The goal of the Kinetics dataset is to help the computer vision and machine learning communities advance models for video understanding. Given this large human action classification dataset, it may be possible to learn powerful video representations that transfer to different video tasks.
[Insert download link or instructions on how to access the test version]
Don't miss this opportunity to test drive Autodesk Inventor and see how it can transform your design and engineering workflow. Download your free test version today!
Use the Inventor trial to evaluate workflow compatibility , performance with your hardware, and integration with your existing CAD data. If you’re a student, get the free 3-year educational license instead of the 30-day trial.
Explore Autodesk Inventor with a Free Test Version
[Insert download link or instructions on how to access the test version]
Don't miss this opportunity to test drive Autodesk Inventor and see how it can transform your design and engineering workflow. Download your free test version today!
Use the Inventor trial to evaluate workflow compatibility , performance with your hardware, and integration with your existing CAD data. If you’re a student, get the free 3-year educational license instead of the 30-day trial.
Explore Autodesk Inventor with a Free Test Version
1. Possible to use ImageNet checkpoints?
We allow finetuning from public ImageNet checkpoints for the supervised track -- but a link to the specific checkpoint should be provided with each submission.
2. Possible to use optical flow?
Flow can be used as long as not trained on external datasets, except if they are synthetic.
autodesk inventor testversion
3. Can we train on test data without labels (e.g. transductive)?
No.
[Insert download link or instructions on how to
4. Can we use semantic class label information?
Yes, for the supervised track.
performance with your hardware
5. Will there be special tracks for methods using fewer FLOPs / small models or just RGB vs RGB+Audio in the self-supervised track?
We will ask participants to provide the total number of model parameters and the modalities used and plan to create special mentions for those doing well in each setting, but not specific tracks.