Frans

This PR integrates two TinyCLIP ViT models to the existing model framework with minimal changes. This is possible because TinyCLIP provides a pure ViT-based model, like CLIP. The TinyCLIP model...

Code of End-to-End Spatio-Temporal Action Localisation with Video Transformers

2

Hi, I am trying to reproduce the results stated in your paper End-to-End Spatio-Temporal Action Localisation with Video Transformers by Alexey A. Gritsenko Xuehan Xiong Josip Djolonga Mostafa Dehghani Chen...