This release includes the following:
- A video model based on ViT-B/16 with 8 frames.
- Score matrixs for the ViT-B/32 8 frams video branch and attribute branch.
- Pre-extracted attribute files.
We hope that these resources will be helpful for your research and experimentation with video models. If you have any questions or feedback, please feel free to let us know.
Thank you for your interest in our project!