Video augmentation methods for Pre-trained model

[Aayush2007]

What are the video augmentation options used in the pre-trained model ([Dropbox]) ? In the code I can see that these are the ones uncommented, is that the case for the pretrained model? dataset/dataloader_video.py

[ycmin95]

Yes，as mentioned in our paper, we adopted three kinds of data augmentation strategies (random crop, horizontal flip and random temporal scaling) during training.

[atonyo11]

@ycmin95, Why you choose horizontal flip methods? Does it change the meaning of sign?

[ycmin95]

Relevant information can be found in the Table 3. (Ablation results of augmentation) of the supplymentary material, which can be download from: https://openaccess.thecvf.com/content/ICCV2021/supplemental/Min_Visual_Alignment_Constraint_ICCV_2021_supplemental.zip