Review Comments
- Proposed Introduction - "Where is the skeleton facing ? Hope we didn't scare you. This problem is an adapted version of the ORIENTME which adds a few more layers of complexity to the task of predicting the orientation of a 3D model from a single image.
This problem introduces a non-uniform distribution of samples in the training and the test set. And most importantly, this problem also evaluates out-of-distribution generalization.
For input you will be given a large number of images, for about half of them, we have measured the orientation of the skeleton. But to be able to stitch all those images together, you have to figure out how to predict
the orientation
of the skeleton for the rest of the images."
- In Evaluation Criteria, add the formula for Mean Squared Error