Davide Coccomini

Can you check that all the frames you are passing have the same size?

Hello, we consider 1 frame per second for our experiments but there it can be set as you desire. In general, the multi-identity case is pretty specific and very few...

Can you give me more details?

Hi, follow this: https://github.com/davide-coccomini/MINTIME-Multi-Identity-size-iNvariant-TIMEsformer-for-Video-Deepfake-Detection/issues/4

Hi, are you sure that the weights are loading correctly? Also, I understand why you removed "state_dict" but why did you disabled cudnn?

Hi, if you need the pretrained weights for the version using EfficientNet we can manage to publish it in a few weeks

Just to be sure, you are referring to Table 6? So the correspondences are: Z_1 --> ADM Z_2 --> ADM-G Z_3 --> DDPM Z_4 --> DDIM Z_5 --> LDM Z_6...

Can you confirm that?

Thank you so much!

For the moment, we provided the explanation in the README.md