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.
This unrated version adds 12 minutes of footage. It includes more intense action, realistic blood effects during sword fights, and deeper character moments.
Report: The Wolverine (2013) Technical Availability The Wolverine
To ensure you are getting a high-quality file and not a poorly compressed copy, check for these technical specs before downloading or encoding:
Do you prefer the or the unrated extended version ? Share public link
This unrated version adds 12 minutes of footage. It includes more intense action, realistic blood effects during sword fights, and deeper character moments.
Report: The Wolverine (2013) Technical Availability The Wolverine
To ensure you are getting a high-quality file and not a poorly compressed copy, check for these technical specs before downloading or encoding:
Do you prefer the or the unrated extended version ? Share public link
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.
The Wolverine 2013 Dual Audio 720p Or 1080p
3. Can we train on test data without labels (e.g. transductive)?
No.
This unrated version adds 12 minutes of footage
4. Can we use semantic class label information?
Yes, for the supervised track.
realistic blood effects during sword fights
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.