# Kinetics-400 Pretraining
Timesformer Large Finetuned K400
TimeSformer is a video classification model based on spatio-temporal attention mechanism, specifically designed for video understanding tasks.
Video Processing
Transformers

T
fcakyon
254
0
Timesformer Base Finetuned K400
TimeSformer is a video classification model based on spatio-temporal attention mechanism, specifically fine-tuned for the Kinetics-400 dataset.
Video Processing
Transformers

T
fcakyon
17
0
Videomae Base Short
VideoMAE is a video self-supervised pretraining model based on Masked Autoencoder (MAE), which learns internal video representations through masked patch prediction, suitable for downstream tasks like video classification.
Video Processing
Transformers

V
MCG-NJU
886
3
Featured Recommended AI Models