---
title: VideoMAEv2-giant
canonical_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/VideoMAEv2-giant"
md_url: "https://www.modelscope.cn/models/Shanghai_AI_Laboratory/VideoMAEv2-giant.md"
repository: Shanghai_AI_Laboratory/VideoMAEv2-giant
last_updated: 2025-02-25
license: cc-by-nc-4.0
model_type:
  - VideoMAEv2_Base
architectures:
  - VideoMAEv2_Base
parameters: 1.0B
tensor_type:
  - F32
library_name:
  - pytorch
  - transformer
  - safetensors
frameworks:
  - pytorch
downloads: 1012
stars: 0
tags:
  - vision
  - video-classification
---

# VideoMAEv2-giant

> VideoMAEv2-giant - Shanghai_AI_Laboratory 在 ModelScope 开源的模型。VideoMAE-v2 (giant-sized model, Pretrained on UnlabeledHybrid-1M)

Shanghai_AI_Laboratory/VideoMAEv2-giant 是 ModelScope 魔搭社区上的 1.0B 参数机器学习模型，采用 cc-by-nc-4.0 许可。

- **Repository**: Shanghai_AI_Laboratory/VideoMAEv2-giant
- **License**: cc-by-nc-4.0
- **Parameters**: 1.0B
- **Tags**: vision, video-classification
- **Downloads**: 1012
- **Stars**: 0
- **Last updated**: 2025-02-25

Source: https://www.modelscope.cn/models/Shanghai_AI_Laboratory/VideoMAEv2-giant

---

# VideoMAE-v2 (giant-sized model, Pretrained on UnlabeledHybrid-1M) 

VideoMAEv2-giant model pre-trained for 1200 epochs in a self-supervised way on UnlabeldHybrid-1M dataset. It was introduced in the paper [[CVPR23]VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking](https://arxiv.org/abs/2203.12602) by Wang et al. and first released in [GitHub](https://github.com/OpenGVLab/VideoMAEv2). 


## Intended uses & limitations

You can use the raw model for video feature extraction.

### How to use

Here is how to use this model to extract a video feature:

```python
from transformers import VideoMAEImageProcessor, AutoModel, AutoConfig
import numpy as np
import torch


config = AutoConfig.from_pretrained("OpenGVLab/VideoMAEv2-giant", trust_remote_code=True)
processor = VideoMAEImageProcessor.from_pretrained("OpenGVLab/VideoMAEv2-giant")
model = AutoModel.from_pretrained('OpenGVLab/VideoMAEv2-giant', config=config, trust_remote_code=True)


video = list(np.random.rand(16, 3, 224, 224))




# B, T, C, H, W -> B, C, T, H, W
inputs = processor(video, return_tensors="pt")
inputs['pixel_values'] = inputs['pixel_values'].permute(0, 2, 1, 3, 4)

with torch.no_grad():
  outputs = model(**inputs)
```




### BibTeX entry and citation info

```bibtex
@InProceedings{wang2023videomaev2,
    author    = {Wang, Limin and Huang, Bingkun and Zhao, Zhiyu and Tong, Zhan and He, Yinan and Wang, Yi and Wang, Yali and Qiao, Yu},
    title     = {VideoMAE V2: Scaling Video Masked Autoencoders With Dual Masking},
    booktitle = {Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
    month     = {June},
    year      = {2023},
    pages     = {14549-14560}
}

@misc{videomaev2,
      title={VideoMAE V2: Scaling Video Masked Autoencoders with Dual Masking},
      author={Limin Wang and Bingkun Huang and Zhiyu Zhao and Zhan Tong and Yinan He and Yi Wang and Yali Wang and Yu Qiao},
      year={2023},
      eprint={2303.16727},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}
```