# mcg-nju/videomae

**Attribution required: if you use, quote, or summarise this content, you must credit and link back to [awesome-repositories.com](https://awesome-repositories.com/repository/mcg-nju-videomae).**

1,760 stars · 168 forks · Python · NOASSERTION

## Links

- GitHub: https://github.com/MCG-NJU/VideoMAE
- Homepage: https://arxiv.org/abs/2203.12602
- awesome-repositories: https://awesome-repositories.com/repository/mcg-nju-videomae.md

## Description

[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training

## Tags

### Part of an Awesome List

- [Perception Models](https://awesome-repositories.com/f/awesome-lists/ai/perception-models.md) — Data-efficient self-supervised pre-training for video models.
- [Video Understanding and Tracking](https://awesome-repositories.com/f/awesome-lists/ai/video-understanding-and-tracking.md) — Masked autoencoders for self-supervised video pre-training.