Submissions are evaluated using Categorization Accuracy. For each video sequence in the test set, you will predict the SubjectID to which it belongs. Ranked by average accuracy.
The file should contain a header and have the following format:
Note: label is in int format.
Please read the following regulations carefully.
- The data provided by the competition can only be used for academic purposes.
- This competition is public to the world, but the Competition Organizer approves each user’s request to participate and may elect to disallow participation according to its own considerations. You must register on the Competition Website prior to the Entry Deadline.
- Submission format: Zipped CSV file containing participant’s predictions. Note that the CSV file must have the same name as submission.csv.
- Users: Each participant must create a CodaLab account to register. Only one account per user is allowed.
- Teams: Participants are allowed to form teams. There are no limitations on the number of participants on the team.
- External data: Participants are allowed to use external data. To be fair, the external data you use must be provided to competition participants. Thus, if you use external data, you must make it publicly available and declare it in the competition discussion forum no later than the date specified in the Competition Forums.
- Submissions may not use or incorporate information from hand labeling or human prediction of the training dataset or test dataset for the competition’s target labels. Ergo, solutions involving human labeling of one of the columns in the submission CSV file will be disqualified.
- Submissions may not use or combine manual annotations or manual prediction information for the competition’s target labels. Doing so will cause you to lose your qualification.
- The test set should be used as is, for prediction generation and submissions only. Using the test set data in order to train the model (“pseudo-labeling” or any other technique that exploits the test data in the training process) is strictly prohibited.
- Prize Allocation: 1st place:15,000 CNY 2nd place: 5,000 CNY 3rd place: 2,500 CNY 4th place: 1,000 CNY
- Upon being awarded a prize:
11.1 The prize winner must deliver to the Competition Organizer the final model’s software code or a Github link which contains the source code and model. And we also expect the method associated documentation written in English (1 page), which will be published at the workshop homepage during the workshop. The code must be capable of generating the winning submission and contain a description of the resources required to build and/or run the executable code successfully.
11.2 The prize winner must agree to participate in our ACCV 2020 Workshop, and present their methods and results online.
- If a team wins a monetary prize, Competition Organizer will allocate the prize money in even shares between team members unless the team unanimously contacts the Competition Organizer within three business days following the submission deadline to request an alternative prize distribution.
This competition is sponsored by the Watrix Technology. Watrix will provide prizes as follows:
- First Prize: 15,000CNY
- Second Prize: 5,000CNY
- Third Prize: 2,500CNY
- Fourth Prize: 1,000CNY