Skip to content

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

Notifications You must be signed in to change notification settings

Singularity0104/NExT-Vid

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

1 Commit
 
 

Repository files navigation

NExT-Vid

This repository will contain the official implementation for our paper:

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

Overview

NExT-Vid is a novel method for effective video representation learning via next-frame prediction in an autoregressive framework.

Coming Soon!

We are currently organizing and preparing the code for public release. Please stay tuned!

About

Learning from Next-Frame Prediction: Autoregressive Video Modeling Encodes Effective Representations

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published