Namespace AiDotNet.Video.ActionRecognition
Classes
- SlowFast<T>
SlowFast Networks for Video Recognition.
- TimeSformer<T>
TimeSformer: Is Space-Time Attention All You Need for Video Understanding?
- VideoMAE<T>
Video Masked Autoencoder (VideoMAE) for video understanding and action recognition.
Enums
- AttentionType
Attention type for TimeSformer.