# Video Feature Extraction

VideoMAEv2-giant is an ultra-large-scale video classification model based on self-supervised learning, employing a dual masking strategy for pretraining.

VideoMAEv2-Huge is a self-supervised learning-based video feature extraction model, pre-trained for 1200 epochs on the UnlabeledHybrid-1M dataset.

VideoMAE is a video self-supervised pretraining model based on Masked Autoencoder (MAE), which learns internal video representations by predicting pixel values of masked video patches.

VideoMAE is a video self-supervised pre-training model based on Masked Autoencoder (MAE), which learns video representations by predicting pixel values of masked video patches