[FEATURE] Pretrained model for TimeSformer

[priya-dwivedi]

Is your feature request related to a problem? Please describe. Is it possible to add pretrained weights for the paper TimeSformer This paper extends the Vision Transformer to attention in both space and time.

Describe the solution you'd like Code and pretrained weights for this would be great.

Describe alternatives you've considered A clear and concise description of any alternative solutions or features you've considered.

Additional context Add any other context or screenshots about the feature request here.