Lizhe (Lucas) Chen

Pretraining VideoMAE on HMDB51

7

Hi Zhan, Thank you for your excellent work! We are surprised by VideoMAE's data efficiency (paper section 4.3), especially on small datasets like HMDB51. We are trying to use your...

Hi Haokui, In your paper, the equation (2) applied TanH function on the C_t before concatenation and feeding them to the refinement R_t. But when I was looking at your...