Related Works

Paper "Video-Induced Visual Invariances" focuses on applying different pre-text tasks on We will change the name of 3D ResNet in our model to "2D+1D ResNet". They will be added in the final version. We will further clarify it in the caption of Table 1. We will add this experiment in our final version. The reason why we didn't compare with CBT and A VSlowFast in Table 3 and For further fair comparison, we will add the number of parameters of each model in Table 3 and 4. Result about fixing the backbone and fine-tune the FC layers was reported only in Table 5 as CCL(FC).