.pdf/description.txt/description.latex).
Submission of Results
- The output corresponding to all images and questions should be saved in a single file ‘result.json', which contains image, question id, question, and corresponding answer .
- Make a zip and upload.
Submission of Trained Model
- Create a zip file of the trained model and upload
Submission of Inference Code
- Inference code, requirement.txt with software packages required to run the code, and ReadMe file with instructions for running the code. Make a zip file and upload it.