Opening book details…
About this document
VJEPA: Semantic Masking for Action Recognition by Aaron Jetro Alvarez is a document available to read on EtoBox.
- Author
- Aaron Jetro Alvarez
- Language
- EN
Checking…
VJEPA: Semantic Masking for Action Recognition
About this book
The document discusses the VJEPA model, trained on the VidMix2m dataset, which utilizes a Joint-Embedding Predictive Architecture (JEPA) for video feature prediction. It highlights the model
Details
Rate this book
Sign in to rate this book
Quick info
- Language
- en
- Availability
- Checking…