Hi, Could you please provide some information on the submission format of the skill predictions? The submission page still states details to follow.. Thank you!

Created by isatwi isatwi
Yes
Thanks Sebastian, since naming convention is such explicit, can we train a separate model on full videos and use it for prediction for full test videos? And then repeat the same for smaller videos, as well?
Perfect thanks
Thanks for letting me know about the oversight! Please provide the output in the same manner as the annotation during planing, in other words, for a given video, please predict the 5 skill categories on a scale from 1 to 5. If you require information whether we are inputting an entire operation video or just a phase from a video, you can rely on the filename, as the format will be identical during testing. I hope this helps! Cheers, Sebastian

Submission format of skill predictions page is loading…