Videomae Base Short Finetuned Kinetics

🚀 VideoMAE (base-sized model, fine-tuned on Kinetics-400)

A VideoMAE model pre - trained for 800 epochs in a self - supervised way and fine - tuned in a supervised way on Kinetics - 400, offering efficient video feature learning for classification tasks.

🚀 Quick Start

You can use the raw model for video classification into one of the 400 possible Kinetics - 400 labels.

✨ Features

• VideoMAE is an extension of Masked Autoencoders (MAE) to video.
• Its architecture is similar to a standard Vision Transformer (ViT), with a decoder for predicting pixel values of masked patches.
• By pre - training, it can learn an inner representation of videos for downstream tasks.

💻 Usage Examples

Basic Usage

from transformers import VideoMAEImageProcessor, VideoMAEForVideoClassification
import numpy as np
import torch

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

processor = VideoMAEImageProcessor.from_pretrained("MCG-NJU/videomae-base-short-finetuned-kinetics")
model = VideoMAEForVideoClassification.from_pretrained("MCG-NJU/videomae-base-short-finetuned-kinetics")

inputs = processor(video, return_tensors="pt")

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

predicted_class_idx = logits.argmax(-1).item()
print("Predicted class:", model.config.id2label[predicted_class_idx])

For more code examples, we refer to the documentation.

📚 Documentation

Model description

VideoMAE is an extension of Masked Autoencoders (MAE) to video. The architecture of the model is very similar to that of a standard Vision Transformer (ViT), with a decoder on top for predicting pixel values for masked patches.

Videos are presented to the model as a sequence of fixed - size patches (resolution 16x16), which are linearly embedded. One also adds a [CLS] token to the beginning of a sequence to use it for classification tasks. One also adds fixed sinus/cosinus position embeddings before feeding the sequence to the layers of the Transformer encoder.

By pre - training the model, it learns an inner representation of videos that can then be used to extract features useful for downstream tasks: if you have a dataset of labeled videos for instance, you can train a standard classifier by placing a linear layer on top of the pre - trained encoder. One typically places a linear layer on top of the [CLS] token, as the last hidden state of this token can be seen as a representation of an entire video.

Intended uses & limitations

You can use the raw model for video classification into one of the 400 possible Kinetics - 400 labels.

🔧 Technical Details

Evaluation results

This model obtains a top - 1 accuracy of 79.4 and a top - 5 accuracy of 94.1 on the test set of Kinetics - 400.

BibTeX entry and citation info

misc{https://doi.org/10.48550/arxiv.2203.12602,
  doi = {10.48550/ARXIV.2203.12602},
  url = {https://arxiv.org/abs/2203.12602},
  author = {Tong, Zhan and Song, Yibing and Wang, Jue and Wang, Limin},
  keywords = {Computer Vision and Pattern Recognition (cs.CV), FOS: Computer and information sciences, FOS: Computer and information sciences},
  title = {VideoMAE: Masked Autoencoders are Data - Efficient Learners for Self - Supervised Video Pre - Training},
  publisher = {arXiv},
  year = {2022},
  copyright = {Creative Commons Attribution 4.0 International}
}

📄 License

This model is released under the CC - BY - NC - 4.0 license.