
VideoMAE
by MCG-NJU (organization)
[NeurIPS 2022 Spotlight] VideoMAE: Masked Autoencoders are Data-Efficient Learners for Self-Supervised Video Pre-Training (description from the project’s GitHub page)
Repository facts
- Stars
- 1,802
- Forks
- 173
- Open issues and pull requests
- 52
- Primary language
- Python
- License
- Other license
- Owner
- MCG-NJU · Organization
- Created
- Mar 23, 2022
- Last push
- Dec 8, 2023
Topics
Related projects
Projects that share this one’s GitHub topics.
Rank 3,141: OpenGVLab/InternVideo
[ECCV2024] Video Foundation Models & Data for Multimodal Understanding
2,408 starsPythonApache-2.0Last push Jul 2, 2026
Rank 4,872: keyu-tian/SparK
[ICLR'23 Spotlight🔥] The first successful BERT/MAE-style pretraining on any convolutional network; Pytorch impl. of "Designing BERT for Convolutional Networks: Sparse and Hierarc…
1,382 starsPythonMITLast push Jan 23, 2024
Rank 2,049: open-mmlab/mmpretrain
OpenMMLab Pre-training Toolbox and Benchmark
3,860 starsPythonApache-2.0Last push Nov 1, 2024
Rank 3,395: ViTAE-Transformer/ViTPose
The official repo for [NeurIPS'22] "ViTPose: Simple Vision Transformer Baselines for Human Pose Estimation" and [TPAMI'23] "ViTPose++: Vision Transformer for Generic Body Pose Est…
2,198 starsPythonApache-2.0Last push Dec 25, 2025
Rank 1,559: open-mmlab/mmaction2
OpenMMLab's Next Generation Video Understanding Toolbox and Benchmark
5,178 starsPythonApache-2.0Last push Mar 18, 2026
Rank 3,848: open-mmlab/mmaction
An open-source toolbox for action understanding based on PyTorch
1,876 starsPythonApache-2.0Last push Apr 8, 2022